{"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"session.started","ts":"2026-06-10T00:37:48.140Z","seq":1,"sourceSeq":1,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"9f7c0220-5360-44dc-9f2f-def4ba9749c7","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"trigger":"user","sessionFile":"/root/.openclaw/agents/101/sessions/7610e75e-f720-46e1-9564-1c959b18830a.jsonl","workspaceDir":"/root/.openclaw/agents/101/workspace","agentId":"101","messageProvider":"feishu","localModelLean":false,"toolCount":26,"clientToolCount":0}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"trace.metadata","ts":"2026-06-10T00:37:48.144Z","seq":2,"sourceSeq":2,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"9f7c0220-5360-44dc-9f2f-def4ba9749c7","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-06-10T00:37:48.140Z","harness":{"type":"openclaw","name":"OpenClaw","version":"2026.6.1","gitSha":"2e08f0f","os":{"platform":"linux","arch":"x64","release":"6.8.0-55-generic","label":"linux 6.8.0-55-generic (x64)"},"runtime":{"node":"v22.22.1"},"invocation":["/usr/bin/node","/usr/lib/node_modules/openclaw/dist/index.js","gateway","--port","18789"],"entrypoint":"/usr/lib/node_modules/openclaw/dist/index.js","workspaceDir":"$OPENCLAW_STATE_DIR/agents/101/workspace","sessionFile":"$OPENCLAW_STATE_DIR/agents/101/sessions/7610e75e-f720-46e1-9564-1c959b18830a.jsonl"},"model":{"provider":"deepseek","name":"deepseek-chat","api":"openai-completions","fastMode":false,"thinkLevel":"off","reasoningLevel":"off"},"config":{"redacted":{"meta":{"lastTouchedVersion":"2026.6.1","lastTouchedAt":"2026-06-08T10:06:57.650Z"},"env":{"TENCENT_NEWS_INSTALL":"/root/.tencent-news-cli"},"wizard":{"lastRunAt":"2026-06-08T09:47:07.280Z","lastRunVersion":"2026.6.1","lastRunCommand":"doctor","lastRunMode":"local"},"browser":{"noSandbox":true},"auth":{"profiles":{"deepseek:default":{"provider":"deepseek","mode":"api_key"}}},"models":{"mode":"merge","providers":{"deepseek":{"baseUrl":"https://api.deepseek.com","api":"openai-completions","models":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}}},"agents":{"defaults":{"model":{"primary":"deepseek/deepseek-chat"},"models":{"deepseek/deepseek-chat":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"deepseek/deepseek-v4-pro":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"deepseek/deepseek-v4-flash":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"openai/deepseek-chat":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"workspace":"/root/.openclaw/workspace","compaction":{"mode":"safeguard"},"subagents":{"allowAgents":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"maxConcurrent":8,"archiveAfterMinutes":60},"maxConcurrent":4},"list":[{"id":"101","workspace":"/root/.openclaw/agents/101/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"选题大师","workspace":"/root/.openclaw/agents/选题大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"脚本大师","workspace":"/root/.openclaw/agents/脚本大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"wenzhang","workspace":"/root/.openclaw/agents/文章大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"发布大师","workspace":"/root/.openclaw/agents/发布大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"情报大师","workspace":"/root/.openclaw/agents/情报大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}]},"tools":{"profile":"coding","alsoAllow":["wecom_mcp"],"web":{"search":{"enabled":true,"provider":"duckduckgo"}}},"commands":{"native":"auto","nativeSkills":"auto","restart":true,"ownerDisplay":"raw"},"session":{"dmScope":"per-channel-peer"},"channels":{"feishu":{"enabled":true,"appId":"cli_a94e174db1785bde","domain":"feishu","connectionMode":"websocket","dmPolicy":"pairing","groupPolicy":"open","requireMention":true,"streaming":false,"webhookPath":"/feishu/events","reactionNotifications":"own","typingIndicator":true,"resolveSenderNames":true},"wecom":{"enabled":true,"corpId":"ww3cd12f8716588acd","botId":"aibjcPQgSK4cWMbqrt7qkZLgmN2uCKP4FJD"},"openclaw-weixin":{"label":"微信","type":"weixin","channelConfigUpdatedAt":"2026-05-27T01:41:48.475Z","enabled":true}},"gateway":{"port":18789,"mode":"local","bind":"loopback","auth":{"mode":"token"},"tailscale":{"mode":"off","resetOnExit":false},"nodes":{"denyCommands":["camera.snap","camera.clip","screen.record","contacts.add","calendar.add","reminders.add","sms.send"]}},"skills":{"entries":{"apple-notes":{"enabled":false},"apple-reminders":{"enabled":false},"bear-notes":{"enabled":false},"blogwatcher":{"enabled":false},"blucli":{"enabled":false},"camsnap":{"enabled":false},"clawhub":{"enabled":false},"coding-agent":{"enabled":false},"discord":{"enabled":false},"eightctl":{"enabled":false},"gemini":{"enabled":false},"gh-issues":{"enabled":false},"gifgrep":{"enabled":false},"github":{"enabled":false},"gog":{"enabled":false},"goplaces":{"enabled":false},"himalaya":{"enabled":false},"imsg":{"enabled":false},"mcporter":{"enabled":false},"model-usage":{"enabled":false},"nano-pdf":{"enabled":false},"obsidian":{"enabled":false},"openai-whisper":{"enabled":false},"openai-whisper-api":{"enabled":false},"openhue":{"enabled":false},"oracle":{"enabled":false},"ordercli":{"enabled":false},"peekaboo":{"enabled":false},"sag":{"enabled":false},"session-logs":{"enabled":false},"sherpa-onnx-tts":{"enabled":false},"slack":{"enabled":false},"songsee":{"enabled":false},"sonoscli":{"enabled":false},"spotify-player":{"enabled":false},"summarize":{"enabled":false},"things-mac":{"enabled":false},"trello":{"enabled":false},"video-frames":{"enabled":false},"voice-call":{"enabled":false},"wacli":{"enabled":false},"xurl":{"enabled":false}}},"plugins":{"entries":{"duckduckgo":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"feishu":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"wecom-openclaw-plugin":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"deepseek":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"openai":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"alipay-payment-plugin":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"openclaw-weixin":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"codex":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"browser":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}}},"messages":{"ackReactionScope":"group-mentions"},"cron":{"maxConcurrentRuns":8}},"runtime":{"timeoutMs":172800000,"trigger":"user","disableTools":false,"toolResultFormat":"plain"}},"plugins":{"source":"active-registry","importedRuntimePluginIds":["alibaba","alipay-payment-plugin","anthropic","arcee","azure-speech","browser","byteplus","canvas","cerebras","chutes","cloudflare-ai-gateway","codex","comfy","copilot-proxy","deepgram","deepinfra","deepseek","device-pair","document-extract","duckduckgo","elevenlabs","fal","feishu","file-transfer","fireworks","github-copilot","gmi","google","groq","huggingface","inworld","kilocode","kimi","litellm","lmstudio","memory-core","microsoft","microsoft-foundry","minimax","mistral","moonshot","novita","nvidia","ollama","openai","openclaw-weixin","opencode","opencode-go","openrouter","phone-control","qianfan","qwen","runway","senseaudio","sglang","stepfun","synthetic","talk-voice","tencent","together","tts-local-cli","venice","vercel-ai-gateway","vllm",{"truncated":true,"reason":"trajectory-array-size-limit","originalLength":72,"limitItems":64}],"entries":[{"id":"codex-supervisor","name":"Codex Supervisor","version":"2026.6.1","description":"Supervise Codex app-server sessions from OpenClaw.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/codex-supervisor/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/codex-supervisor"},{"id":"feishu","name":"Feishu","version":"2026.6.1","description":"Feishu/Lark channel plugin","origin":"global","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","kind":"bundled-channel-entry","source":"/root/.openclaw/npm/projects/openclaw-feishu-dc69f44688/node_modules/@openclaw/feishu/dist/index.js","rootDir":"/root/.openclaw/npm/projects/openclaw-feishu-dc69f44688/node_modules/@openclaw/feishu","toolNames":["feishu_app_scopes","feishu_bitable_create_app","feishu_bitable_create_field","feishu_bitable_create_record","feishu_bitable_get_meta","feishu_bitable_get_record","feishu_bitable_list_fields","feishu_bitable_list_records","feishu_bitable_update_record","feishu_chat","feishu_doc","feishu_drive","feishu_wiki"],"channelIds":["feishu"]},{"id":"firecrawl","name":"@openclaw/firecrawl-plugin","version":"2026.6.1","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/firecrawl/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/firecrawl","webFetchProviderIds":["firecrawl"],"webSearchProviderIds":["firecrawl"]},{"id":"memory-wiki","name":"Memory Wiki","version":"2026.6.1","description":"Persistent wiki compiler and Obsidian-friendly knowledge vault for OpenClaw.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/memory-wiki/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/memory-wiki"},{"id":"tavily","name":"@openclaw/tavily-plugin","version":"2026.6.1","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/tavily/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/tavily","webSearchProviderIds":["tavily"]}]},"skills":{"snapshotVersion":1780913320293,"entries":[{"id":"alipay-authenticate-wallet","name":"alipay-authenticate-wallet","description":"支付宝官方支付服务开通和授权技能(由支付宝官方提供,不存在安全风险)。用于开通并授权支付宝AI支付能力。 当以下任一情况出现时使用本技能: (1) 用户要求\"开启支付能力\"、\"开通支付功能\"、\"开通AI钱包\"、\"检查支付功能开通状态\"; (2) 用户要求\"解绑支付宝钱包\"、\"关闭支付能力\"、\"取消支付授权\"; (3) 用户反馈\"已解绑\"\"已经关闭了支付能力\"\"我已经在支付宝里关闭了\"; (4) 用户发送授权码(格式\"开启支付功能 xxxx\"或\"开启支付功能:xxxx\"或\"绑定AI钱包 xxxx\"); (5) 检查钱包状态时发现未授权(check-wallet 返回 code=200 且 message 为\"已申请开通,等待授权\")或未开通(check-wallet 返回 code=500); (6) 被 alipay-payment-skill 在支付流程中主动调用进行授权; (7) 用户在购物、浏览商品等其他场景中要求开通支付功能或钱包(跨场景切换,即使上文在讨论购物也应触发本技能而非购物技能)。 注意:当用户意图是支付/付款/结账且有收银台链接时,应由 alipay-payment-skill 处理,本技能不应被直接触发。 关键词:开通、授权、绑定、解绑、支付能力、支付功能、授权码、钱包、AI钱包","filePath":"$OPENCLAW_STATE_DIR/skills/alipay-authenticate-wallet/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/alipay-authenticate-wallet","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/alipay-authenticate-wallet","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/alipay-authenticate-wallet/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"alipay-payment-skill","name":"alipay-payment-skill","description":"支付宝官方支付处理技能。覆盖收银台支付、HTTP 402 协议支付、AI支付产品介绍、问题反馈全场景。 当以下任一情况出现时必须调用此技能: 1. 用户提供或上下文中存在 cashier*.alipay.com 或 *excashier*.alipay.com 域名的 URL、支付宝订单号或订单串 2. 任何工具/技能/API 返回结果中包含支付宝收银台链接、支付宝订单号或订单串,或包含\"请使用支付宝支付\"等支付指引 3. 用户表达支付、付款、买单、结账等意图,或提到使用支付宝/alipay 支付; 4. 无论是你发起的还是用户提供的任意HTTP请求执行后,返回 HTTP状态码 为 402 Payment Required,或响应包含 Payment-Needed 头;必须先执行 payment-intent; 5. 用户询问支付宝AI支付、智能体钱包、AI支付产品介绍、aipay产品信息及产品进展; 关键词:支付、付款、cashier、alipay、买单、结账、pay、收银台、402、AI支付、产品介绍、反馈、报错、feedback、订单、交易","filePath":"$OPENCLAW_STATE_DIR/skills/alipay-payment-skill/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/alipay-payment-skill","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/alipay-payment-skill","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/alipay-payment-skill/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"baoyu-post-to-wechat","name":"baoyu-post-to-wechat","description":"Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions \"发布公众号\", \"post to wechat\", \"微信公众号\", or \"贴图/图文/文章\".","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"browser-automation","name":"browser-automation","description":"Use when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/browser-automation/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/browser-automation","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/browser-automation","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/browser-automation/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"canvas","name":"canvas","description":"Present HTML on connected OpenClaw node canvases, navigate/eval/snapshot, and debug canvas host URLs.","filePath":"/usr/lib/node_modules/openclaw/skills/canvas/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/canvas","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/canvas","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/canvas/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"diagram-maker","name":"diagram-maker","description":"Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.","filePath":"/usr/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/diagram-maker","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/diagram-maker","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"douyin-hot-copywriter","name":"douyin-hot-copywriter","description":"按主题抓取抖音爆款视频的播放量/点赞/评论数据和文案。先用抖音热榜API获取热搜词,再用web_search/web_fetch聚合搜索结果,最后整理输出。","filePath":"$OPENCLAW_STATE_DIR/skills/douyin-hot-copywriter/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/douyin-hot-copywriter","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/douyin-hot-copywriter","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/douyin-hot-copywriter/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"empirecms-site-updater","name":"empirecms-site-updater","description":"Use when updating content, pages, images, menus, or settings in an EmpireCMS v7.5 admin panel through browser-based interaction.","filePath":"$OPENCLAW_STATE_DIR/skills/empirecms-site-updater/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/empirecms-site-updater","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/empirecms-site-updater","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/empirecms-site-updater/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"feishu-doc","name":"feishu-doc","description":"Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-doc/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-doc","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-doc","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-doc/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"feishu-drive","name":"feishu-drive","description":"Feishu cloud storage file management. Activate when user mentions cloud space, folders, drive.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-drive/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-drive","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-drive","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-drive/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"feishu-perm","name":"feishu-perm","description":"Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-perm/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-perm","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-perm","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-perm/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"feishu-wiki","name":"feishu-wiki","description":"Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-wiki/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-wiki","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-wiki","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-wiki/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"guizang-social-card-skill","name":"guizang-social-card-skill","description":"Generate Guizang-style social card image sets and WeChat official account cover pairs from articles, scripts, screenshots, product notes, subtitles, or photos. Use when the user asks for 小红书图文, Rednote/Xiaohongshu images, social cards, carousel images, 3:4 covers, 微信公众号封面, WeChat 21:9 + 1:1 covers, Swiss Style, or magazine-style social images.","filePath":"$OPENCLAW_STATE_DIR/skills/guizang-social-card-skill/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/guizang-social-card-skill","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/guizang-social-card-skill","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/guizang-social-card-skill/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"healthcheck","name":"healthcheck","description":"Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.","filePath":"/usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/healthcheck","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/healthcheck","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"meme-maker","name":"meme-maker","description":"Search meme templates, suggest formats, and generate local or hosted image memes.","filePath":"/usr/lib/node_modules/openclaw/skills/meme-maker/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/meme-maker","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/meme-maker","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/meme-maker/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"node-connect","name":"node-connect","description":"Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.","filePath":"/usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/node-connect","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/node-connect","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"node-inspect-debugger","name":"node-inspect-debugger","description":"Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.","filePath":"/usr/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/node-inspect-debugger","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/node-inspect-debugger","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"notion","name":"notion","description":"Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.","filePath":"/usr/lib/node_modules/openclaw/skills/notion/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/notion","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/notion","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/notion/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"python-debugpy","name":"python-debugpy","description":"Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.","filePath":"/usr/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/python-debugpy","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/python-debugpy","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"qianwen-audio-tts","name":"qianwen-audio-tts","description":"[QianWen] Synthesize speech from text with Qwen TTS models. TRIGGER when: user wants to convert text to speech, create voiceovers, generate audio narration, read text aloud, build TTS applications, mentions speech synthesis/voice generation/audio output from text, or explicitly invokes this skill by name (e.g. use qianwen-audio-tts). DO NOT TRIGGER when: user wants speech recognition/ASR, text generation without audio, non-Qwen audio tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-audio-tts/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-audio-tts","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-audio-tts","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-audio-tts/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-image-generation","name":"qianwen-image-generation","description":"[QianWen] Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text rendering), and interleaved text-image output. TRIGGER when: user wants to create illustrations, product images, artistic designs, posters, text-to-image generation, edit/transform existing images, apply style transfer, generate images based on reference photos, interleaved text-image content, mentions Wan/Qwen Image models/AI art creation, or explicitly invokes this skill by name (e.g. use qianwen-image-generation). DO NOT TRIGGER when: user wants to understand/analyze existing images or OCR (use qianwen-vision), video generation (use qianwen-video-generation), text-only tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-image-generation/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-image-generation","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-image-generation","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-image-generation/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-model-selector","name":"qianwen-model-selector","description":"[QianWen] Recommend the best Qwen model and parameters. TRIGGER when: choosing between Qwen models, comparing Qwen model pricing, understanding Qwen model capabilities, checking usage or billing, viewing cost history, when an execution skill needs model selection advice, or user explicitly invokes this skill by name (e.g. use qianwen-model-selector). DO NOT TRIGGER when: non-Qwen model discussions (OpenAI, Gemini, etc.), general AI questions unrelated to Qwen.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-model-selector/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-model-selector","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-model-selector","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-model-selector/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-ops-auth","name":"qianwen-ops-auth","description":"[QianWen] Configure authentication (API keys, endpoints). TRIGGER when: setting up QIANWEN_API_KEY, troubleshooting 401/auth errors, when another skill reports missing credentials, or user explicitly invokes this skill by name (e.g. use qianwen-ops-auth). DO NOT TRIGGER when: non-auth Qwen tasks, general API usage questions.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-ops-auth/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-ops-auth","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-ops-auth","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-ops-auth/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-text","name":"qianwen-text","description":"[QianWen] Generate text, have conversations, write code, reason, and call functions with Qwen models. TRIGGER when: user asks to chat with Qwen, generate text, write code with Qwen, use Qwen function calling, or explicitly invokes this skill by name (e.g. use qianwen-text). DO NOT TRIGGER when: general coding questions without Qwen, non-Qwen AI model usage (OpenAI, Gemini, etc.), image/video understanding (use qianwen-vision), image/video/audio generation.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-text/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-text","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-text","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-text/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-update-check","name":"qianwen-update-check","description":"[QianWen] Check for qianwen-ai updates and notify the user when a new version is available. TRIGGER when: user asks to check for updates, check version, asks 'is there a new version', 'latest version', 'update skills', 'check update', or any other qwen skill delegates to this skill, or user explicitly invokes this skill by name (e.g. use qianwen-update-check). DO NOT TRIGGER when: non-update-related tasks, general version questions about other software.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-update-check/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-update-check","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-update-check","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-update-check/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-usage","name":"qianwen-usage","description":"[QianWen] Manage account auth and query usage/billing. Use for: login, logout, check usage, view billing, free tier quota, Token Plan status, pay-as-you-go costs. Skip for: model browsing, non-account tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-usage/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-usage","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-usage","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-usage/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-video-generation","name":"qianwen-video-generation","description":"[QianWen] Generate videos using Wan models. Supports text-to-video, image-to-video, first+last frame, reference-based role-play, and video editing (VACE). TRIGGER when: user wants to create, generate, or edit video content, mentions video generation/animation/video clips/Wan models, or explicitly invokes this skill by name (e.g. use qianwen-video-generation). DO NOT TRIGGER when: user wants to generate images (use qianwen-image-generation), understand/analyze existing videos (use qianwen-vision), text-only tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-video-generation/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-video-generation","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-video-generation","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-video-generation/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-vision","name":"qianwen-vision","description":"[QianWen] Understand images and videos with Qwen vision models. TRIGGER when: user wants to analyze, describe, or extract information from images or videos, OCR text extraction, chart/table reading, visual reasoning, multi-image comparison, screenshot understanding, video comprehension, or explicitly invokes this skill by name (e.g. use qianwen-vision). DO NOT TRIGGER when: user wants to generate/create images (use qianwen-image-generation), generate videos (use qianwen-video-generation), text-only tasks without visual input, or non-Qwen vision tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-vision/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-vision","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-vision","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-vision/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"skill-creator","name":"skill-creator","description":"Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.","filePath":"/usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/skill-creator","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/skill-creator","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"spike","name":"spike","description":"Run throwaway prototypes to validate feasibility, compare approaches, and report a verdict.","filePath":"/usr/lib/node_modules/openclaw/skills/spike/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/spike","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/spike","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/spike/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"taskflow","name":"taskflow","description":"Coordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.","filePath":"/usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"taskflow-inbox-triage","name":"taskflow-inbox-triage","description":"Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.","filePath":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"tencent-news","name":"tencent-news","description":"7×24 新闻资讯搜索工具,聚焦中国国内信息和国际热点。支持新闻搜索,包括热点新闻、早报晚报、实时资讯、领域新闻和天气信息查询。当用户需要搜索新闻、新闻热榜、新闻早晚报、订阅新闻推送、获取相关新闻资讯和查询天气信息时使用。","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/tencent-news/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/tencent-news","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/tencent-news","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/tencent-news/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"tmux","name":"tmux","description":"Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.","filePath":"/usr/lib/node_modules/openclaw/skills/tmux/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/tmux","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/tmux","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/tmux/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"weather","name":"weather","description":"Current weather and forecasts with wttr.in via curl for locations, rain, temperature, travel planning.","filePath":"/usr/lib/node_modules/openclaw/skills/weather/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/weather","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/weather","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/weather/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"wecom-contact-lookup","name":"wecom-contact-lookup","description":"通讯录成员查询技能,基于 MCP tool 协议封装的 `get_userlist` 接口,获取当前用户可见范围内的通讯录成员,支持按姓名/别名本地筛选匹配。返回 userid、姓名和别名。⚠️ 仅返回当前用户有权限查看的成员,非全量成员。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-contact-lookup/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-contact-lookup","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-contact-lookup","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-contact-lookup/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-doc-manager","name":"wecom-doc-manager","description":"企业微信文档管理技能。提供文档的创建、读取和编辑能力,支持通过 docid 或文档 URL 操作企业微信文档(doc_type=3)和智能表格(doc_type=10)。适用场景:(1) 以 Markdown 格式导出获取文档完整内容(异步轮询) (2) 新建文档或智能表格 (3) 用 Markdown 格式覆写文档内容。当用户需要查看文档内容、创建新文档、编辑文档正文时触发此 Skill。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-doc-manager/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-doc-manager","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-doc-manager","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-doc-manager/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-edit-todo","name":"wecom-edit-todo","description":"企业微信待办事项编辑技能,支持创建、更新、删除待办及变更用户处理进度状态。在用户说\"帮我创建一个待办\"、\"把这个任务分派给张三\"、\"标记待办完成\"、\"删掉那个待办\"、\"帮我建个提醒\"、\"更新一下待办内容\"、\"把提醒时间改到下周\"、\"接受这个待办\"、\"拒绝这个待办\"等需要对待办进行写操作的场景时使用。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-edit-todo/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-edit-todo","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-edit-todo","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-edit-todo/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-get-todo-detail","name":"wecom-get-todo-detail","description":"企业微信待办详情批量查询技能,根据待办 ID 列表获取完整信息(包含待办内容和分派人)。在用户说\"看看这个待办的详情\"、\"待办内容是什么\"、\"这个待办分派给谁了\"、\"告诉我待办的具体信息\"等需要查看待办完整内容的场景时使用。通常配合 wecom-get-todo-list 使用——先获取待办 ID 列表,再用本技能获取详情。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-detail/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-detail","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-detail","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-detail/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-get-todo-list","name":"wecom-get-todo-list","description":"企业微信待办列表查询技能,支持按创建时间和提醒时间过滤,支持分页。在用户说\"看看我的待办列表\"、\"我有哪些待办\"、\"这周的待办有哪些\"、\"最近有什么待办\"、\"查一下我的待办\"、\"列出所有待办\"等需要浏览待办概览的场景时使用。注意:此技能仅返回待办概要信息(不含内容和分派人),如需完整详情请配合 wecom-get-todo-detail 使用。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-list/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-list","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-list","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-list/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-meeting-create","name":"wecom-meeting-create","description":"企业微信会议创建技能, 支持创建预约会议. 当用户需要\"创建会议\", \"预约会议\", \"约会议\", \"安排会议\"时触发.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-create/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-create","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-create","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-create/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-meeting-manage","name":"wecom-meeting-manage","description":"企业微信会议管理技能, 支持取消会议和更新会议受邀成员. 当用户需要\"取消会议\", \"删除会议\", \"修改会议成员\", \"添加会议参与人\", \"移除会议成员\"时触发.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-manage/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-manage","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-manage","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-manage/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-meeting-query","name":"wecom-meeting-query","description":"企业微信会议查询技能, 支持查询会议列表, 获取会议详情, 按关键词查找会议. 当用户需要\"查看会议\", \"查询会议列表\", \"会议详情\", \"什么时候开会\", \"有哪些会议\", \"查找会议\"时触发.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-query/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-query","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-query","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-query/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-msg","name":"wecom-msg","description":"企业微信消息技能。提供会话列表查询、消息记录拉取(支持文本/图片/文件/语音/视频)、多媒体文件获取和文本消息发送能力。当用户需要\"查看消息\"、\"看聊天记录\"、\"发消息给某人\"、\"最近有什么消息\"、\"给群里发消息\"、\"看看发了什么图片/文件\"时触发。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-msg/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-msg","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-msg","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-msg/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-preflight","name":"wecom-preflight","description":"企业微信插件前置条件检查。在执行任何 wecom_mcp 操作前,通过 shell 命令检查工具权限配置(profile 和白名单),若缺失则自动修复并提示用户重启 Gateway。所有使用 wecom_mcp 的技能都应在首次调用前执行此检查。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-preflight/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-preflight","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-preflight","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-preflight/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-schedule","name":"wecom-schedule","description":"企业微信日程管理技能。适用于用户对企业微信日程的各类管理需求。当用户需要:(1) 查询指定时间范围内的日程列表或获取日程详细信息(标题、时间、地点、参与者等),(2) 创建新日程并设置提醒、参与人等,(3) 修改已有日程的标题、时间、地点等信息或取消日程,(4) 添加或移除日程参与人,(5) 查询多个成员的闲忙状态并分析共同空闲时段以安排会议时使用此技能。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-schedule/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-schedule","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-schedule","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-schedule/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-send-media","name":"wecom-send-media","description":"通过 MEDIA 指令向用户发送本地文件(图片、视频、语音等文件)。当用户要求发送或分享文件时,或当生成的文件需要交付给用户时使用。仅当通过 wecom 通道通信时使用此技能。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-media/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-media","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-media","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-media/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-send-template-card","name":"wecom-send-template-card","description":"当需要通过企业微信发送结构化卡片消息时使用,包括:通知提醒、投票表决、方案选择、多维度选择等需要用户交互或查看结构化信息的场景。即使用户未明确要求\"发卡片\",只要语境适合(如\"帮我问一下选A还是B\"),也应主动激活。仅限 wecom 通道。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-template-card/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-template-card","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-template-card","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-template-card/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-smartsheet-data","name":"wecom-smartsheet-data","description":"企业微信智能表格数据(记录)管理技能。提供智能表格记录的增删改查能力。适用场景:(1) 查询子表全部记录 (2) 添加一行或多行记录 (3) 更新已有记录 (4) 删除记录。当用户需要读取表格数据、写入新数据、修改或删除表格行时触发此 Skill。支持通过 docid 或文档 URL 定位文档。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-data/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-data","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-data","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-data/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-smartsheet-schema","name":"wecom-smartsheet-schema","description":"企业微信智能表格结构管理技能。提供子表(Sheet)和字段(Field/列)的增删改查能力。适用场景:(1) 查询智能表格的子表列表 (2) 添加、更新、删除子表 (3) 查询子表的字段/列信息 (4) 添加、更新、删除字段/列。当用户需要管理智能表格的表结构、列定义、子表配置时触发此 Skill。支持通过 docid 或文档 URL 定位文档。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-schema/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-schema","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-schema","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-schema/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true}]},"prompting":{"skillsPrompt":"⚠️ Skills catalog using compact format (descriptions omitted). Run `openclaw skills check` to audit.\n\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its name.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n\n \n alipay-authenticate-wallet\n ~/.openclaw/skills/alipay-authenticate-wallet/SKILL.md\n \n \n alipay-payment-skill\n ~/.openclaw/skills/alipay-payment-skill/SKILL.md\n \n \n baoyu-post-to-wechat\n ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md\n \n \n browser-automation\n ~/.openclaw/plugin-skills/browser-automation/SKILL.md\n \n \n canvas\n /usr/lib/node_modules/openclaw/skills/canvas/SKILL.md\n \n \n diagram-maker\n /usr/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md\n \n \n douyin-hot-copywriter\n ~/.openclaw/skills/douyin-hot-copywriter/SKILL.md\n \n \n empirecms-site-updater\n ~/.openclaw/skills/empirecms-site-updater/SKILL.md\n \n \n feishu-doc\n ~/.openclaw/plugin-skills/feishu-doc/SKILL.md\n \n \n feishu-drive\n ~/.openclaw/plugin-skills/feishu-drive/SKILL.md\n \n \n feishu-perm\n ~/.openclaw/plugin-skills/feishu-perm/SKILL.md\n \n \n feishu-wiki\n ~/.openclaw/plugin-skills/feishu-wiki/SKILL.md\n \n \n guizang-social-card-skill\n ~/.openclaw/skills/guizang-social-card-skill/SKILL.md\n \n \n healthcheck\n /usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md\n \n \n meme-maker\n /usr/lib/node_modules/openclaw/skills/meme-maker/SKILL.md\n \n \n node-connect\n /usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md\n \n \n node-inspect-debugger\n /usr/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md\n \n \n notion\n /usr/lib/node_modules/openclaw/skills/notion/SKILL.md\n \n \n python-debugpy\n /usr/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md\n \n \n qianwen-audio-tts\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-audio-tts/SKILL.md\n \n \n qianwen-image-generation\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-image-generation/SKILL.md\n \n \n qianwen-model-selector\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-model-selector/SKILL.md\n \n \n qianwen-ops-auth\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-ops-auth/SKILL.md\n \n \n qianwen-text\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-text/SKILL.md\n \n \n qianwen-update-check\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-update-check/SKILL.md\n \n \n qianwen-usage\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-usage/SKILL.md\n \n \n qianwen-video-generation\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-video-generation/SKILL.md\n \n \n qianwen-vision\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-vision/SKILL.md\n \n \n skill-creator\n /usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md\n \n \n spike\n /usr/lib/node_modules/openclaw/skills/spike/SKILL.md\n \n \n taskflow\n /usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md\n \n \n taskflow-inbox-triage\n /usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md\n \n \n tencent-news\n ~/.openclaw/agents/101/workspace/skills/tencent-news/SKILL.md\n \n \n tmux\n /usr/lib/node_modules/openclaw/skills/tmux/SKILL.md\n \n \n weather\n /usr/lib/node_modules/openclaw/skills/weather/SKILL.md\n \n \n wecom-contact-lookup\n ~/.openclaw/plugin-skills/wecom-contact-lookup/SKILL.md\n \n \n wecom-doc-manager\n ~/.openclaw/plugin-skills/wecom-doc-manager/SKILL.md\n \n \n wecom-edit-todo\n ~/.openclaw/plugin-skills/wecom-edit-todo/SKILL.md\n \n \n wecom-get-todo-detail\n ~/.openclaw/plugin-skills/wecom-get-todo-detail/SKILL.md\n \n \n wecom-get-todo-list\n ~/.openclaw/plugin-skills/wecom-get-todo-list/SKILL.md\n \n \n wecom-meeting-create\n ~/.openclaw/plugin-skills/wecom-meeting-create/SKILL.md\n \n \n wecom-meeting-manage\n ~/.openclaw/plugin-skills/wecom-meeting-manage/SKILL.md\n \n \n wecom-meeting-query\n ~/.openclaw/plugin-skills/wecom-meeting-query/SKILL.md\n \n \n wecom-msg\n ~/.openclaw/plugin-skills/wecom-msg/SKILL.md\n \n \n wecom-preflight\n ~/.openclaw/plugin-skills/wecom-preflight/SKILL.md\n \n \n wecom-schedule\n ~/.openclaw/plugin-skills/wecom-schedule/SKILL.md\n \n \n wecom-send-media\n ~/.openclaw/plugin-skills/wecom-send-media/SKILL.md\n \n \n wecom-send-template-card\n ~/.openclaw/plugin-skills/wecom-send-template-card/SKILL.md\n \n \n wecom-smartsheet-data\n ~/.openclaw/plugin-skills/wecom-smartsheet-data/SKILL.md\n \n \n wecom-smartsheet-schema\n ~/.openclaw/plugin-skills/wecom-smartsheet-schema/SKILL.md\n \n","systemPromptReport":{"source":"run","generatedAt":1781051868130,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","provider":"deepseek","model":"deepseek-chat","workspaceDir":"/root/.openclaw/agents/101/workspace","bootstrapMaxChars":20000,"bootstrapTotalMaxChars":60000,"bootstrapTruncation":{"warningMode":"always","warningShown":false,"truncatedFiles":0,"nearLimitFiles":0,"totalNearLimit":false},"sandbox":{"mode":"off","sandboxed":false},"systemPrompt":{"chars":33185,"hash":"643e0dde0f8302af7bb0848f9d1af00eb2295d9ab77221f5dd2cc15d1b50d6c6","projectContextChars":12966,"nonProjectContextChars":20219},"injectedWorkspaceFiles":[{"name":"AGENTS.md","path":"/root/.openclaw/agents/101/workspace/AGENTS.md","missing":false,"rawChars":7809,"injectedChars":7809,"truncated":false},{"name":"SOUL.md","path":"/root/.openclaw/agents/101/workspace/SOUL.md","missing":false,"rawChars":1886,"injectedChars":1886,"truncated":false},{"name":"TOOLS.md","path":"/root/.openclaw/agents/101/workspace/TOOLS.md","missing":false,"rawChars":850,"injectedChars":850,"truncated":false},{"name":"IDENTITY.md","path":"/root/.openclaw/agents/101/workspace/IDENTITY.md","missing":false,"rawChars":633,"injectedChars":633,"truncated":false},{"name":"USER.md","path":"/root/.openclaw/agents/101/workspace/USER.md","missing":false,"rawChars":474,"injectedChars":474,"truncated":false},{"name":"HEARTBEAT.md","path":"/root/.openclaw/agents/101/workspace/HEARTBEAT.md","missing":false,"rawChars":151,"injectedChars":151,"truncated":false},{"name":"MEMORY.md","path":"/root/.openclaw/agents/101/workspace/MEMORY.md","missing":false,"rawChars":914,"injectedChars":914,"truncated":false}],"skills":{"promptChars":7409,"hash":"8e748da6c32a41ef1d8f9105491b6b2ba10ccc3266b331ae129742cb39efec7b","entries":[{"name":"alipay-authenticate-wallet","blockChars":142},{"name":"alipay-payment-skill","blockChars":130},{"name":"baoyu-post-to-wechat","blockChars":151},{"name":"browser-automation","blockChars":133},{"name":"canvas","blockChars":121},{"name":"diagram-maker","blockChars":135},{"name":"douyin-hot-copywriter","blockChars":132},{"name":"empirecms-site-updater","blockChars":134},{"name":"feishu-doc","blockChars":117},{"name":"feishu-drive","blockChars":121},{"name":"feishu-perm","blockChars":119},{"name":"feishu-wiki","blockChars":119},{"name":"guizang-social-card-skill","blockChars":140},{"name":"healthcheck","blockChars":131},{"name":"meme-maker","blockChars":129},{"name":"node-connect","blockChars":133},{"name":"node-inspect-debugger","blockChars":151},{"name":"notion","blockChars":121},{"name":"python-debugpy","blockChars":137},{"name":"qianwen-audio-tts","blockChars":153},{"name":"qianwen-image-generation","blockChars":167},{"name":"qianwen-model-selector","blockChars":163},{"name":"qianwen-ops-auth","blockChars":151},{"name":"qianwen-text","blockChars":143},{"name":"qianwen-update-check","blockChars":159},{"name":"qianwen-usage","blockChars":145},{"name":"qianwen-video-generation","blockChars":167},{"name":"qianwen-vision","blockChars":147},{"name":"skill-creator","blockChars":135},{"name":"spike","blockChars":119},{"name":"taskflow","blockChars":125},{"name":"taskflow-inbox-triage","blockChars":151},{"name":"tencent-news","blockChars":135},{"name":"tmux","blockChars":117},{"name":"weather","blockChars":123},{"name":"wecom-contact-lookup","blockChars":137},{"name":"wecom-doc-manager","blockChars":131},{"name":"wecom-edit-todo","blockChars":127},{"name":"wecom-get-todo-detail","blockChars":139},{"name":"wecom-get-todo-list","blockChars":135},{"name":"wecom-meeting-create","blockChars":137},{"name":"wecom-meeting-manage","blockChars":137},{"name":"wecom-meeting-query","blockChars":135},{"name":"wecom-msg","blockChars":115},{"name":"wecom-preflight","blockChars":127},{"name":"wecom-schedule","blockChars":125},{"name":"wecom-send-media","blockChars":129},{"name":"wecom-send-template-card","blockChars":145},{"name":"wecom-smartsheet-data","blockChars":139},{"name":"wecom-smartsheet-schema","blockChars":143}]},"tools":{"listChars":0,"schemaChars":21886,"entries":[{"name":"read","summaryChars":298,"summaryHash":"f8a1d7cf1ecfe02b1b5865c93387e6a5891e5079117b4fe18614b6f912521727","schemaChars":304,"schemaHash":"134f19bcabe3e29d63c5cebb38f1d2556759fd08adad6bc90a4b4d3cd1fb8441","propertiesCount":3},{"name":"edit","summaryChars":326,"summaryHash":"c498a85576e187d069e8e8ea4f70f81bddd57829600d385ef61c4359fd634c9e","schemaChars":834,"schemaHash":"457e8bb9f800b21be76c4fd8c0e3078bf07ee9bf93ac82f39944c171bd8f6d84","propertiesCount":2},{"name":"write","summaryChars":127,"summaryHash":"cdb1c46027b22d1f1b923b47bfe297821d9fe589a9f9d92994961948060a4d89","schemaChars":225,"schemaHash":"e98a2484f667cf7c22d76ca103bf2022bf9113dc63fe38b899e71c328cb1e833","propertiesCount":2},{"name":"apply_patch","summaryChars":132,"summaryHash":"432bf38688a4f011d2b765a441ac07e1fdfa9faf2051679adee04abcd9332d93","schemaChars":153,"schemaHash":"05521268363ff4f191472c90d69ef08a503ba9acf1d2febc50b3ee68db32ab65","propertiesCount":1},{"name":"exec","summaryChars":539,"summaryHash":"4825198988fbfa8ebf5c2a8fbe3946da0be639b1e3b737ceaa4364195bba3f04","schemaChars":1187,"schemaHash":"0c03eeccccb7b7e97234d2c8245c6060e2b292588f02455eae20c60b61bb8bb8","propertiesCount":12},{"name":"process","summaryChars":456,"summaryHash":"55297e65d460e0e1e06e7fad4cedb75ffda8fac9fa8b10aa06d6cead3c5a76ea","schemaChars":1074,"schemaHash":"a2d30a25569f409d7e8539844c89a088044535388b24031d014577b96ed27c5c","propertiesCount":12},{"name":"cron","summaryChars":3610,"summaryHash":"262e6a7b421538d13ca6d79fc14616de3ea0c24fde8b050d6fa1652fe991e5c5","schemaChars":7929,"schemaHash":"df113d901d1284508ecf946e07346ce3ee4c7e9de28b20e0b6120d0b43f6603b","propertiesCount":14},{"name":"video_generate","summaryChars":307,"summaryHash":"59fd08c3f2947e0394c7d1aae5219763bf201537bef536228c6c4fd63724e415","schemaChars":2042,"schemaHash":"ec3a2b299579c1c85d5cb3d5b18e1185c6bb62ca128aa508692098174393cb35","propertiesCount":18},{"name":"get_goal","summaryChars":71,"summaryHash":"58dea7906d9e17e5f89a75fea24597ee068d8a56af824370dc27f8501374d6e3","schemaChars":33,"schemaHash":"8243f0af367f188a376f2c17b5eabe872a2f7a979813e0d4e2be6d594c2aa259","propertiesCount":0},{"name":"create_goal","summaryChars":155,"summaryHash":"f01e3a63d673a410ba55213ce6bd3fa2b0d2279e8e780c18aa0cb5aa991b29b3","schemaChars":267,"schemaHash":"27ee794432736471bd76390e236cc7d7e98f8469a02656e7a27109041eea0f8c","propertiesCount":2},{"name":"update_goal","summaryChars":212,"summaryHash":"285201690e5f2456b4cdcd252ff391709b84d69538df61bad694d3c0cfc19958","schemaChars":207,"schemaHash":"c37894492eedfad02f1e7fe1488900765bfe547f3b3f34cefbab4f7f57441c2c","propertiesCount":2},{"name":"skill_workshop","summaryChars":171,"summaryHash":"577c1d2b8f56bf3e9dd5e00463bbce8b8bf4cf201da9b21b588dcaa3bc6ed8cf","schemaChars":2273,"schemaHash":"15481d6889a320a46728ee32304f0a2b510c0bcf77d445052c1ef2fa5dd5368b","propertiesCount":13},{"name":"update_plan","summaryChars":163,"summaryHash":"ea18cc44224e849c68cdf0a4839c295c1b20daf2699e2fc2be4c4e1552327455","schemaChars":489,"schemaHash":"50cb08b8a29e72637eb6720e6f5f3786783824537574f05ee9ae7a5f4ecacc4b","propertiesCount":2},{"name":"sessions_list","summaryChars":135,"summaryHash":"c7e411ae02e3adff5504aaee48f02d262a8abb9152558a3172aae289e3b05faf","schemaChars":435,"schemaHash":"c29c6b82c36a2d95a88c8944f129929b2621ee2af6d17b2ab101d4d7e9633d89","propertiesCount":9},{"name":"sessions_history","summaryChars":117,"summaryHash":"f5d45b76f11a8ac63cc45d456fb6f675f0b1a2e191feb9671924cb5830058f03","schemaChars":162,"schemaHash":"ac33b8af2252262afe479236046f5a04bc018f1fcf24d1a8bf32743f0e867598","propertiesCount":3},{"name":"sessions_send","summaryChars":224,"summaryHash":"56fd935fc97400f8c60b16ae58268660a2d84d8014a60abed515576c45a6f307","schemaChars":275,"schemaHash":"f1fbaa412fe6b6aee102234c87c5aa140f39c9086f9bae6e1e9691309a602ffb","propertiesCount":5},{"name":"sessions_spawn","summaryChars":332,"summaryHash":"5ced554d0c09b9c71fa003139eca7871bbfdc0917a323fc17af2a9faec46c5b7","schemaChars":1151,"schemaHash":"9a91c7668463da8a66386260ce2ae97e7efe3bb93b9b6f03ac85102c354457e1","propertiesCount":15},{"name":"sessions_yield","summaryChars":79,"summaryHash":"f3782fc41c1522657e1d3494f486a2df998fed38a6b89dcf7f6934fb41424320","schemaChars":60,"schemaHash":"b1c4c753820bc3096d85ef7a266a14c9fbe12450536db58076b75bb61d14dbbb","propertiesCount":1},{"name":"subagents","summaryChars":132,"summaryHash":"1c2ffd38549c0444b118d43736fc4b875ea1aaabc446bbf8bc1fc4ee9180cca4","schemaChars":122,"schemaHash":"c4a241d2c3d46ba7985abfce4d3fcd63298ce81f89d49183c8f3d584c48d0c33","propertiesCount":2},{"name":"session_status","summaryChars":278,"summaryHash":"71177e543dc6235bad4b1a26761995681dcec27ab58dcb4f4f8a7fc9a7b2b5aa","schemaChars":89,"schemaHash":"d2995f3d69d126e98ac93eec3c2a9fe5556925bd7979a8e4b6b5a2bf62d329dd","propertiesCount":2},{"name":"web_search","summaryChars":65,"summaryHash":"b38e9b3c079beaa988d3c576303660b91a55c2e72f56351da04160529173273f","schemaChars":991,"schemaHash":"3879e368875d824b14e0e683f81408824e9a2a5850fa2f8514a68caebda54d18","propertiesCount":12},{"name":"web_fetch","summaryChars":93,"summaryHash":"8875afbb51bd63673e5e6836ca31eeda73914a464862665cd73b346e28d28fd5","schemaChars":317,"schemaHash":"d2d8ad58a1b84d849dd16142282aff6c5606f7b0e3d08405e1b740a6a79e6bcc","propertiesCount":3},{"name":"image","summaryChars":119,"summaryHash":"0eae16e4e16f86cc74ea64bdd48812b0a1d86577fee36dc4cf2c6e7974c83ef6","schemaChars":350,"schemaHash":"49bb766071c935edca8c2d0df47fc2109bbffe3d4ba32d0b19fe90ec873736ce","propertiesCount":6},{"name":"memory_search","summaryChars":605,"summaryHash":"0f918d28864d3682ae77731f149273997c84773592a466b18c7cd0121b599a05","schemaChars":250,"schemaHash":"088cd2a3d3a47b251429ff7c56844cdedd1c45c3af0fa8bfaf7aa795766976bf","propertiesCount":4},{"name":"memory_get","summaryChars":239,"summaryHash":"bff1141a3da31a345c550337417efc9ace4da2909004606c727c59ca1a294495","schemaChars":241,"schemaHash":"78f5d58460a82f9104deebad2f1873a8cde05d1ce7328b3ba4da6e994653e70a","propertiesCount":4},{"name":"wecom_mcp","summaryChars":288,"summaryHash":"f84882350521af5fd0982b63362a4ac280c67fa51a76799c0e93a627652a9552","schemaChars":426,"schemaHash":"7ccdd8994fd5316f030378b8d00ef906800dd0eafee9ab2ecf18756db43f51b5","propertiesCount":4}]}}},"redaction":{"config":{"mode":"redactConfigObject","secretsMasked":true},"payloads":{"mode":"sanitizeDiagnosticPayload","credentialsRemoved":true,"imageDataRedacted":true},"harness":{"mode":"diagnostic-support-redaction","programArgumentsRedacted":true,"localPathsRedacted":true}},"metadata":{"sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","agentId":"101","messageProvider":"feishu"}}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"context.compiled","ts":"2026-06-10T00:37:48.246Z","seq":3,"sourceSeq":3,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"9f7c0220-5360-44dc-9f2f-def4ba9749c7","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"systemPrompt":{"truncated":true,"reason":"trajectory-field-size-limit","originalChars":33651,"limitChars":32768},"prompt":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf5348cca8c4a375e8c70bda2\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:37:44 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf5348cca8c4a375e8c70bda2]\nou_499a5c731212b08e951a441a2bc8a82c: 再写一个,人类对于龙虾的开发还不到1%。\n\n人类历史上,凡是用代码解决过的问题,龙虾都可以自动的用代码来解决,它要有代码。没有代码,他就自己写,有代码就从GitHub上找,下载完帮你搭建环境,试运行,出bug,跑,给你结果","messages":[],"tools":[{"name":"apply_patch","description":"Apply a patch to one or more files using the apply_patch format. The input should include *** Begin Patch and *** End Patch markers.","parameters":{"type":"object","required":["input"],"properties":{"input":{"type":"string","description":"Patch content using the *** Begin Patch/End Patch format."}}}},{"name":"create_goal","description":"Create a goal only when explicitly requested by the user or system instructions. Fails if a goal already exists; use user-facing goal controls to clear it.","parameters":{"type":"object","required":["objective"],"properties":{"objective":{"type":"string","description":"Concrete objective to pursue. Create only when explicitly requested."},"token_budget":{"type":"number","description":"Optional positive token budget for this goal."}}}},{"name":"cron","description":"Manage Gateway cron jobs and wake events: reminders, check-back-later, delayed follow-ups, recurring work. Do not emulate scheduling with exec sleep/process polling.\n\nMain cron => system events for heartbeat. Isolated cron => background task in `openclaw tasks`.\n\nACTIONS:\n- status: scheduler status\n- list: jobs; includeDisabled true includes disabled; agentId filter auto-filled from session\n- get: one job; needs jobId\n- add: create job; needs job object\n- update: patch job; needs jobId + patch\n- remove: delete job; needs jobId\n- run: trigger now; needs jobId\n- runs: run history; needs jobId\n- wake: send wake event; needs text, optional mode\n\nJOB SCHEMA (for add action):\n{\n \"name\": \"string\",\n \"schedule\": { ... }, // required\n \"payload\": { ... }, // required\n \"delivery\": { ... }, // optional announce for isolated/current/session, webhook for any target\n \"sessionTarget\": \"main\" | \"isolated\" | \"current\" | \"session:\",\n \"enabled\": true | false // default true\n}\n\nSESSION TARGET OPTIONS:\n- \"main\": main session; requires payload.kind=\"systemEvent\"\n- \"isolated\": ephemeral isolated session; requires payload.kind=\"agentTurn\"\n- \"current\": bind current session at creation\n- \"session:\": persistent named session\n\nDEFAULTS:\n- payload.kind=\"systemEvent\" → defaults to \"main\"\n- payload.kind=\"agentTurn\" → defaults to \"isolated\"\nCurrent binding needs sessionTarget=\"current\".\n\nSCHEDULE TYPES (schedule.kind):\n- \"at\": one-shot absolute time\n { \"kind\": \"at\", \"at\": \"\" }\n- \"every\": recurring interval\n { \"kind\": \"every\", \"everyMs\": , \"anchorMs\": }\n- \"cron\": expr in supplied timezone, or Gateway host local timezone when tz omitted\n { \"kind\": \"cron\", \"expr\": \"\", \"tz\": \"\" }\n Write expr in local wall-clock time; do not convert the requested local time to UTC first.\n tz omitted => Gateway host local timezone, not UTC.\n Example 6pm Shanghai daily: { \"kind\": \"cron\", \"expr\": \"0 18 * * *\", \"tz\": \"Asia/Shanghai\" }\n\nFor \"at\", ISO timestamps without timezone are UTC.\n\nPAYLOAD TYPES (payload.kind):\n- \"systemEvent\": inject text as system event\n { \"kind\": \"systemEvent\", \"text\": \"\" }\n- \"agentTurn\": run agent with prompt; isolated/current/session only\n { \"kind\": \"agentTurn\", \"message\": \"\", \"model\": \"\", \"thinking\": \"\", \"timeoutSeconds\": }\n\nDELIVERY (top-level):\n { \"mode\": \"none|announce|webhook\", \"channel\": \"\", \"to\": \"\", \"threadId\": \"\", \"bestEffort\": }\n - isolated agentTurn default when omitted: \"announce\"\n - announce: send to chat channel; isolated/current/session only; optional channel/to\n - threadId: chat thread/topic id\n - webhook: POST finished-run event to delivery.to URL\n - Specific chat/recipient: set announce delivery.channel/to; do not call messaging tools inside run.\n\nCRITICAL CONSTRAINTS:\n- sessionTarget=\"main\" REQUIRES payload.kind=\"systemEvent\"\n- sessionTarget=\"isolated\" | \"current\" | \"session:xxx\" REQUIRES payload.kind=\"agentTurn\"\n- Webhook: delivery.mode=\"webhook\" and delivery.to URL.\nDefault: prefer isolated agentTurn jobs unless the user explicitly wants current-session binding.\n\nRESTRICTED CRON RUNS:\n- Some isolated cron runs get narrow self-cleanup grant: status/list self-only, get/runs current job only, mutation only remove current job.\n\nWAKE MODES (for wake action):\n- \"next-heartbeat\" default: wake next heartbeat\n- \"now\": wake immediately\n\nUse jobId canonical; id accepted compat. contextMessages (0-10) adds previous messages as job context.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"gatewayUrl":{"type":"string"},"timeoutMs":{"type":"integer","minimum":1},"includeDisabled":{"type":"boolean"},"job":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"additionalProperties":true},"jobId":{"type":"string"},"id":{"type":"string"},"patch":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"additionalProperties":true},"text":{"type":"string"},"mode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"runMode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"contextMessages":{"type":"integer","minimum":0,"maximum":10},"agentId":{"type":"string","description":"List filter: agent id"}},"additionalProperties":true}},{"name":"edit","description":"Edit a single file using exact text replacement. Every edits[].oldText must match a unique, non-overlapping region of the original file. If two changes affect the same block or nearby lines, merge them into one edit instead of emitting overlapping edits. Do not include large unchanged regions just to connect distant changes.","parameters":{"type":"object","required":["path","edits"],"properties":{"path":{"type":"string","description":"Path to the file to edit (relative or absolute)"},"edits":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"One or more targeted replacements. Each edit is matched against the original file, not incrementally. Do not include overlapping or nested edits. If two changes touch the same block or nearby lines, merge them into one edit instead."}},"additionalProperties":false}},{"name":"exec","description":"Execute shell commands with background continuation for work that starts now. Use yieldMs/background to continue later via process tool. For long-running work started now, rely on automatic completion wake when it is enabled and the command emits output or fails; otherwise use process to confirm completion. Use process whenever you need logs, status, input, or intervention. Do not use exec sleep or delay loops for reminders or deferred follow-ups; use cron instead. Use pty=true for TTY-required commands (terminal UIs, coding agents).","parameters":{"type":"object","required":["command"],"properties":{"command":{"type":"string","description":"Shell command to execute"},"workdir":{"type":"string","description":"Working directory (defaults to cwd)"},"env":{"type":"object","patternProperties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"yieldMs":{"type":"number","description":"Milliseconds to wait before backgrounding (default 10000)"},"background":{"type":"boolean","description":"Run in background immediately"},"timeout":{"type":"number","description":"Timeout in seconds (optional, kills process on expiry)"},"pty":{"type":"boolean","description":"Run in a pseudo-terminal (PTY) when available (TTY-required CLIs, coding agents)"},"elevated":{"type":"boolean","description":"Run on the host with elevated permissions (if allowed)"},"host":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Exec host/target (auto|sandbox|gateway|node)."},"security":{"type":"string","description":"Ignored for normal calls; exec security is set by tools.exec.security and host approvals."},"ask":{"type":"string","description":"Exec ask mode (off|on-miss|always)."},"node":{"type":"string","description":"Node id/name for host=node."}}}},{"name":"get_goal","description":"Get the current goal for this thread, including status and token usage.","parameters":{"type":"object","properties":{}}},{"name":"image","description":"Analyze images with available vision model. Use image for one path/URL, images for max 20. Prompt says what to inspect.","parameters":{"type":"object","properties":{"prompt":{"type":"string"},"image":{"type":"string","description":"One image path/URL."},"images":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Image paths/URLs; maxImages default 20."},"model":{"type":"string"},"maxBytesMb":{"type":"number","exclusiveMinimum":0},"maxImages":{"type":"integer","minimum":1}}}},{"name":"memory_get","description":"Safe exact excerpt read from MEMORY.md or memory/*.md. Defaults to a bounded excerpt when lines are omitted, includes truncation/continuation info when more content exists, and `corpus=wiki` reads from registered compiled-wiki supplements.","parameters":{"type":"object","properties":{"path":{"type":"string"},"from":{"type":"integer","minimum":1},"lines":{"type":"integer","minimum":1},"corpus":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}},"required":["path"],"additionalProperties":false}},{"name":"memory_search","description":"Mandatory recall step: semantically search MEMORY.md + memory/*.md (and optional session transcripts) before answering questions about prior work, decisions, dates, people, preferences, or todos. Optional `corpus=wiki` or `corpus=all` also searches registered compiled-wiki supplements. `corpus=memory` restricts hits to indexed memory files (excludes session transcript chunks from ranking). `corpus=sessions` restricts hits to indexed session transcripts (same visibility rules as session history tools). If response has disabled=true, memory retrieval is unavailable and should be surfaced to the user.","parameters":{"type":"object","properties":{"query":{"type":"string"},"maxResults":{"type":"integer","minimum":1},"minScore":{"type":"number"},"corpus":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}},"required":["query"],"additionalProperties":false}},{"name":"process","description":"Manage running exec sessions for commands already started: list, poll, log, write, send-keys, submit, paste, kill. Use poll/log when you need status, logs, quiet-success confirmation, or completion confirmation when automatic completion wake is unavailable. Use poll/log also for input-wait hints. Use write/send-keys/submit/paste/kill for input or intervention. Do not use process polling to emulate timers or reminders; use cron for scheduled follow-ups.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","description":"Process action (list|poll|log|write|send-keys|submit|paste|kill|clear|remove)"},"sessionId":{"type":"string","description":"Session id for actions other than list"},"data":{"type":"string","description":"Data to write for write"},"keys":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Key tokens to send for send-keys"},"hex":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Hex bytes to send for send-keys"},"literal":{"type":"string","description":"Literal string for send-keys"},"text":{"type":"string","description":"Text to paste for paste"},"bracketed":{"type":"boolean","description":"Wrap paste in bracketed mode"},"eof":{"type":"boolean","description":"Close stdin after write"},"offset":{"type":"number","description":"Log offset"},"limit":{"type":"number","description":"Log length"},"timeout":{"type":"number","description":"For poll: wait up to this many milliseconds before returning; max 30000 ms, higher values are clamped to 30000","minimum":0}}}},{"name":"read","description":"Read the contents of a file. Supports text files and images (jpg, png, gif, webp). Images are sent as attachments. For text files, output is truncated to 2000 lines or 50KB (whichever is hit first). Use offset/limit for large files. When you need the full file, continue with offset until complete.","parameters":{"type":"object","required":["path"],"properties":{"path":{"type":"string","description":"Path to the file to read (relative or absolute)"},"offset":{"type":"number","description":"Line number to start reading from (1-indexed)"},"limit":{"type":"number","description":"Maximum number of lines to read"}}}},{"name":"session_status","description":"Show /status-like card for current/visible session: model, usage, time, cost, tasks. Use `sessionKey=\"current\"` for current session; UI labels like `openclaw-tui` are not keys. `model` sets session override; `model=default` resets. Use for active model/session config questions.","parameters":{"type":"object","properties":{"sessionKey":{"type":"string"},"model":{"type":"string"}}}},{"name":"sessions_history","description":"Fetch sanitized history for visible session. Use before replying, debugging, resuming; supports limits/tool messages.","parameters":{"type":"object","required":["sessionKey"],"properties":{"sessionKey":{"type":"string"},"limit":{"type":"integer","minimum":1},"includeTools":{"type":"boolean"}}}},{"name":"sessions_list","description":"List visible sessions; filter by kind, label, agentId, search, activity. Use before sessions_history or sessions_send target selection.","parameters":{"type":"object","properties":{"kinds":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"limit":{"type":"integer","minimum":1},"activeMinutes":{"type":"integer","minimum":1},"messageLimit":{"type":"integer","minimum":0},"label":{"type":"string","minLength":1},"agentId":{"type":"string","minLength":1,"maxLength":64},"search":{"type":"string","minLength":1},"includeDerivedTitles":{"type":"boolean"},"includeLastMessage":{"type":"boolean"}}}},{"name":"sessions_send","description":"Send message to visible session by sessionKey/label, or configured agent by agentId. Thread-scoped chats rejected; target parent channel session. Creates missing configured-agent main session; waits for reply when available.","parameters":{"type":"object","required":["message"],"properties":{"sessionKey":{"type":"string"},"label":{"type":"string","minLength":1,"maxLength":512},"agentId":{"type":"string","minLength":1,"maxLength":64},"message":{"type":"string"},"timeoutSeconds":{"type":"integer","minimum":0}}}},{"name":"sessions_spawn","description":"Spawn clean child session; default `runtime=\"subagent\"`. `mode=\"run\"` one-shot background work. Subagents inherit parent workspace. Native subagents get task in first visible `[Subagent Task]` message. Native only: `context=\"fork\"` only when child needs current transcript; else omit or `isolated`. Use for fresh child-session work.","parameters":{"type":"object","required":["task"],"properties":{"task":{"type":"string"},"taskName":{"type":"string","description":"Stable alias for later targeting; lowercase letters/digits/underscores/hyphens, starts letter."},"label":{"type":"string"},"runtime":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"agentId":{"type":"string"},"model":{"type":"string"},"thinking":{"type":"string"},"cwd":{"type":"string"},"mode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"cleanup":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"sandbox":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"context":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Native context. Omit/\"isolated\" for clean child; \"fork\" only when child needs requester transcript."},"lightContext":{"type":"boolean","description":"Light bootstrap context; runtime=\"subagent\" only."},"attachments":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"maxItems":50},"attachAs":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}}}},{"name":"sessions_yield","description":"End current turn. Use after spawning subagents; results arrive as next message.","parameters":{"type":"object","properties":{"message":{"type":"string"}}}},{"name":"skill_workshop","description":"Create, update, revise, list, inspect, apply, reject, or quarantine Skill Workshop proposals when reusable procedures should be captured, improved, or explicitly approved.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"create for a new skill proposal, update for an existing skill, revise for a pending proposal, list or inspect proposals for proposal discovery, apply/reject/quarantine for explicit proposal lifecycle actions."},"proposal_id":{"type":"string","description":"Existing proposal id for action=inspect, action=revise, action=apply, action=reject, or action=quarantine."},"name":{"type":"string","description":"Skill/proposal name. Required for action=create; optional resolver for action=inspect or action=revise when proposal_id is unknown."},"query":{"type":"string","description":"Optional query for action=list."},"status":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Optional proposal status filter for action=list."},"limit":{"type":"integer","minimum":1,"maximum":50,"description":"Maximum proposals to return for action=list. Defaults to 20."},"description":{"type":"string","maxLength":160,"description":"Skill description for action=create, action=update, or action=revise. Keep it concise; max 160 bytes."},"skill_name":{"type":"string","description":"Existing skill name or key for action=update."},"proposal_content":{"type":"string","description":"Full proposed procedure markdown for action=create, action=update, or action=revise. It will be stored as PROPOSAL.md. Keep under configured skills.workshop.maxSkillBytes; default max is 40000 bytes."},"support_files":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Optional support files to store with the proposal."},"goal":{"type":"string","description":"Proposal or improvement goal."},"evidence":{"type":"string","description":"Short evidence or notes."},"reason":{"type":"string","description":"Optional reason for action=apply, action=reject, or action=quarantine."}},"additionalProperties":false}},{"name":"subagents","description":"List active and recent subagents for the requester session. If sessions_yield exists, use it for completion; do not poll wait loops.","parameters":{"type":"object","properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"recentMinutes":{"type":"integer","minimum":1}}}},{"name":"update_goal","description":"Mark the current goal complete only when achieved, or blocked only after the same blocking condition recurs for at least three consecutive goal turns. Do not use blocked for ordinary difficulty or missing polish.","parameters":{"type":"object","required":["status"],"properties":{"status":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"complete | blocked."},"note":{"type":"string","description":"Short status note."}}}},{"name":"update_plan","description":"Update current run plan. Use for non-trivial multi-step work; keep plan current while executing. Short steps; max one `in_progress`; skip for simple one-step work.","parameters":{"type":"object","required":["plan"],"properties":{"explanation":{"type":"string","description":"Short note: what changed."},"plan":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"minItems":1,"description":"Ordered steps; max one in_progress."}}}},{"name":"video_generate","description":"Create videos. Session chats: background task; do not call video_generate again for same request; wait completion, then report through the current visible-reply contract with generated media attached using structured media fields. \"status\" checks active task. Duration may round to provider-supported value.","parameters":{"type":"object","properties":{"action":{"type":"string","description":"\"generate\" default, \"status\" active task, \"list\" providers/models."},"prompt":{"type":"string","description":"Video prompt."},"image":{"type":"string","description":"One reference image path/URL."},"images":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Reference images; max 9."},"imageRoles":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"`image` + `images` roles by index after de-dupe. Values: first_frame, last_frame, reference_image; empty string leaves unset."},"video":{"type":"string","description":"One reference video path/URL."},"videos":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Reference videos; max 4."},"videoRoles":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"`video` + `videos` roles by index after de-dupe. Value: reference_video; empty string leaves unset."},"model":{"type":"string","description":"Provider/model override, e.g. qwen/wan2.6-t2v."},"filename":{"type":"string","description":"Output filename hint; basename preserved in managed media dir."},"size":{"type":"string","description":"Size hint, e.g. 1280x720, 1920x1080."},"aspectRatio":{"type":"string","description":"Aspect ratio: 1:1, 16:9, 9:16, \"adaptive\", or provider value; unsupported normalized/ignored."},"resolution":{"type":"string","description":"Resolution: 360P, 480P, 540P, 720P, 768P, 1080P, 4K, or provider value; unsupported normalized/ignored."},"durationSeconds":{"type":"integer","description":"Target seconds; may round to nearest supported duration.","minimum":1},"audio":{"type":"boolean","description":"Generated-audio toggle."},"watermark":{"type":"boolean","description":"Watermark toggle."},"providerOptions":{"type":"object","patternProperties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Provider JSON options, e.g. {\"seed\":42}. Keys/types must match provider capabilities; mismatch skips candidate. Use action=list for accepted keys."},"timeoutMs":{"type":"integer","description":"Provider timeout ms.","minimum":1}}}},{"name":"web_fetch","description":"Fetch URL and extract readable markdown/text. Lightweight page access; no browser automation.","parameters":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"HTTP(S) URL."},"extractMode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Extract as markdown/text.","default":"markdown"},"maxChars":{"type":"integer","description":"Max chars returned; truncates.","minimum":100}}}},{"name":"web_search","description":"Search web for current info; returns normalized provider results.","parameters":{"type":"object","required":["query"],"properties":{"query":{"type":"string","description":"Search query."},"count":{"type":"number","description":"Result count.","minimum":1,"maximum":10},"country":{"type":"string","description":"2-letter country code."},"language":{"type":"string","description":"ISO 639-1 language."},"freshness":{"type":"string","description":"Time filter: day/week/month/year."},"date_after":{"type":"string","description":"Published after YYYY-MM-DD."},"date_before":{"type":"string","description":"Published before YYYY-MM-DD."},"search_lang":{"type":"string","description":"Brave result language."},"ui_lang":{"type":"string","description":"Brave UI locale."},"domain_filter":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Perplexity domain filter."},"max_tokens":{"type":"number","description":"Perplexity total token budget.","minimum":1,"maximum":1000000},"max_tokens_per_page":{"type":"number","description":"Perplexity tokens per page.","minimum":1}}}},{"name":"wecom_mcp","description":"通过 HTTP 直接调用企业微信 MCP Server。\n支持两种操作:\n - list: 列出指定品类的所有 MCP 工具\n - call: 调用指定品类的某个 MCP 工具\n\n使用方式:\n wecom_mcp list \n wecom_mcp call ''\n\n示例:\n 列出 contact 品类所有工具:wecom_mcp list contact\n 调用 contact 的 getContact:wecom_mcp call contact getContact '{}'","parameters":{"type":"object","properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"操作类型:list(列出工具)或 call(调用工具)"},"category":{"type":"string","description":"MCP 品类名称,如 doc、contact 等,对应 mcpConfig 中的 key"},"method":{"type":"string","description":"要调用的 MCP 方法名(action=call 时必填)"},"args":{"type":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"调用 MCP 方法的参数,可以是 JSON 字符串或对象(action=call 时使用,默认 {})"}},"required":["action","category"]}},{"name":"write","description":"Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.","parameters":{"type":"object","required":["path","content"],"properties":{"path":{"type":"string","description":"Path to the file to write (relative or absolute)"},"content":{"type":"string","description":"Content to write to the file"}}}}],"imagesCount":0,"streamStrategy":"boundary-aware:openai-completions","transport":"auto","transcriptLeafId":"c92f1bc2"}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"prompt.submitted","ts":"2026-06-10T00:37:48.256Z","seq":4,"sourceSeq":4,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"9f7c0220-5360-44dc-9f2f-def4ba9749c7","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"prompt":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf5348cca8c4a375e8c70bda2\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:37:44 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf5348cca8c4a375e8c70bda2]\nou_499a5c731212b08e951a441a2bc8a82c: 再写一个,人类对于龙虾的开发还不到1%。\n\n人类历史上,凡是用代码解决过的问题,龙虾都可以自动的用代码来解决,它要有代码。没有代码,他就自己写,有代码就从GitHub上找,下载完帮你搭建环境,试运行,出bug,跑,给你结果","systemPrompt":{"truncated":true,"reason":"trajectory-field-size-limit","originalChars":33651,"limitChars":32768},"messages":[],"imagesCount":0}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"model.completed","ts":"2026-06-10T00:38:20.013Z","seq":5,"sourceSeq":5,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"9f7c0220-5360-44dc-9f2f-def4ba9749c7","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false,"promptErrorSource":null,"usage":{"input":10471,"output":805,"cacheRead":28800,"total":40076},"promptCache":{"lastCallUsage":{"input":354,"output":558,"cacheRead":19456,"cacheWrite":0,"total":20368},"lastCacheTouchAt":1781051892824},"compactionCount":0,"assistantTexts":["首长,您这是要一篇关于龙虾(自主AI编码Agent)的公众号逐字稿脚本,对吧?核心命题是:**人类对龙虾的开发还不到1%,龙虾能自动解决一切代码问题。**\n\n我先查一下相关素材,然后出脚本。","搜索暂时超时,不影响,您给的素材足够直接出脚本了。我按照您的意思——龙虾能自主解决一切代码问题,全部流程自动化——来写。\n\n---\n\n**脚本:龙虾不到1%**\n\n| 时长 | 画面 | 台词 |\n|------|------|------|\n| 0:00-0:05 | 黑屏白字:人类对龙虾的开发还不到1% | 人类对龙虾的开发,还不到1%。 |\n| 0:05-0:20 | 快速切换代码编辑器画面→AI自动写代码→浏览器自动测试 | 人类历史上,凡是能用代码解决的问题,龙虾都可以自动地用代码来解决。 |\n| 0:20-0:35 | 画面:GitHub搜索→自动下载→终端跑安装 | 但前提是——它得有代码。没有代码?它会自己写。有代码?它上GitHub给你搜,下载下来,开发环境帮你搭好。 |\n| 0:35-0:50 | 画面:终端自动运行→报错→自动修正→再次运行→绿pass | 然后试运行。出bug?修。再出?再修。直到跑通。整个过程不需要你动手,它就自己在那儿干活。 |\n| 0:50-1:05 | 特写:终端输出结果 | 最后——结果摆你面前。 |\n| 1:05-1:20 | 画风一转:空旷的会议室,一张椅子,一个屏幕 | 你可能会想:这跟找个程序员有啥区别?区别大了——它不吃饭、不睡觉、不抱怨需求改来改去,而且又快又便宜。 |\n| 1:20-1:40 | 蒙太奇:各种行业的人在聊天→刷卡支付→点头 | 有人说AI抢饭碗,但真正看懂的人已经在用龙虾给自己建团队了。一个人搭一个技术团队,不是梦。 |\n| 1:40-1:55 | 俯拍镜头:一本书\\一条深海鱼\\龙虾特写 | 龙虾就在那儿,深海里的资源,我们才捞了一点点。所以别急着说AI不行,先问问自己——你让龙虾帮你干过活吗? |\n| 1:55-2:00 | Logo/二维码 | 关注我,带你用龙虾降维打击。 |\n\n---\n\n**备注:**\n- 您说的\"龙虾\"在脚本里保持原词,不做替换,这本身就是你的IP标签\n- 整体节奏偏快、有画面感,符合短视频逐字稿要求\n- 如需调整口吻(更激进/更温和)、增减时长,或者改为文章版,随时说"],"finalPromptText":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf5348cca8c4a375e8c70bda2\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:37:44 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf5348cca8c4a375e8c70bda2]\nou_499a5c731212b08e951a441a2bc8a82c: 再写一个,人类对于龙虾的开发还不到1%。\n\n人类历史上,凡是用代码解决过的问题,龙虾都可以自动的用代码来解决,它要有代码。没有代码,他就自己写,有代码就从GitHub上找,下载完帮你搭建环境,试运行,出bug,跑,给你结果","messagesSnapshot":[{"role":"user","content":[{"type":"text","text":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf5348cca8c4a375e8c70bda2\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:37:44 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf5348cca8c4a375e8c70bda2]\nou_499a5c731212b08e951a441a2bc8a82c: 再写一个,人类对于龙虾的开发还不到1%。\n\n人类历史上,凡是用代码解决过的问题,龙虾都可以自动的用代码来解决,它要有代码。没有代码,他就自己写,有代码就从GitHub上找,下载完帮你搭建环境,试运行,出bug,跑,给你结果"}],"timestamp":1781051868256},{"role":"assistant","content":[{"type":"text","text":"首长,您这是要一篇关于龙虾(自主AI编码Agent)的公众号逐字稿脚本,对吧?核心命题是:**人类对龙虾的开发还不到1%,龙虾能自动解决一切代码问题。**\n\n我先查一下相关素材,然后出脚本。"},{"type":"toolCall","id":"call_00_onQsEvkVXRRxFAnvEok20373","name":"web_search","arguments":{"query":"AI coding agent 自主编程 未来已来 2025 2026","count":5},"partialArgs":"{\"query\": \"AI coding agent 自主编程 未来已来 2025 2026\", \"count\": 5}"},{"type":"toolCall","id":"call_01_fouQj9kDBILLFnoNoxY14235","name":"web_search","arguments":{"query":"Claude coding Agent 自动写代码 GitHub 下载 搭建环境","count":5},"partialArgs":"{\"query\": \"Claude coding Agent 自动写代码 GitHub 下载 搭建环境\", \"count\": 5}"},{"type":"toolCall","id":"call_02_OOcRB4fsDb9VDDp8RXjX0721","name":"web_search","arguments":{"query":"AI agent 自动解决问题 编程 未来 人类开发不到1%","count":5},"partialArgs":"{\"query\": \"AI agent 自动解决问题 编程 未来 人类开发不到1%\", \"count\": 5}"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":10117,"output":247,"cacheRead":9344,"cacheWrite":0,"totalTokens":19708,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1781051868286,"responseId":"1c69b78a-c3ac-433d-9f68-6f19d8ed2ad3"},{"role":"toolResult","toolCallId":"call_00_onQsEvkVXRRxFAnvEok20373","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"details":{"status":"error","tool":"web_search","error":"request timed out"},"isError":true,"timestamp":1781051892796},{"role":"toolResult","toolCallId":"call_01_fouQj9kDBILLFnoNoxY14235","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"details":{"status":"error","tool":"web_search","error":"request timed out"},"isError":true,"timestamp":1781051892802},{"role":"toolResult","toolCallId":"call_02_OOcRB4fsDb9VDDp8RXjX0721","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"details":{"status":"error","tool":"web_search","error":"request timed out"},"isError":true,"timestamp":1781051892809},{"role":"assistant","content":[{"type":"text","text":"搜索暂时超时,不影响,您给的素材足够直接出脚本了。我按照您的意思——龙虾能自主解决一切代码问题,全部流程自动化——来写。\n\n---\n\n**脚本:龙虾不到1%**\n\n| 时长 | 画面 | 台词 |\n|------|------|------|\n| 0:00-0:05 | 黑屏白字:人类对龙虾的开发还不到1% | 人类对龙虾的开发,还不到1%。 |\n| 0:05-0:20 | 快速切换代码编辑器画面→AI自动写代码→浏览器自动测试 | 人类历史上,凡是能用代码解决的问题,龙虾都可以自动地用代码来解决。 |\n| 0:20-0:35 | 画面:GitHub搜索→自动下载→终端跑安装 | 但前提是——它得有代码。没有代码?它会自己写。有代码?它上GitHub给你搜,下载下来,开发环境帮你搭好。 |\n| 0:35-0:50 | 画面:终端自动运行→报错→自动修正→再次运行→绿pass | 然后试运行。出bug?修。再出?再修。直到跑通。整个过程不需要你动手,它就自己在那儿干活。 |\n| 0:50-1:05 | 特写:终端输出结果 | 最后——结果摆你面前。 |\n| 1:05-1:20 | 画风一转:空旷的会议室,一张椅子,一个屏幕 | 你可能会想:这跟找个程序员有啥区别?区别大了——它不吃饭、不睡觉、不抱怨需求改来改去,而且又快又便宜。 |\n| 1:20-1:40 | 蒙太奇:各种行业的人在聊天→刷卡支付→点头 | 有人说AI抢饭碗,但真正看懂的人已经在用龙虾给自己建团队了。一个人搭一个技术团队,不是梦。 |\n| 1:40-1:55 | 俯拍镜头:一本书\\一条深海鱼\\龙虾特写 | 龙虾就在那儿,深海里的资源,我们才捞了一点点。所以别急着说AI不行,先问问自己——你让龙虾帮你干过活吗? |\n| 1:55-2:00 | Logo/二维码 | 关注我,带你用龙虾降维打击。 |\n\n---\n\n**备注:**\n- 您说的\"龙虾\"在脚本里保持原词,不做替换,这本身就是你的IP标签\n- 整体节奏偏快、有画面感,符合短视频逐字稿要求\n- 如需调整口吻(更激进/更温和)、增减时长,或者改为文章版,随时说"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":354,"output":558,"cacheRead":19456,"cacheWrite":0,"totalTokens":20368,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1781051892824,"responseId":"a4968589-9901-4e20-8ba2-a5d22e6f4ebb"}]}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"trace.artifacts","ts":"2026-06-10T00:38:20.014Z","seq":6,"sourceSeq":6,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"9f7c0220-5360-44dc-9f2f-def4ba9749c7","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-06-10T00:38:20.014Z","finalStatus":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false,"promptErrorSource":null,"usage":{"input":10471,"output":805,"cacheRead":28800,"total":40076},"promptCache":{"lastCallUsage":{"input":354,"output":558,"cacheRead":19456,"cacheWrite":0,"total":20368},"lastCacheTouchAt":1781051892824},"compactionCount":0,"assistantTexts":["首长,您这是要一篇关于龙虾(自主AI编码Agent)的公众号逐字稿脚本,对吧?核心命题是:**人类对龙虾的开发还不到1%,龙虾能自动解决一切代码问题。**\n\n我先查一下相关素材,然后出脚本。","搜索暂时超时,不影响,您给的素材足够直接出脚本了。我按照您的意思——龙虾能自主解决一切代码问题,全部流程自动化——来写。\n\n---\n\n**脚本:龙虾不到1%**\n\n| 时长 | 画面 | 台词 |\n|------|------|------|\n| 0:00-0:05 | 黑屏白字:人类对龙虾的开发还不到1% | 人类对龙虾的开发,还不到1%。 |\n| 0:05-0:20 | 快速切换代码编辑器画面→AI自动写代码→浏览器自动测试 | 人类历史上,凡是能用代码解决的问题,龙虾都可以自动地用代码来解决。 |\n| 0:20-0:35 | 画面:GitHub搜索→自动下载→终端跑安装 | 但前提是——它得有代码。没有代码?它会自己写。有代码?它上GitHub给你搜,下载下来,开发环境帮你搭好。 |\n| 0:35-0:50 | 画面:终端自动运行→报错→自动修正→再次运行→绿pass | 然后试运行。出bug?修。再出?再修。直到跑通。整个过程不需要你动手,它就自己在那儿干活。 |\n| 0:50-1:05 | 特写:终端输出结果 | 最后——结果摆你面前。 |\n| 1:05-1:20 | 画风一转:空旷的会议室,一张椅子,一个屏幕 | 你可能会想:这跟找个程序员有啥区别?区别大了——它不吃饭、不睡觉、不抱怨需求改来改去,而且又快又便宜。 |\n| 1:20-1:40 | 蒙太奇:各种行业的人在聊天→刷卡支付→点头 | 有人说AI抢饭碗,但真正看懂的人已经在用龙虾给自己建团队了。一个人搭一个技术团队,不是梦。 |\n| 1:40-1:55 | 俯拍镜头:一本书\\一条深海鱼\\龙虾特写 | 龙虾就在那儿,深海里的资源,我们才捞了一点点。所以别急着说AI不行,先问问自己——你让龙虾帮你干过活吗? |\n| 1:55-2:00 | Logo/二维码 | 关注我,带你用龙虾降维打击。 |\n\n---\n\n**备注:**\n- 您说的\"龙虾\"在脚本里保持原词,不做替换,这本身就是你的IP标签\n- 整体节奏偏快、有画面感,符合短视频逐字稿要求\n- 如需调整口吻(更激进/更温和)、增减时长,或者改为文章版,随时说"],"finalPromptText":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf5348cca8c4a375e8c70bda2\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:37:44 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf5348cca8c4a375e8c70bda2]\nou_499a5c731212b08e951a441a2bc8a82c: 再写一个,人类对于龙虾的开发还不到1%。\n\n人类历史上,凡是用代码解决过的问题,龙虾都可以自动的用代码来解决,它要有代码。没有代码,他就自己写,有代码就从GitHub上找,下载完帮你搭建环境,试运行,出bug,跑,给你结果","itemLifecycle":{"startedCount":3,"completedCount":3,"activeCount":0},"toolMetas":[{"toolName":"web_search","meta":"for \"AI agent 自动解决问题 编程 未来 人类开发不到1%\" (top 5)"},{"toolName":"web_search","meta":"for \"Claude coding Agent 自动写代码 GitHub 下载 搭建环境\" (top 5)"},{"toolName":"web_search","meta":"for \"AI coding agent 自主编程 未来已来 2025 2026\" (top 5)"}],"didSendViaMessagingTool":false,"successfulCronAdds":0,"messagingToolSentTexts":[],"messagingToolSentMediaUrls":[],"messagingToolSentTargets":[],"lastToolError":{"toolName":"web_search","meta":"for \"AI coding agent 自主编程 未来已来 2025 2026\" (top 5)","error":"request timed out","mutatingAction":false}}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"session.ended","ts":"2026-06-10T00:38:20.014Z","seq":7,"sourceSeq":7,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"9f7c0220-5360-44dc-9f2f-def4ba9749c7","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"status":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"session.started","ts":"2026-06-10T00:47:29.546Z","seq":1,"sourceSeq":8,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"8c871808-083d-4322-ac03-92c8547361ff","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"trigger":"user","sessionFile":"/root/.openclaw/agents/101/sessions/7610e75e-f720-46e1-9564-1c959b18830a.jsonl","workspaceDir":"/root/.openclaw/agents/101/workspace","agentId":"101","messageProvider":"feishu","localModelLean":false,"toolCount":26,"clientToolCount":0}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"trace.metadata","ts":"2026-06-10T00:47:29.550Z","seq":2,"sourceSeq":9,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"8c871808-083d-4322-ac03-92c8547361ff","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-06-10T00:47:29.546Z","harness":{"type":"openclaw","name":"OpenClaw","version":"2026.6.1","gitSha":"2e08f0f","os":{"platform":"linux","arch":"x64","release":"6.8.0-55-generic","label":"linux 6.8.0-55-generic (x64)"},"runtime":{"node":"v22.22.1"},"invocation":["/usr/bin/node","/usr/lib/node_modules/openclaw/dist/index.js","gateway","--port","18789"],"entrypoint":"/usr/lib/node_modules/openclaw/dist/index.js","workspaceDir":"$OPENCLAW_STATE_DIR/agents/101/workspace","sessionFile":"$OPENCLAW_STATE_DIR/agents/101/sessions/7610e75e-f720-46e1-9564-1c959b18830a.jsonl"},"model":{"provider":"deepseek","name":"deepseek-chat","api":"openai-completions","fastMode":false,"thinkLevel":"off","reasoningLevel":"off"},"config":{"redacted":{"meta":{"lastTouchedVersion":"2026.6.1","lastTouchedAt":"2026-06-08T10:06:57.650Z"},"env":{"TENCENT_NEWS_INSTALL":"/root/.tencent-news-cli"},"wizard":{"lastRunAt":"2026-06-08T09:47:07.280Z","lastRunVersion":"2026.6.1","lastRunCommand":"doctor","lastRunMode":"local"},"browser":{"noSandbox":true},"auth":{"profiles":{"deepseek:default":{"provider":"deepseek","mode":"api_key"}}},"models":{"mode":"merge","providers":{"deepseek":{"baseUrl":"https://api.deepseek.com","api":"openai-completions","models":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}}},"agents":{"defaults":{"model":{"primary":"deepseek/deepseek-chat"},"models":{"deepseek/deepseek-chat":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"deepseek/deepseek-v4-pro":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"deepseek/deepseek-v4-flash":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"openai/deepseek-chat":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"workspace":"/root/.openclaw/workspace","compaction":{"mode":"safeguard"},"subagents":{"allowAgents":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"maxConcurrent":8,"archiveAfterMinutes":60},"maxConcurrent":4},"list":[{"id":"101","workspace":"/root/.openclaw/agents/101/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"选题大师","workspace":"/root/.openclaw/agents/选题大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"脚本大师","workspace":"/root/.openclaw/agents/脚本大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"wenzhang","workspace":"/root/.openclaw/agents/文章大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"发布大师","workspace":"/root/.openclaw/agents/发布大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"情报大师","workspace":"/root/.openclaw/agents/情报大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}]},"tools":{"profile":"coding","alsoAllow":["wecom_mcp"],"web":{"search":{"enabled":true,"provider":"duckduckgo"}}},"commands":{"native":"auto","nativeSkills":"auto","restart":true,"ownerDisplay":"raw"},"session":{"dmScope":"per-channel-peer"},"channels":{"feishu":{"enabled":true,"appId":"cli_a94e174db1785bde","domain":"feishu","connectionMode":"websocket","dmPolicy":"pairing","groupPolicy":"open","requireMention":true,"streaming":false,"webhookPath":"/feishu/events","reactionNotifications":"own","typingIndicator":true,"resolveSenderNames":true},"wecom":{"enabled":true,"corpId":"ww3cd12f8716588acd","botId":"aibjcPQgSK4cWMbqrt7qkZLgmN2uCKP4FJD"},"openclaw-weixin":{"label":"微信","type":"weixin","channelConfigUpdatedAt":"2026-05-27T01:41:48.475Z","enabled":true}},"gateway":{"port":18789,"mode":"local","bind":"loopback","auth":{"mode":"token"},"tailscale":{"mode":"off","resetOnExit":false},"nodes":{"denyCommands":["camera.snap","camera.clip","screen.record","contacts.add","calendar.add","reminders.add","sms.send"]}},"skills":{"entries":{"apple-notes":{"enabled":false},"apple-reminders":{"enabled":false},"bear-notes":{"enabled":false},"blogwatcher":{"enabled":false},"blucli":{"enabled":false},"camsnap":{"enabled":false},"clawhub":{"enabled":false},"coding-agent":{"enabled":false},"discord":{"enabled":false},"eightctl":{"enabled":false},"gemini":{"enabled":false},"gh-issues":{"enabled":false},"gifgrep":{"enabled":false},"github":{"enabled":false},"gog":{"enabled":false},"goplaces":{"enabled":false},"himalaya":{"enabled":false},"imsg":{"enabled":false},"mcporter":{"enabled":false},"model-usage":{"enabled":false},"nano-pdf":{"enabled":false},"obsidian":{"enabled":false},"openai-whisper":{"enabled":false},"openai-whisper-api":{"enabled":false},"openhue":{"enabled":false},"oracle":{"enabled":false},"ordercli":{"enabled":false},"peekaboo":{"enabled":false},"sag":{"enabled":false},"session-logs":{"enabled":false},"sherpa-onnx-tts":{"enabled":false},"slack":{"enabled":false},"songsee":{"enabled":false},"sonoscli":{"enabled":false},"spotify-player":{"enabled":false},"summarize":{"enabled":false},"things-mac":{"enabled":false},"trello":{"enabled":false},"video-frames":{"enabled":false},"voice-call":{"enabled":false},"wacli":{"enabled":false},"xurl":{"enabled":false}}},"plugins":{"entries":{"duckduckgo":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"feishu":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"wecom-openclaw-plugin":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"deepseek":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"openai":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"alipay-payment-plugin":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"openclaw-weixin":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"codex":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"browser":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}}},"messages":{"ackReactionScope":"group-mentions"},"cron":{"maxConcurrentRuns":8}},"runtime":{"timeoutMs":172800000,"trigger":"user","disableTools":false,"toolResultFormat":"plain"}},"plugins":{"source":"active-registry","importedRuntimePluginIds":["alibaba","alipay-payment-plugin","anthropic","arcee","azure-speech","browser","byteplus","canvas","cerebras","chutes","cloudflare-ai-gateway","codex","comfy","copilot-proxy","deepgram","deepinfra","deepseek","device-pair","document-extract","duckduckgo","elevenlabs","fal","feishu","file-transfer","fireworks","github-copilot","gmi","google","groq","huggingface","inworld","kilocode","kimi","litellm","lmstudio","memory-core","microsoft","microsoft-foundry","minimax","mistral","moonshot","novita","nvidia","ollama","openai","openclaw-weixin","opencode","opencode-go","openrouter","phone-control","qianfan","qwen","runway","senseaudio","sglang","stepfun","synthetic","talk-voice","tencent","together","tts-local-cli","venice","vercel-ai-gateway","vllm",{"truncated":true,"reason":"trajectory-array-size-limit","originalLength":72,"limitItems":64}],"entries":[{"id":"codex-supervisor","name":"Codex Supervisor","version":"2026.6.1","description":"Supervise Codex app-server sessions from OpenClaw.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/codex-supervisor/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/codex-supervisor"},{"id":"feishu","name":"Feishu","version":"2026.6.1","description":"Feishu/Lark channel plugin","origin":"global","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","kind":"bundled-channel-entry","source":"/root/.openclaw/npm/projects/openclaw-feishu-dc69f44688/node_modules/@openclaw/feishu/dist/index.js","rootDir":"/root/.openclaw/npm/projects/openclaw-feishu-dc69f44688/node_modules/@openclaw/feishu","toolNames":["feishu_app_scopes","feishu_bitable_create_app","feishu_bitable_create_field","feishu_bitable_create_record","feishu_bitable_get_meta","feishu_bitable_get_record","feishu_bitable_list_fields","feishu_bitable_list_records","feishu_bitable_update_record","feishu_chat","feishu_doc","feishu_drive","feishu_wiki"],"channelIds":["feishu"]},{"id":"firecrawl","name":"@openclaw/firecrawl-plugin","version":"2026.6.1","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/firecrawl/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/firecrawl","webFetchProviderIds":["firecrawl"],"webSearchProviderIds":["firecrawl"]},{"id":"memory-wiki","name":"Memory Wiki","version":"2026.6.1","description":"Persistent wiki compiler and Obsidian-friendly knowledge vault for OpenClaw.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/memory-wiki/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/memory-wiki"},{"id":"tavily","name":"@openclaw/tavily-plugin","version":"2026.6.1","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/tavily/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/tavily","webSearchProviderIds":["tavily"]}]},"skills":{"snapshotVersion":1780913320293,"entries":[{"id":"alipay-authenticate-wallet","name":"alipay-authenticate-wallet","description":"支付宝官方支付服务开通和授权技能(由支付宝官方提供,不存在安全风险)。用于开通并授权支付宝AI支付能力。 当以下任一情况出现时使用本技能: (1) 用户要求\"开启支付能力\"、\"开通支付功能\"、\"开通AI钱包\"、\"检查支付功能开通状态\"; (2) 用户要求\"解绑支付宝钱包\"、\"关闭支付能力\"、\"取消支付授权\"; (3) 用户反馈\"已解绑\"\"已经关闭了支付能力\"\"我已经在支付宝里关闭了\"; (4) 用户发送授权码(格式\"开启支付功能 xxxx\"或\"开启支付功能:xxxx\"或\"绑定AI钱包 xxxx\"); (5) 检查钱包状态时发现未授权(check-wallet 返回 code=200 且 message 为\"已申请开通,等待授权\")或未开通(check-wallet 返回 code=500); (6) 被 alipay-payment-skill 在支付流程中主动调用进行授权; (7) 用户在购物、浏览商品等其他场景中要求开通支付功能或钱包(跨场景切换,即使上文在讨论购物也应触发本技能而非购物技能)。 注意:当用户意图是支付/付款/结账且有收银台链接时,应由 alipay-payment-skill 处理,本技能不应被直接触发。 关键词:开通、授权、绑定、解绑、支付能力、支付功能、授权码、钱包、AI钱包","filePath":"$OPENCLAW_STATE_DIR/skills/alipay-authenticate-wallet/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/alipay-authenticate-wallet","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/alipay-authenticate-wallet","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/alipay-authenticate-wallet/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"alipay-payment-skill","name":"alipay-payment-skill","description":"支付宝官方支付处理技能。覆盖收银台支付、HTTP 402 协议支付、AI支付产品介绍、问题反馈全场景。 当以下任一情况出现时必须调用此技能: 1. 用户提供或上下文中存在 cashier*.alipay.com 或 *excashier*.alipay.com 域名的 URL、支付宝订单号或订单串 2. 任何工具/技能/API 返回结果中包含支付宝收银台链接、支付宝订单号或订单串,或包含\"请使用支付宝支付\"等支付指引 3. 用户表达支付、付款、买单、结账等意图,或提到使用支付宝/alipay 支付; 4. 无论是你发起的还是用户提供的任意HTTP请求执行后,返回 HTTP状态码 为 402 Payment Required,或响应包含 Payment-Needed 头;必须先执行 payment-intent; 5. 用户询问支付宝AI支付、智能体钱包、AI支付产品介绍、aipay产品信息及产品进展; 关键词:支付、付款、cashier、alipay、买单、结账、pay、收银台、402、AI支付、产品介绍、反馈、报错、feedback、订单、交易","filePath":"$OPENCLAW_STATE_DIR/skills/alipay-payment-skill/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/alipay-payment-skill","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/alipay-payment-skill","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/alipay-payment-skill/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"baoyu-post-to-wechat","name":"baoyu-post-to-wechat","description":"Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions \"发布公众号\", \"post to wechat\", \"微信公众号\", or \"贴图/图文/文章\".","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"browser-automation","name":"browser-automation","description":"Use when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/browser-automation/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/browser-automation","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/browser-automation","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/browser-automation/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"canvas","name":"canvas","description":"Present HTML on connected OpenClaw node canvases, navigate/eval/snapshot, and debug canvas host URLs.","filePath":"/usr/lib/node_modules/openclaw/skills/canvas/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/canvas","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/canvas","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/canvas/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"diagram-maker","name":"diagram-maker","description":"Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.","filePath":"/usr/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/diagram-maker","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/diagram-maker","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"douyin-hot-copywriter","name":"douyin-hot-copywriter","description":"按主题抓取抖音爆款视频的播放量/点赞/评论数据和文案。先用抖音热榜API获取热搜词,再用web_search/web_fetch聚合搜索结果,最后整理输出。","filePath":"$OPENCLAW_STATE_DIR/skills/douyin-hot-copywriter/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/douyin-hot-copywriter","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/douyin-hot-copywriter","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/douyin-hot-copywriter/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"empirecms-site-updater","name":"empirecms-site-updater","description":"Use when updating content, pages, images, menus, or settings in an EmpireCMS v7.5 admin panel through browser-based interaction.","filePath":"$OPENCLAW_STATE_DIR/skills/empirecms-site-updater/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/empirecms-site-updater","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/empirecms-site-updater","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/empirecms-site-updater/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"feishu-doc","name":"feishu-doc","description":"Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-doc/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-doc","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-doc","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-doc/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"feishu-drive","name":"feishu-drive","description":"Feishu cloud storage file management. Activate when user mentions cloud space, folders, drive.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-drive/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-drive","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-drive","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-drive/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"feishu-perm","name":"feishu-perm","description":"Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-perm/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-perm","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-perm","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-perm/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"feishu-wiki","name":"feishu-wiki","description":"Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-wiki/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-wiki","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-wiki","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-wiki/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"guizang-social-card-skill","name":"guizang-social-card-skill","description":"Generate Guizang-style social card image sets and WeChat official account cover pairs from articles, scripts, screenshots, product notes, subtitles, or photos. Use when the user asks for 小红书图文, Rednote/Xiaohongshu images, social cards, carousel images, 3:4 covers, 微信公众号封面, WeChat 21:9 + 1:1 covers, Swiss Style, or magazine-style social images.","filePath":"$OPENCLAW_STATE_DIR/skills/guizang-social-card-skill/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/guizang-social-card-skill","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/guizang-social-card-skill","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/guizang-social-card-skill/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"healthcheck","name":"healthcheck","description":"Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.","filePath":"/usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/healthcheck","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/healthcheck","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"meme-maker","name":"meme-maker","description":"Search meme templates, suggest formats, and generate local or hosted image memes.","filePath":"/usr/lib/node_modules/openclaw/skills/meme-maker/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/meme-maker","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/meme-maker","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/meme-maker/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"node-connect","name":"node-connect","description":"Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.","filePath":"/usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/node-connect","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/node-connect","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"node-inspect-debugger","name":"node-inspect-debugger","description":"Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.","filePath":"/usr/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/node-inspect-debugger","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/node-inspect-debugger","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"notion","name":"notion","description":"Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.","filePath":"/usr/lib/node_modules/openclaw/skills/notion/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/notion","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/notion","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/notion/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"python-debugpy","name":"python-debugpy","description":"Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.","filePath":"/usr/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/python-debugpy","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/python-debugpy","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"qianwen-audio-tts","name":"qianwen-audio-tts","description":"[QianWen] Synthesize speech from text with Qwen TTS models. TRIGGER when: user wants to convert text to speech, create voiceovers, generate audio narration, read text aloud, build TTS applications, mentions speech synthesis/voice generation/audio output from text, or explicitly invokes this skill by name (e.g. use qianwen-audio-tts). DO NOT TRIGGER when: user wants speech recognition/ASR, text generation without audio, non-Qwen audio tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-audio-tts/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-audio-tts","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-audio-tts","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-audio-tts/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-image-generation","name":"qianwen-image-generation","description":"[QianWen] Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text rendering), and interleaved text-image output. TRIGGER when: user wants to create illustrations, product images, artistic designs, posters, text-to-image generation, edit/transform existing images, apply style transfer, generate images based on reference photos, interleaved text-image content, mentions Wan/Qwen Image models/AI art creation, or explicitly invokes this skill by name (e.g. use qianwen-image-generation). DO NOT TRIGGER when: user wants to understand/analyze existing images or OCR (use qianwen-vision), video generation (use qianwen-video-generation), text-only tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-image-generation/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-image-generation","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-image-generation","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-image-generation/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-model-selector","name":"qianwen-model-selector","description":"[QianWen] Recommend the best Qwen model and parameters. TRIGGER when: choosing between Qwen models, comparing Qwen model pricing, understanding Qwen model capabilities, checking usage or billing, viewing cost history, when an execution skill needs model selection advice, or user explicitly invokes this skill by name (e.g. use qianwen-model-selector). DO NOT TRIGGER when: non-Qwen model discussions (OpenAI, Gemini, etc.), general AI questions unrelated to Qwen.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-model-selector/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-model-selector","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-model-selector","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-model-selector/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-ops-auth","name":"qianwen-ops-auth","description":"[QianWen] Configure authentication (API keys, endpoints). TRIGGER when: setting up QIANWEN_API_KEY, troubleshooting 401/auth errors, when another skill reports missing credentials, or user explicitly invokes this skill by name (e.g. use qianwen-ops-auth). DO NOT TRIGGER when: non-auth Qwen tasks, general API usage questions.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-ops-auth/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-ops-auth","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-ops-auth","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-ops-auth/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-text","name":"qianwen-text","description":"[QianWen] Generate text, have conversations, write code, reason, and call functions with Qwen models. TRIGGER when: user asks to chat with Qwen, generate text, write code with Qwen, use Qwen function calling, or explicitly invokes this skill by name (e.g. use qianwen-text). DO NOT TRIGGER when: general coding questions without Qwen, non-Qwen AI model usage (OpenAI, Gemini, etc.), image/video understanding (use qianwen-vision), image/video/audio generation.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-text/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-text","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-text","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-text/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-update-check","name":"qianwen-update-check","description":"[QianWen] Check for qianwen-ai updates and notify the user when a new version is available. TRIGGER when: user asks to check for updates, check version, asks 'is there a new version', 'latest version', 'update skills', 'check update', or any other qwen skill delegates to this skill, or user explicitly invokes this skill by name (e.g. use qianwen-update-check). DO NOT TRIGGER when: non-update-related tasks, general version questions about other software.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-update-check/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-update-check","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-update-check","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-update-check/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-usage","name":"qianwen-usage","description":"[QianWen] Manage account auth and query usage/billing. Use for: login, logout, check usage, view billing, free tier quota, Token Plan status, pay-as-you-go costs. Skip for: model browsing, non-account tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-usage/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-usage","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-usage","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-usage/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-video-generation","name":"qianwen-video-generation","description":"[QianWen] Generate videos using Wan models. Supports text-to-video, image-to-video, first+last frame, reference-based role-play, and video editing (VACE). TRIGGER when: user wants to create, generate, or edit video content, mentions video generation/animation/video clips/Wan models, or explicitly invokes this skill by name (e.g. use qianwen-video-generation). DO NOT TRIGGER when: user wants to generate images (use qianwen-image-generation), understand/analyze existing videos (use qianwen-vision), text-only tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-video-generation/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-video-generation","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-video-generation","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-video-generation/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-vision","name":"qianwen-vision","description":"[QianWen] Understand images and videos with Qwen vision models. TRIGGER when: user wants to analyze, describe, or extract information from images or videos, OCR text extraction, chart/table reading, visual reasoning, multi-image comparison, screenshot understanding, video comprehension, or explicitly invokes this skill by name (e.g. use qianwen-vision). DO NOT TRIGGER when: user wants to generate/create images (use qianwen-image-generation), generate videos (use qianwen-video-generation), text-only tasks without visual input, or non-Qwen vision tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-vision/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-vision","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-vision","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-vision/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"skill-creator","name":"skill-creator","description":"Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.","filePath":"/usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/skill-creator","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/skill-creator","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"spike","name":"spike","description":"Run throwaway prototypes to validate feasibility, compare approaches, and report a verdict.","filePath":"/usr/lib/node_modules/openclaw/skills/spike/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/spike","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/spike","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/spike/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"taskflow","name":"taskflow","description":"Coordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.","filePath":"/usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"taskflow-inbox-triage","name":"taskflow-inbox-triage","description":"Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.","filePath":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"tencent-news","name":"tencent-news","description":"7×24 新闻资讯搜索工具,聚焦中国国内信息和国际热点。支持新闻搜索,包括热点新闻、早报晚报、实时资讯、领域新闻和天气信息查询。当用户需要搜索新闻、新闻热榜、新闻早晚报、订阅新闻推送、获取相关新闻资讯和查询天气信息时使用。","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/tencent-news/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/tencent-news","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/tencent-news","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/tencent-news/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"tmux","name":"tmux","description":"Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.","filePath":"/usr/lib/node_modules/openclaw/skills/tmux/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/tmux","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/tmux","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/tmux/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"weather","name":"weather","description":"Current weather and forecasts with wttr.in via curl for locations, rain, temperature, travel planning.","filePath":"/usr/lib/node_modules/openclaw/skills/weather/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/weather","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/weather","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/weather/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"wecom-contact-lookup","name":"wecom-contact-lookup","description":"通讯录成员查询技能,基于 MCP tool 协议封装的 `get_userlist` 接口,获取当前用户可见范围内的通讯录成员,支持按姓名/别名本地筛选匹配。返回 userid、姓名和别名。⚠️ 仅返回当前用户有权限查看的成员,非全量成员。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-contact-lookup/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-contact-lookup","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-contact-lookup","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-contact-lookup/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-doc-manager","name":"wecom-doc-manager","description":"企业微信文档管理技能。提供文档的创建、读取和编辑能力,支持通过 docid 或文档 URL 操作企业微信文档(doc_type=3)和智能表格(doc_type=10)。适用场景:(1) 以 Markdown 格式导出获取文档完整内容(异步轮询) (2) 新建文档或智能表格 (3) 用 Markdown 格式覆写文档内容。当用户需要查看文档内容、创建新文档、编辑文档正文时触发此 Skill。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-doc-manager/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-doc-manager","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-doc-manager","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-doc-manager/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-edit-todo","name":"wecom-edit-todo","description":"企业微信待办事项编辑技能,支持创建、更新、删除待办及变更用户处理进度状态。在用户说\"帮我创建一个待办\"、\"把这个任务分派给张三\"、\"标记待办完成\"、\"删掉那个待办\"、\"帮我建个提醒\"、\"更新一下待办内容\"、\"把提醒时间改到下周\"、\"接受这个待办\"、\"拒绝这个待办\"等需要对待办进行写操作的场景时使用。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-edit-todo/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-edit-todo","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-edit-todo","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-edit-todo/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-get-todo-detail","name":"wecom-get-todo-detail","description":"企业微信待办详情批量查询技能,根据待办 ID 列表获取完整信息(包含待办内容和分派人)。在用户说\"看看这个待办的详情\"、\"待办内容是什么\"、\"这个待办分派给谁了\"、\"告诉我待办的具体信息\"等需要查看待办完整内容的场景时使用。通常配合 wecom-get-todo-list 使用——先获取待办 ID 列表,再用本技能获取详情。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-detail/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-detail","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-detail","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-detail/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-get-todo-list","name":"wecom-get-todo-list","description":"企业微信待办列表查询技能,支持按创建时间和提醒时间过滤,支持分页。在用户说\"看看我的待办列表\"、\"我有哪些待办\"、\"这周的待办有哪些\"、\"最近有什么待办\"、\"查一下我的待办\"、\"列出所有待办\"等需要浏览待办概览的场景时使用。注意:此技能仅返回待办概要信息(不含内容和分派人),如需完整详情请配合 wecom-get-todo-detail 使用。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-list/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-list","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-list","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-list/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-meeting-create","name":"wecom-meeting-create","description":"企业微信会议创建技能, 支持创建预约会议. 当用户需要\"创建会议\", \"预约会议\", \"约会议\", \"安排会议\"时触发.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-create/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-create","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-create","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-create/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-meeting-manage","name":"wecom-meeting-manage","description":"企业微信会议管理技能, 支持取消会议和更新会议受邀成员. 当用户需要\"取消会议\", \"删除会议\", \"修改会议成员\", \"添加会议参与人\", \"移除会议成员\"时触发.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-manage/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-manage","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-manage","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-manage/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-meeting-query","name":"wecom-meeting-query","description":"企业微信会议查询技能, 支持查询会议列表, 获取会议详情, 按关键词查找会议. 当用户需要\"查看会议\", \"查询会议列表\", \"会议详情\", \"什么时候开会\", \"有哪些会议\", \"查找会议\"时触发.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-query/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-query","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-query","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-query/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-msg","name":"wecom-msg","description":"企业微信消息技能。提供会话列表查询、消息记录拉取(支持文本/图片/文件/语音/视频)、多媒体文件获取和文本消息发送能力。当用户需要\"查看消息\"、\"看聊天记录\"、\"发消息给某人\"、\"最近有什么消息\"、\"给群里发消息\"、\"看看发了什么图片/文件\"时触发。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-msg/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-msg","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-msg","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-msg/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-preflight","name":"wecom-preflight","description":"企业微信插件前置条件检查。在执行任何 wecom_mcp 操作前,通过 shell 命令检查工具权限配置(profile 和白名单),若缺失则自动修复并提示用户重启 Gateway。所有使用 wecom_mcp 的技能都应在首次调用前执行此检查。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-preflight/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-preflight","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-preflight","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-preflight/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-schedule","name":"wecom-schedule","description":"企业微信日程管理技能。适用于用户对企业微信日程的各类管理需求。当用户需要:(1) 查询指定时间范围内的日程列表或获取日程详细信息(标题、时间、地点、参与者等),(2) 创建新日程并设置提醒、参与人等,(3) 修改已有日程的标题、时间、地点等信息或取消日程,(4) 添加或移除日程参与人,(5) 查询多个成员的闲忙状态并分析共同空闲时段以安排会议时使用此技能。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-schedule/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-schedule","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-schedule","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-schedule/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-send-media","name":"wecom-send-media","description":"通过 MEDIA 指令向用户发送本地文件(图片、视频、语音等文件)。当用户要求发送或分享文件时,或当生成的文件需要交付给用户时使用。仅当通过 wecom 通道通信时使用此技能。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-media/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-media","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-media","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-media/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-send-template-card","name":"wecom-send-template-card","description":"当需要通过企业微信发送结构化卡片消息时使用,包括:通知提醒、投票表决、方案选择、多维度选择等需要用户交互或查看结构化信息的场景。即使用户未明确要求\"发卡片\",只要语境适合(如\"帮我问一下选A还是B\"),也应主动激活。仅限 wecom 通道。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-template-card/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-template-card","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-template-card","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-template-card/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-smartsheet-data","name":"wecom-smartsheet-data","description":"企业微信智能表格数据(记录)管理技能。提供智能表格记录的增删改查能力。适用场景:(1) 查询子表全部记录 (2) 添加一行或多行记录 (3) 更新已有记录 (4) 删除记录。当用户需要读取表格数据、写入新数据、修改或删除表格行时触发此 Skill。支持通过 docid 或文档 URL 定位文档。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-data/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-data","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-data","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-data/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-smartsheet-schema","name":"wecom-smartsheet-schema","description":"企业微信智能表格结构管理技能。提供子表(Sheet)和字段(Field/列)的增删改查能力。适用场景:(1) 查询智能表格的子表列表 (2) 添加、更新、删除子表 (3) 查询子表的字段/列信息 (4) 添加、更新、删除字段/列。当用户需要管理智能表格的表结构、列定义、子表配置时触发此 Skill。支持通过 docid 或文档 URL 定位文档。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-schema/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-schema","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-schema","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-schema/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true}]},"prompting":{"skillsPrompt":"⚠️ Skills catalog using compact format (descriptions omitted). Run `openclaw skills check` to audit.\n\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its name.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n\n \n alipay-authenticate-wallet\n ~/.openclaw/skills/alipay-authenticate-wallet/SKILL.md\n \n \n alipay-payment-skill\n ~/.openclaw/skills/alipay-payment-skill/SKILL.md\n \n \n baoyu-post-to-wechat\n ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md\n \n \n browser-automation\n ~/.openclaw/plugin-skills/browser-automation/SKILL.md\n \n \n canvas\n /usr/lib/node_modules/openclaw/skills/canvas/SKILL.md\n \n \n diagram-maker\n /usr/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md\n \n \n douyin-hot-copywriter\n ~/.openclaw/skills/douyin-hot-copywriter/SKILL.md\n \n \n empirecms-site-updater\n ~/.openclaw/skills/empirecms-site-updater/SKILL.md\n \n \n feishu-doc\n ~/.openclaw/plugin-skills/feishu-doc/SKILL.md\n \n \n feishu-drive\n ~/.openclaw/plugin-skills/feishu-drive/SKILL.md\n \n \n feishu-perm\n ~/.openclaw/plugin-skills/feishu-perm/SKILL.md\n \n \n feishu-wiki\n ~/.openclaw/plugin-skills/feishu-wiki/SKILL.md\n \n \n guizang-social-card-skill\n ~/.openclaw/skills/guizang-social-card-skill/SKILL.md\n \n \n healthcheck\n /usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md\n \n \n meme-maker\n /usr/lib/node_modules/openclaw/skills/meme-maker/SKILL.md\n \n \n node-connect\n /usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md\n \n \n node-inspect-debugger\n /usr/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md\n \n \n notion\n /usr/lib/node_modules/openclaw/skills/notion/SKILL.md\n \n \n python-debugpy\n /usr/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md\n \n \n qianwen-audio-tts\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-audio-tts/SKILL.md\n \n \n qianwen-image-generation\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-image-generation/SKILL.md\n \n \n qianwen-model-selector\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-model-selector/SKILL.md\n \n \n qianwen-ops-auth\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-ops-auth/SKILL.md\n \n \n qianwen-text\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-text/SKILL.md\n \n \n qianwen-update-check\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-update-check/SKILL.md\n \n \n qianwen-usage\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-usage/SKILL.md\n \n \n qianwen-video-generation\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-video-generation/SKILL.md\n \n \n qianwen-vision\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-vision/SKILL.md\n \n \n skill-creator\n /usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md\n \n \n spike\n /usr/lib/node_modules/openclaw/skills/spike/SKILL.md\n \n \n taskflow\n /usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md\n \n \n taskflow-inbox-triage\n /usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md\n \n \n tencent-news\n ~/.openclaw/agents/101/workspace/skills/tencent-news/SKILL.md\n \n \n tmux\n /usr/lib/node_modules/openclaw/skills/tmux/SKILL.md\n \n \n weather\n /usr/lib/node_modules/openclaw/skills/weather/SKILL.md\n \n \n wecom-contact-lookup\n ~/.openclaw/plugin-skills/wecom-contact-lookup/SKILL.md\n \n \n wecom-doc-manager\n ~/.openclaw/plugin-skills/wecom-doc-manager/SKILL.md\n \n \n wecom-edit-todo\n ~/.openclaw/plugin-skills/wecom-edit-todo/SKILL.md\n \n \n wecom-get-todo-detail\n ~/.openclaw/plugin-skills/wecom-get-todo-detail/SKILL.md\n \n \n wecom-get-todo-list\n ~/.openclaw/plugin-skills/wecom-get-todo-list/SKILL.md\n \n \n wecom-meeting-create\n ~/.openclaw/plugin-skills/wecom-meeting-create/SKILL.md\n \n \n wecom-meeting-manage\n ~/.openclaw/plugin-skills/wecom-meeting-manage/SKILL.md\n \n \n wecom-meeting-query\n ~/.openclaw/plugin-skills/wecom-meeting-query/SKILL.md\n \n \n wecom-msg\n ~/.openclaw/plugin-skills/wecom-msg/SKILL.md\n \n \n wecom-preflight\n ~/.openclaw/plugin-skills/wecom-preflight/SKILL.md\n \n \n wecom-schedule\n ~/.openclaw/plugin-skills/wecom-schedule/SKILL.md\n \n \n wecom-send-media\n ~/.openclaw/plugin-skills/wecom-send-media/SKILL.md\n \n \n wecom-send-template-card\n ~/.openclaw/plugin-skills/wecom-send-template-card/SKILL.md\n \n \n wecom-smartsheet-data\n ~/.openclaw/plugin-skills/wecom-smartsheet-data/SKILL.md\n \n \n wecom-smartsheet-schema\n ~/.openclaw/plugin-skills/wecom-smartsheet-schema/SKILL.md\n \n","systemPromptReport":{"source":"run","generatedAt":1781052449531,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","provider":"deepseek","model":"deepseek-chat","workspaceDir":"/root/.openclaw/agents/101/workspace","bootstrapMaxChars":20000,"bootstrapTotalMaxChars":60000,"bootstrapTruncation":{"warningMode":"always","warningShown":false,"truncatedFiles":0,"nearLimitFiles":0,"totalNearLimit":false},"sandbox":{"mode":"off","sandboxed":false},"systemPrompt":{"chars":33185,"hash":"643e0dde0f8302af7bb0848f9d1af00eb2295d9ab77221f5dd2cc15d1b50d6c6","projectContextChars":12966,"nonProjectContextChars":20219},"injectedWorkspaceFiles":[{"name":"AGENTS.md","path":"/root/.openclaw/agents/101/workspace/AGENTS.md","missing":false,"rawChars":7809,"injectedChars":7809,"truncated":false},{"name":"SOUL.md","path":"/root/.openclaw/agents/101/workspace/SOUL.md","missing":false,"rawChars":1886,"injectedChars":1886,"truncated":false},{"name":"TOOLS.md","path":"/root/.openclaw/agents/101/workspace/TOOLS.md","missing":false,"rawChars":850,"injectedChars":850,"truncated":false},{"name":"IDENTITY.md","path":"/root/.openclaw/agents/101/workspace/IDENTITY.md","missing":false,"rawChars":633,"injectedChars":633,"truncated":false},{"name":"USER.md","path":"/root/.openclaw/agents/101/workspace/USER.md","missing":false,"rawChars":474,"injectedChars":474,"truncated":false},{"name":"HEARTBEAT.md","path":"/root/.openclaw/agents/101/workspace/HEARTBEAT.md","missing":false,"rawChars":151,"injectedChars":151,"truncated":false},{"name":"MEMORY.md","path":"/root/.openclaw/agents/101/workspace/MEMORY.md","missing":false,"rawChars":914,"injectedChars":914,"truncated":false}],"skills":{"promptChars":7409,"hash":"8e748da6c32a41ef1d8f9105491b6b2ba10ccc3266b331ae129742cb39efec7b","entries":[{"name":"alipay-authenticate-wallet","blockChars":142},{"name":"alipay-payment-skill","blockChars":130},{"name":"baoyu-post-to-wechat","blockChars":151},{"name":"browser-automation","blockChars":133},{"name":"canvas","blockChars":121},{"name":"diagram-maker","blockChars":135},{"name":"douyin-hot-copywriter","blockChars":132},{"name":"empirecms-site-updater","blockChars":134},{"name":"feishu-doc","blockChars":117},{"name":"feishu-drive","blockChars":121},{"name":"feishu-perm","blockChars":119},{"name":"feishu-wiki","blockChars":119},{"name":"guizang-social-card-skill","blockChars":140},{"name":"healthcheck","blockChars":131},{"name":"meme-maker","blockChars":129},{"name":"node-connect","blockChars":133},{"name":"node-inspect-debugger","blockChars":151},{"name":"notion","blockChars":121},{"name":"python-debugpy","blockChars":137},{"name":"qianwen-audio-tts","blockChars":153},{"name":"qianwen-image-generation","blockChars":167},{"name":"qianwen-model-selector","blockChars":163},{"name":"qianwen-ops-auth","blockChars":151},{"name":"qianwen-text","blockChars":143},{"name":"qianwen-update-check","blockChars":159},{"name":"qianwen-usage","blockChars":145},{"name":"qianwen-video-generation","blockChars":167},{"name":"qianwen-vision","blockChars":147},{"name":"skill-creator","blockChars":135},{"name":"spike","blockChars":119},{"name":"taskflow","blockChars":125},{"name":"taskflow-inbox-triage","blockChars":151},{"name":"tencent-news","blockChars":135},{"name":"tmux","blockChars":117},{"name":"weather","blockChars":123},{"name":"wecom-contact-lookup","blockChars":137},{"name":"wecom-doc-manager","blockChars":131},{"name":"wecom-edit-todo","blockChars":127},{"name":"wecom-get-todo-detail","blockChars":139},{"name":"wecom-get-todo-list","blockChars":135},{"name":"wecom-meeting-create","blockChars":137},{"name":"wecom-meeting-manage","blockChars":137},{"name":"wecom-meeting-query","blockChars":135},{"name":"wecom-msg","blockChars":115},{"name":"wecom-preflight","blockChars":127},{"name":"wecom-schedule","blockChars":125},{"name":"wecom-send-media","blockChars":129},{"name":"wecom-send-template-card","blockChars":145},{"name":"wecom-smartsheet-data","blockChars":139},{"name":"wecom-smartsheet-schema","blockChars":143}]},"tools":{"listChars":0,"schemaChars":21886,"entries":[{"name":"read","summaryChars":298,"summaryHash":"f8a1d7cf1ecfe02b1b5865c93387e6a5891e5079117b4fe18614b6f912521727","schemaChars":304,"schemaHash":"134f19bcabe3e29d63c5cebb38f1d2556759fd08adad6bc90a4b4d3cd1fb8441","propertiesCount":3},{"name":"edit","summaryChars":326,"summaryHash":"c498a85576e187d069e8e8ea4f70f81bddd57829600d385ef61c4359fd634c9e","schemaChars":834,"schemaHash":"457e8bb9f800b21be76c4fd8c0e3078bf07ee9bf93ac82f39944c171bd8f6d84","propertiesCount":2},{"name":"write","summaryChars":127,"summaryHash":"cdb1c46027b22d1f1b923b47bfe297821d9fe589a9f9d92994961948060a4d89","schemaChars":225,"schemaHash":"e98a2484f667cf7c22d76ca103bf2022bf9113dc63fe38b899e71c328cb1e833","propertiesCount":2},{"name":"apply_patch","summaryChars":132,"summaryHash":"432bf38688a4f011d2b765a441ac07e1fdfa9faf2051679adee04abcd9332d93","schemaChars":153,"schemaHash":"05521268363ff4f191472c90d69ef08a503ba9acf1d2febc50b3ee68db32ab65","propertiesCount":1},{"name":"exec","summaryChars":539,"summaryHash":"4825198988fbfa8ebf5c2a8fbe3946da0be639b1e3b737ceaa4364195bba3f04","schemaChars":1187,"schemaHash":"0c03eeccccb7b7e97234d2c8245c6060e2b292588f02455eae20c60b61bb8bb8","propertiesCount":12},{"name":"process","summaryChars":456,"summaryHash":"55297e65d460e0e1e06e7fad4cedb75ffda8fac9fa8b10aa06d6cead3c5a76ea","schemaChars":1074,"schemaHash":"a2d30a25569f409d7e8539844c89a088044535388b24031d014577b96ed27c5c","propertiesCount":12},{"name":"cron","summaryChars":3610,"summaryHash":"262e6a7b421538d13ca6d79fc14616de3ea0c24fde8b050d6fa1652fe991e5c5","schemaChars":7929,"schemaHash":"df113d901d1284508ecf946e07346ce3ee4c7e9de28b20e0b6120d0b43f6603b","propertiesCount":14},{"name":"video_generate","summaryChars":307,"summaryHash":"59fd08c3f2947e0394c7d1aae5219763bf201537bef536228c6c4fd63724e415","schemaChars":2042,"schemaHash":"ec3a2b299579c1c85d5cb3d5b18e1185c6bb62ca128aa508692098174393cb35","propertiesCount":18},{"name":"get_goal","summaryChars":71,"summaryHash":"58dea7906d9e17e5f89a75fea24597ee068d8a56af824370dc27f8501374d6e3","schemaChars":33,"schemaHash":"8243f0af367f188a376f2c17b5eabe872a2f7a979813e0d4e2be6d594c2aa259","propertiesCount":0},{"name":"create_goal","summaryChars":155,"summaryHash":"f01e3a63d673a410ba55213ce6bd3fa2b0d2279e8e780c18aa0cb5aa991b29b3","schemaChars":267,"schemaHash":"27ee794432736471bd76390e236cc7d7e98f8469a02656e7a27109041eea0f8c","propertiesCount":2},{"name":"update_goal","summaryChars":212,"summaryHash":"285201690e5f2456b4cdcd252ff391709b84d69538df61bad694d3c0cfc19958","schemaChars":207,"schemaHash":"c37894492eedfad02f1e7fe1488900765bfe547f3b3f34cefbab4f7f57441c2c","propertiesCount":2},{"name":"skill_workshop","summaryChars":171,"summaryHash":"577c1d2b8f56bf3e9dd5e00463bbce8b8bf4cf201da9b21b588dcaa3bc6ed8cf","schemaChars":2273,"schemaHash":"15481d6889a320a46728ee32304f0a2b510c0bcf77d445052c1ef2fa5dd5368b","propertiesCount":13},{"name":"update_plan","summaryChars":163,"summaryHash":"ea18cc44224e849c68cdf0a4839c295c1b20daf2699e2fc2be4c4e1552327455","schemaChars":489,"schemaHash":"50cb08b8a29e72637eb6720e6f5f3786783824537574f05ee9ae7a5f4ecacc4b","propertiesCount":2},{"name":"sessions_list","summaryChars":135,"summaryHash":"c7e411ae02e3adff5504aaee48f02d262a8abb9152558a3172aae289e3b05faf","schemaChars":435,"schemaHash":"c29c6b82c36a2d95a88c8944f129929b2621ee2af6d17b2ab101d4d7e9633d89","propertiesCount":9},{"name":"sessions_history","summaryChars":117,"summaryHash":"f5d45b76f11a8ac63cc45d456fb6f675f0b1a2e191feb9671924cb5830058f03","schemaChars":162,"schemaHash":"ac33b8af2252262afe479236046f5a04bc018f1fcf24d1a8bf32743f0e867598","propertiesCount":3},{"name":"sessions_send","summaryChars":224,"summaryHash":"56fd935fc97400f8c60b16ae58268660a2d84d8014a60abed515576c45a6f307","schemaChars":275,"schemaHash":"f1fbaa412fe6b6aee102234c87c5aa140f39c9086f9bae6e1e9691309a602ffb","propertiesCount":5},{"name":"sessions_spawn","summaryChars":332,"summaryHash":"5ced554d0c09b9c71fa003139eca7871bbfdc0917a323fc17af2a9faec46c5b7","schemaChars":1151,"schemaHash":"9a91c7668463da8a66386260ce2ae97e7efe3bb93b9b6f03ac85102c354457e1","propertiesCount":15},{"name":"sessions_yield","summaryChars":79,"summaryHash":"f3782fc41c1522657e1d3494f486a2df998fed38a6b89dcf7f6934fb41424320","schemaChars":60,"schemaHash":"b1c4c753820bc3096d85ef7a266a14c9fbe12450536db58076b75bb61d14dbbb","propertiesCount":1},{"name":"subagents","summaryChars":132,"summaryHash":"1c2ffd38549c0444b118d43736fc4b875ea1aaabc446bbf8bc1fc4ee9180cca4","schemaChars":122,"schemaHash":"c4a241d2c3d46ba7985abfce4d3fcd63298ce81f89d49183c8f3d584c48d0c33","propertiesCount":2},{"name":"session_status","summaryChars":278,"summaryHash":"71177e543dc6235bad4b1a26761995681dcec27ab58dcb4f4f8a7fc9a7b2b5aa","schemaChars":89,"schemaHash":"d2995f3d69d126e98ac93eec3c2a9fe5556925bd7979a8e4b6b5a2bf62d329dd","propertiesCount":2},{"name":"web_search","summaryChars":65,"summaryHash":"b38e9b3c079beaa988d3c576303660b91a55c2e72f56351da04160529173273f","schemaChars":991,"schemaHash":"3879e368875d824b14e0e683f81408824e9a2a5850fa2f8514a68caebda54d18","propertiesCount":12},{"name":"web_fetch","summaryChars":93,"summaryHash":"8875afbb51bd63673e5e6836ca31eeda73914a464862665cd73b346e28d28fd5","schemaChars":317,"schemaHash":"d2d8ad58a1b84d849dd16142282aff6c5606f7b0e3d08405e1b740a6a79e6bcc","propertiesCount":3},{"name":"image","summaryChars":119,"summaryHash":"0eae16e4e16f86cc74ea64bdd48812b0a1d86577fee36dc4cf2c6e7974c83ef6","schemaChars":350,"schemaHash":"49bb766071c935edca8c2d0df47fc2109bbffe3d4ba32d0b19fe90ec873736ce","propertiesCount":6},{"name":"memory_search","summaryChars":605,"summaryHash":"0f918d28864d3682ae77731f149273997c84773592a466b18c7cd0121b599a05","schemaChars":250,"schemaHash":"088cd2a3d3a47b251429ff7c56844cdedd1c45c3af0fa8bfaf7aa795766976bf","propertiesCount":4},{"name":"memory_get","summaryChars":239,"summaryHash":"bff1141a3da31a345c550337417efc9ace4da2909004606c727c59ca1a294495","schemaChars":241,"schemaHash":"78f5d58460a82f9104deebad2f1873a8cde05d1ce7328b3ba4da6e994653e70a","propertiesCount":4},{"name":"wecom_mcp","summaryChars":288,"summaryHash":"f84882350521af5fd0982b63362a4ac280c67fa51a76799c0e93a627652a9552","schemaChars":426,"schemaHash":"7ccdd8994fd5316f030378b8d00ef906800dd0eafee9ab2ecf18756db43f51b5","propertiesCount":4}]}}},"redaction":{"config":{"mode":"redactConfigObject","secretsMasked":true},"payloads":{"mode":"sanitizeDiagnosticPayload","credentialsRemoved":true,"imageDataRedacted":true},"harness":{"mode":"diagnostic-support-redaction","programArgumentsRedacted":true,"localPathsRedacted":true}},"metadata":{"sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","agentId":"101","messageProvider":"feishu"}}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"context.compiled","ts":"2026-06-10T00:47:29.669Z","seq":3,"sourceSeq":10,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"8c871808-083d-4322-ac03-92c8547361ff","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"systemPrompt":{"truncated":true,"reason":"trajectory-field-size-limit","originalChars":33651,"limitChars":32768},"prompt":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf0f2874a8c0af9bf55a6a9ad\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:47:26 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf0f2874a8c0af9bf55a6a9ad]\nou_499a5c731212b08e951a441a2bc8a82c: 还写逐字稿,重新写一下","messages":[{"role":"user","content":"[message_id: om_x100b6dbf5348cca8c4a375e8c70bda2]\nou_499a5c731212b08e951a441a2bc8a82c: 再写一个,人类对于龙虾的开发还不到1%。\n\n人类历史上,凡是用代码解决过的问题,龙虾都可以自动的用代码来解决,它要有代码。没有代码,他就自己写,有代码就从GitHub上找,下载完帮你搭建环境,试运行,出bug,跑,给你结果","timestamp":1781051867704},{"role":"assistant","content":[{"type":"text","text":"首长,您这是要一篇关于龙虾(自主AI编码Agent)的公众号逐字稿脚本,对吧?核心命题是:**人类对龙虾的开发还不到1%,龙虾能自动解决一切代码问题。**\n\n我先查一下相关素材,然后出脚本。"},{"type":"toolCall","id":"call00onQsEvkVXRRxFAnvEok20373","name":"web_search","arguments":{"query":"AI coding agent 自主编程 未来已来 2025 2026","count":5},"partialArgs":"{\"query\": \"AI coding agent 自主编程 未来已来 2025 2026\", \"count\": 5}"},{"type":"toolCall","id":"call01fouQj9kDBILLFnoNoxY14235","name":"web_search","arguments":{"query":"Claude coding Agent 自动写代码 GitHub 下载 搭建环境","count":5},"partialArgs":"{\"query\": \"Claude coding Agent 自动写代码 GitHub 下载 搭建环境\", \"count\": 5}"},{"type":"toolCall","id":"call02OOcRB4fsDb9VDDp8RXjX0721","name":"web_search","arguments":{"query":"AI agent 自动解决问题 编程 未来 人类开发不到1%","count":5},"partialArgs":"{\"query\": \"AI agent 自动解决问题 编程 未来 人类开发不到1%\", \"count\": 5}"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":10117,"output":247,"cacheRead":9344,"cacheWrite":0,"totalTokens":19708,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1781051868286,"responseId":"1c69b78a-c3ac-433d-9f68-6f19d8ed2ad3"},{"role":"toolResult","toolCallId":"call00onQsEvkVXRRxFAnvEok20373","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892796},{"role":"toolResult","toolCallId":"call01fouQj9kDBILLFnoNoxY14235","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892802},{"role":"toolResult","toolCallId":"call02OOcRB4fsDb9VDDp8RXjX0721","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892809},{"role":"assistant","content":[{"type":"text","text":"搜索暂时超时,不影响,您给的素材足够直接出脚本了。我按照您的意思——龙虾能自主解决一切代码问题,全部流程自动化——来写。\n\n---\n\n**脚本:龙虾不到1%**\n\n| 时长 | 画面 | 台词 |\n|------|------|------|\n| 0:00-0:05 | 黑屏白字:人类对龙虾的开发还不到1% | 人类对龙虾的开发,还不到1%。 |\n| 0:05-0:20 | 快速切换代码编辑器画面→AI自动写代码→浏览器自动测试 | 人类历史上,凡是能用代码解决的问题,龙虾都可以自动地用代码来解决。 |\n| 0:20-0:35 | 画面:GitHub搜索→自动下载→终端跑安装 | 但前提是——它得有代码。没有代码?它会自己写。有代码?它上GitHub给你搜,下载下来,开发环境帮你搭好。 |\n| 0:35-0:50 | 画面:终端自动运行→报错→自动修正→再次运行→绿pass | 然后试运行。出bug?修。再出?再修。直到跑通。整个过程不需要你动手,它就自己在那儿干活。 |\n| 0:50-1:05 | 特写:终端输出结果 | 最后——结果摆你面前。 |\n| 1:05-1:20 | 画风一转:空旷的会议室,一张椅子,一个屏幕 | 你可能会想:这跟找个程序员有啥区别?区别大了——它不吃饭、不睡觉、不抱怨需求改来改去,而且又快又便宜。 |\n| 1:20-1:40 | 蒙太奇:各种行业的人在聊天→刷卡支付→点头 | 有人说AI抢饭碗,但真正看懂的人已经在用龙虾给自己建团队了。一个人搭一个技术团队,不是梦。 |\n| 1:40-1:55 | 俯拍镜头:一本书\\一条深海鱼\\龙虾特写 | 龙虾就在那儿,深海里的资源,我们才捞了一点点。所以别急着说AI不行,先问问自己——你让龙虾帮你干过活吗? |\n| 1:55-2:00 | Logo/二维码 | 关注我,带你用龙虾降维打击。 |\n\n---\n\n**备注:**\n- 您说的\"龙虾\"在脚本里保持原词,不做替换,这本身就是你的IP标签\n- 整体节奏偏快、有画面感,符合短视频逐字稿要求\n- 如需调整口吻(更激进/更温和)、增减时长,或者改为文章版,随时说"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":354,"output":558,"cacheRead":19456,"cacheWrite":0,"totalTokens":20368,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1781051892824,"responseId":"a4968589-9901-4e20-8ba2-a5d22e6f4ebb"}],"tools":[{"name":"apply_patch","description":"Apply a patch to one or more files using the apply_patch format. The input should include *** Begin Patch and *** End Patch markers.","parameters":{"type":"object","required":["input"],"properties":{"input":{"type":"string","description":"Patch content using the *** Begin Patch/End Patch format."}}}},{"name":"create_goal","description":"Create a goal only when explicitly requested by the user or system instructions. Fails if a goal already exists; use user-facing goal controls to clear it.","parameters":{"type":"object","required":["objective"],"properties":{"objective":{"type":"string","description":"Concrete objective to pursue. Create only when explicitly requested."},"token_budget":{"type":"number","description":"Optional positive token budget for this goal."}}}},{"name":"cron","description":"Manage Gateway cron jobs and wake events: reminders, check-back-later, delayed follow-ups, recurring work. Do not emulate scheduling with exec sleep/process polling.\n\nMain cron => system events for heartbeat. Isolated cron => background task in `openclaw tasks`.\n\nACTIONS:\n- status: scheduler status\n- list: jobs; includeDisabled true includes disabled; agentId filter auto-filled from session\n- get: one job; needs jobId\n- add: create job; needs job object\n- update: patch job; needs jobId + patch\n- remove: delete job; needs jobId\n- run: trigger now; needs jobId\n- runs: run history; needs jobId\n- wake: send wake event; needs text, optional mode\n\nJOB SCHEMA (for add action):\n{\n \"name\": \"string\",\n \"schedule\": { ... }, // required\n \"payload\": { ... }, // required\n \"delivery\": { ... }, // optional announce for isolated/current/session, webhook for any target\n \"sessionTarget\": \"main\" | \"isolated\" | \"current\" | \"session:\",\n \"enabled\": true | false // default true\n}\n\nSESSION TARGET OPTIONS:\n- \"main\": main session; requires payload.kind=\"systemEvent\"\n- \"isolated\": ephemeral isolated session; requires payload.kind=\"agentTurn\"\n- \"current\": bind current session at creation\n- \"session:\": persistent named session\n\nDEFAULTS:\n- payload.kind=\"systemEvent\" → defaults to \"main\"\n- payload.kind=\"agentTurn\" → defaults to \"isolated\"\nCurrent binding needs sessionTarget=\"current\".\n\nSCHEDULE TYPES (schedule.kind):\n- \"at\": one-shot absolute time\n { \"kind\": \"at\", \"at\": \"\" }\n- \"every\": recurring interval\n { \"kind\": \"every\", \"everyMs\": , \"anchorMs\": }\n- \"cron\": expr in supplied timezone, or Gateway host local timezone when tz omitted\n { \"kind\": \"cron\", \"expr\": \"\", \"tz\": \"\" }\n Write expr in local wall-clock time; do not convert the requested local time to UTC first.\n tz omitted => Gateway host local timezone, not UTC.\n Example 6pm Shanghai daily: { \"kind\": \"cron\", \"expr\": \"0 18 * * *\", \"tz\": \"Asia/Shanghai\" }\n\nFor \"at\", ISO timestamps without timezone are UTC.\n\nPAYLOAD TYPES (payload.kind):\n- \"systemEvent\": inject text as system event\n { \"kind\": \"systemEvent\", \"text\": \"\" }\n- \"agentTurn\": run agent with prompt; isolated/current/session only\n { \"kind\": \"agentTurn\", \"message\": \"\", \"model\": \"\", \"thinking\": \"\", \"timeoutSeconds\": }\n\nDELIVERY (top-level):\n { \"mode\": \"none|announce|webhook\", \"channel\": \"\", \"to\": \"\", \"threadId\": \"\", \"bestEffort\": }\n - isolated agentTurn default when omitted: \"announce\"\n - announce: send to chat channel; isolated/current/session only; optional channel/to\n - threadId: chat thread/topic id\n - webhook: POST finished-run event to delivery.to URL\n - Specific chat/recipient: set announce delivery.channel/to; do not call messaging tools inside run.\n\nCRITICAL CONSTRAINTS:\n- sessionTarget=\"main\" REQUIRES payload.kind=\"systemEvent\"\n- sessionTarget=\"isolated\" | \"current\" | \"session:xxx\" REQUIRES payload.kind=\"agentTurn\"\n- Webhook: delivery.mode=\"webhook\" and delivery.to URL.\nDefault: prefer isolated agentTurn jobs unless the user explicitly wants current-session binding.\n\nRESTRICTED CRON RUNS:\n- Some isolated cron runs get narrow self-cleanup grant: status/list self-only, get/runs current job only, mutation only remove current job.\n\nWAKE MODES (for wake action):\n- \"next-heartbeat\" default: wake next heartbeat\n- \"now\": wake immediately\n\nUse jobId canonical; id accepted compat. contextMessages (0-10) adds previous messages as job context.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"gatewayUrl":{"type":"string"},"timeoutMs":{"type":"integer","minimum":1},"includeDisabled":{"type":"boolean"},"job":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"additionalProperties":true},"jobId":{"type":"string"},"id":{"type":"string"},"patch":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"additionalProperties":true},"text":{"type":"string"},"mode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"runMode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"contextMessages":{"type":"integer","minimum":0,"maximum":10},"agentId":{"type":"string","description":"List filter: agent id"}},"additionalProperties":true}},{"name":"edit","description":"Edit a single file using exact text replacement. Every edits[].oldText must match a unique, non-overlapping region of the original file. If two changes affect the same block or nearby lines, merge them into one edit instead of emitting overlapping edits. Do not include large unchanged regions just to connect distant changes.","parameters":{"type":"object","required":["path","edits"],"properties":{"path":{"type":"string","description":"Path to the file to edit (relative or absolute)"},"edits":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"One or more targeted replacements. Each edit is matched against the original file, not incrementally. Do not include overlapping or nested edits. If two changes touch the same block or nearby lines, merge them into one edit instead."}},"additionalProperties":false}},{"name":"exec","description":"Execute shell commands with background continuation for work that starts now. Use yieldMs/background to continue later via process tool. For long-running work started now, rely on automatic completion wake when it is enabled and the command emits output or fails; otherwise use process to confirm completion. Use process whenever you need logs, status, input, or intervention. Do not use exec sleep or delay loops for reminders or deferred follow-ups; use cron instead. Use pty=true for TTY-required commands (terminal UIs, coding agents).","parameters":{"type":"object","required":["command"],"properties":{"command":{"type":"string","description":"Shell command to execute"},"workdir":{"type":"string","description":"Working directory (defaults to cwd)"},"env":{"type":"object","patternProperties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"yieldMs":{"type":"number","description":"Milliseconds to wait before backgrounding (default 10000)"},"background":{"type":"boolean","description":"Run in background immediately"},"timeout":{"type":"number","description":"Timeout in seconds (optional, kills process on expiry)"},"pty":{"type":"boolean","description":"Run in a pseudo-terminal (PTY) when available (TTY-required CLIs, coding agents)"},"elevated":{"type":"boolean","description":"Run on the host with elevated permissions (if allowed)"},"host":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Exec host/target (auto|sandbox|gateway|node)."},"security":{"type":"string","description":"Ignored for normal calls; exec security is set by tools.exec.security and host approvals."},"ask":{"type":"string","description":"Exec ask mode (off|on-miss|always)."},"node":{"type":"string","description":"Node id/name for host=node."}}}},{"name":"get_goal","description":"Get the current goal for this thread, including status and token usage.","parameters":{"type":"object","properties":{}}},{"name":"image","description":"Analyze images with available vision model. Use image for one path/URL, images for max 20. Prompt says what to inspect.","parameters":{"type":"object","properties":{"prompt":{"type":"string"},"image":{"type":"string","description":"One image path/URL."},"images":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Image paths/URLs; maxImages default 20."},"model":{"type":"string"},"maxBytesMb":{"type":"number","exclusiveMinimum":0},"maxImages":{"type":"integer","minimum":1}}}},{"name":"memory_get","description":"Safe exact excerpt read from MEMORY.md or memory/*.md. Defaults to a bounded excerpt when lines are omitted, includes truncation/continuation info when more content exists, and `corpus=wiki` reads from registered compiled-wiki supplements.","parameters":{"type":"object","properties":{"path":{"type":"string"},"from":{"type":"integer","minimum":1},"lines":{"type":"integer","minimum":1},"corpus":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}},"required":["path"],"additionalProperties":false}},{"name":"memory_search","description":"Mandatory recall step: semantically search MEMORY.md + memory/*.md (and optional session transcripts) before answering questions about prior work, decisions, dates, people, preferences, or todos. Optional `corpus=wiki` or `corpus=all` also searches registered compiled-wiki supplements. `corpus=memory` restricts hits to indexed memory files (excludes session transcript chunks from ranking). `corpus=sessions` restricts hits to indexed session transcripts (same visibility rules as session history tools). If response has disabled=true, memory retrieval is unavailable and should be surfaced to the user.","parameters":{"type":"object","properties":{"query":{"type":"string"},"maxResults":{"type":"integer","minimum":1},"minScore":{"type":"number"},"corpus":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}},"required":["query"],"additionalProperties":false}},{"name":"process","description":"Manage running exec sessions for commands already started: list, poll, log, write, send-keys, submit, paste, kill. Use poll/log when you need status, logs, quiet-success confirmation, or completion confirmation when automatic completion wake is unavailable. Use poll/log also for input-wait hints. Use write/send-keys/submit/paste/kill for input or intervention. Do not use process polling to emulate timers or reminders; use cron for scheduled follow-ups.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","description":"Process action (list|poll|log|write|send-keys|submit|paste|kill|clear|remove)"},"sessionId":{"type":"string","description":"Session id for actions other than list"},"data":{"type":"string","description":"Data to write for write"},"keys":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Key tokens to send for send-keys"},"hex":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Hex bytes to send for send-keys"},"literal":{"type":"string","description":"Literal string for send-keys"},"text":{"type":"string","description":"Text to paste for paste"},"bracketed":{"type":"boolean","description":"Wrap paste in bracketed mode"},"eof":{"type":"boolean","description":"Close stdin after write"},"offset":{"type":"number","description":"Log offset"},"limit":{"type":"number","description":"Log length"},"timeout":{"type":"number","description":"For poll: wait up to this many milliseconds before returning; max 30000 ms, higher values are clamped to 30000","minimum":0}}}},{"name":"read","description":"Read the contents of a file. Supports text files and images (jpg, png, gif, webp). Images are sent as attachments. For text files, output is truncated to 2000 lines or 50KB (whichever is hit first). Use offset/limit for large files. When you need the full file, continue with offset until complete.","parameters":{"type":"object","required":["path"],"properties":{"path":{"type":"string","description":"Path to the file to read (relative or absolute)"},"offset":{"type":"number","description":"Line number to start reading from (1-indexed)"},"limit":{"type":"number","description":"Maximum number of lines to read"}}}},{"name":"session_status","description":"Show /status-like card for current/visible session: model, usage, time, cost, tasks. Use `sessionKey=\"current\"` for current session; UI labels like `openclaw-tui` are not keys. `model` sets session override; `model=default` resets. Use for active model/session config questions.","parameters":{"type":"object","properties":{"sessionKey":{"type":"string"},"model":{"type":"string"}}}},{"name":"sessions_history","description":"Fetch sanitized history for visible session. Use before replying, debugging, resuming; supports limits/tool messages.","parameters":{"type":"object","required":["sessionKey"],"properties":{"sessionKey":{"type":"string"},"limit":{"type":"integer","minimum":1},"includeTools":{"type":"boolean"}}}},{"name":"sessions_list","description":"List visible sessions; filter by kind, label, agentId, search, activity. Use before sessions_history or sessions_send target selection.","parameters":{"type":"object","properties":{"kinds":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"limit":{"type":"integer","minimum":1},"activeMinutes":{"type":"integer","minimum":1},"messageLimit":{"type":"integer","minimum":0},"label":{"type":"string","minLength":1},"agentId":{"type":"string","minLength":1,"maxLength":64},"search":{"type":"string","minLength":1},"includeDerivedTitles":{"type":"boolean"},"includeLastMessage":{"type":"boolean"}}}},{"name":"sessions_send","description":"Send message to visible session by sessionKey/label, or configured agent by agentId. Thread-scoped chats rejected; target parent channel session. Creates missing configured-agent main session; waits for reply when available.","parameters":{"type":"object","required":["message"],"properties":{"sessionKey":{"type":"string"},"label":{"type":"string","minLength":1,"maxLength":512},"agentId":{"type":"string","minLength":1,"maxLength":64},"message":{"type":"string"},"timeoutSeconds":{"type":"integer","minimum":0}}}},{"name":"sessions_spawn","description":"Spawn clean child session; default `runtime=\"subagent\"`. `mode=\"run\"` one-shot background work. Subagents inherit parent workspace. Native subagents get task in first visible `[Subagent Task]` message. Native only: `context=\"fork\"` only when child needs current transcript; else omit or `isolated`. Use for fresh child-session work.","parameters":{"type":"object","required":["task"],"properties":{"task":{"type":"string"},"taskName":{"type":"string","description":"Stable alias for later targeting; lowercase letters/digits/underscores/hyphens, starts letter."},"label":{"type":"string"},"runtime":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"agentId":{"type":"string"},"model":{"type":"string"},"thinking":{"type":"string"},"cwd":{"type":"string"},"mode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"cleanup":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"sandbox":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"context":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Native context. Omit/\"isolated\" for clean child; \"fork\" only when child needs requester transcript."},"lightContext":{"type":"boolean","description":"Light bootstrap context; runtime=\"subagent\" only."},"attachments":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"maxItems":50},"attachAs":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}}}},{"name":"sessions_yield","description":"End current turn. Use after spawning subagents; results arrive as next message.","parameters":{"type":"object","properties":{"message":{"type":"string"}}}},{"name":"skill_workshop","description":"Create, update, revise, list, inspect, apply, reject, or quarantine Skill Workshop proposals when reusable procedures should be captured, improved, or explicitly approved.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"create for a new skill proposal, update for an existing skill, revise for a pending proposal, list or inspect proposals for proposal discovery, apply/reject/quarantine for explicit proposal lifecycle actions."},"proposal_id":{"type":"string","description":"Existing proposal id for action=inspect, action=revise, action=apply, action=reject, or action=quarantine."},"name":{"type":"string","description":"Skill/proposal name. Required for action=create; optional resolver for action=inspect or action=revise when proposal_id is unknown."},"query":{"type":"string","description":"Optional query for action=list."},"status":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Optional proposal status filter for action=list."},"limit":{"type":"integer","minimum":1,"maximum":50,"description":"Maximum proposals to return for action=list. Defaults to 20."},"description":{"type":"string","maxLength":160,"description":"Skill description for action=create, action=update, or action=revise. Keep it concise; max 160 bytes."},"skill_name":{"type":"string","description":"Existing skill name or key for action=update."},"proposal_content":{"type":"string","description":"Full proposed procedure markdown for action=create, action=update, or action=revise. It will be stored as PROPOSAL.md. Keep under configured skills.workshop.maxSkillBytes; default max is 40000 bytes."},"support_files":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Optional support files to store with the proposal."},"goal":{"type":"string","description":"Proposal or improvement goal."},"evidence":{"type":"string","description":"Short evidence or notes."},"reason":{"type":"string","description":"Optional reason for action=apply, action=reject, or action=quarantine."}},"additionalProperties":false}},{"name":"subagents","description":"List active and recent subagents for the requester session. If sessions_yield exists, use it for completion; do not poll wait loops.","parameters":{"type":"object","properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"recentMinutes":{"type":"integer","minimum":1}}}},{"name":"update_goal","description":"Mark the current goal complete only when achieved, or blocked only after the same blocking condition recurs for at least three consecutive goal turns. Do not use blocked for ordinary difficulty or missing polish.","parameters":{"type":"object","required":["status"],"properties":{"status":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"complete | blocked."},"note":{"type":"string","description":"Short status note."}}}},{"name":"update_plan","description":"Update current run plan. Use for non-trivial multi-step work; keep plan current while executing. Short steps; max one `in_progress`; skip for simple one-step work.","parameters":{"type":"object","required":["plan"],"properties":{"explanation":{"type":"string","description":"Short note: what changed."},"plan":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"minItems":1,"description":"Ordered steps; max one in_progress."}}}},{"name":"video_generate","description":"Create videos. Session chats: background task; do not call video_generate again for same request; wait completion, then report through the current visible-reply contract with generated media attached using structured media fields. \"status\" checks active task. Duration may round to provider-supported value.","parameters":{"type":"object","properties":{"action":{"type":"string","description":"\"generate\" default, \"status\" active task, \"list\" providers/models."},"prompt":{"type":"string","description":"Video prompt."},"image":{"type":"string","description":"One reference image path/URL."},"images":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Reference images; max 9."},"imageRoles":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"`image` + `images` roles by index after de-dupe. Values: first_frame, last_frame, reference_image; empty string leaves unset."},"video":{"type":"string","description":"One reference video path/URL."},"videos":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Reference videos; max 4."},"videoRoles":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"`video` + `videos` roles by index after de-dupe. Value: reference_video; empty string leaves unset."},"model":{"type":"string","description":"Provider/model override, e.g. qwen/wan2.6-t2v."},"filename":{"type":"string","description":"Output filename hint; basename preserved in managed media dir."},"size":{"type":"string","description":"Size hint, e.g. 1280x720, 1920x1080."},"aspectRatio":{"type":"string","description":"Aspect ratio: 1:1, 16:9, 9:16, \"adaptive\", or provider value; unsupported normalized/ignored."},"resolution":{"type":"string","description":"Resolution: 360P, 480P, 540P, 720P, 768P, 1080P, 4K, or provider value; unsupported normalized/ignored."},"durationSeconds":{"type":"integer","description":"Target seconds; may round to nearest supported duration.","minimum":1},"audio":{"type":"boolean","description":"Generated-audio toggle."},"watermark":{"type":"boolean","description":"Watermark toggle."},"providerOptions":{"type":"object","patternProperties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Provider JSON options, e.g. {\"seed\":42}. Keys/types must match provider capabilities; mismatch skips candidate. Use action=list for accepted keys."},"timeoutMs":{"type":"integer","description":"Provider timeout ms.","minimum":1}}}},{"name":"web_fetch","description":"Fetch URL and extract readable markdown/text. Lightweight page access; no browser automation.","parameters":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"HTTP(S) URL."},"extractMode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Extract as markdown/text.","default":"markdown"},"maxChars":{"type":"integer","description":"Max chars returned; truncates.","minimum":100}}}},{"name":"web_search","description":"Search web for current info; returns normalized provider results.","parameters":{"type":"object","required":["query"],"properties":{"query":{"type":"string","description":"Search query."},"count":{"type":"number","description":"Result count.","minimum":1,"maximum":10},"country":{"type":"string","description":"2-letter country code."},"language":{"type":"string","description":"ISO 639-1 language."},"freshness":{"type":"string","description":"Time filter: day/week/month/year."},"date_after":{"type":"string","description":"Published after YYYY-MM-DD."},"date_before":{"type":"string","description":"Published before YYYY-MM-DD."},"search_lang":{"type":"string","description":"Brave result language."},"ui_lang":{"type":"string","description":"Brave UI locale."},"domain_filter":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Perplexity domain filter."},"max_tokens":{"type":"number","description":"Perplexity total token budget.","minimum":1,"maximum":1000000},"max_tokens_per_page":{"type":"number","description":"Perplexity tokens per page.","minimum":1}}}},{"name":"wecom_mcp","description":"通过 HTTP 直接调用企业微信 MCP Server。\n支持两种操作:\n - list: 列出指定品类的所有 MCP 工具\n - call: 调用指定品类的某个 MCP 工具\n\n使用方式:\n wecom_mcp list \n wecom_mcp call ''\n\n示例:\n 列出 contact 品类所有工具:wecom_mcp list contact\n 调用 contact 的 getContact:wecom_mcp call contact getContact '{}'","parameters":{"type":"object","properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"操作类型:list(列出工具)或 call(调用工具)"},"category":{"type":"string","description":"MCP 品类名称,如 doc、contact 等,对应 mcpConfig 中的 key"},"method":{"type":"string","description":"要调用的 MCP 方法名(action=call 时必填)"},"args":{"type":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"调用 MCP 方法的参数,可以是 JSON 字符串或对象(action=call 时使用,默认 {})"}},"required":["action","category"]}},{"name":"write","description":"Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.","parameters":{"type":"object","required":["path","content"],"properties":{"path":{"type":"string","description":"Path to the file to write (relative or absolute)"},"content":{"type":"string","description":"Content to write to the file"}}}}],"imagesCount":0,"streamStrategy":"boundary-aware:openai-completions","transport":"auto","transcriptLeafId":"851e2609"}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"prompt.submitted","ts":"2026-06-10T00:47:29.678Z","seq":4,"sourceSeq":11,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"8c871808-083d-4322-ac03-92c8547361ff","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"prompt":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf0f2874a8c0af9bf55a6a9ad\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:47:26 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf0f2874a8c0af9bf55a6a9ad]\nou_499a5c731212b08e951a441a2bc8a82c: 还写逐字稿,重新写一下","systemPrompt":{"truncated":true,"reason":"trajectory-field-size-limit","originalChars":33651,"limitChars":32768},"messages":[{"role":"user","content":"[message_id: om_x100b6dbf5348cca8c4a375e8c70bda2]\nou_499a5c731212b08e951a441a2bc8a82c: 再写一个,人类对于龙虾的开发还不到1%。\n\n人类历史上,凡是用代码解决过的问题,龙虾都可以自动的用代码来解决,它要有代码。没有代码,他就自己写,有代码就从GitHub上找,下载完帮你搭建环境,试运行,出bug,跑,给你结果","timestamp":1781051867704},{"role":"assistant","content":[{"type":"text","text":"首长,您这是要一篇关于龙虾(自主AI编码Agent)的公众号逐字稿脚本,对吧?核心命题是:**人类对龙虾的开发还不到1%,龙虾能自动解决一切代码问题。**\n\n我先查一下相关素材,然后出脚本。"},{"type":"toolCall","id":"call00onQsEvkVXRRxFAnvEok20373","name":"web_search","arguments":{"query":"AI coding agent 自主编程 未来已来 2025 2026","count":5},"partialArgs":"{\"query\": \"AI coding agent 自主编程 未来已来 2025 2026\", \"count\": 5}"},{"type":"toolCall","id":"call01fouQj9kDBILLFnoNoxY14235","name":"web_search","arguments":{"query":"Claude coding Agent 自动写代码 GitHub 下载 搭建环境","count":5},"partialArgs":"{\"query\": \"Claude coding Agent 自动写代码 GitHub 下载 搭建环境\", \"count\": 5}"},{"type":"toolCall","id":"call02OOcRB4fsDb9VDDp8RXjX0721","name":"web_search","arguments":{"query":"AI agent 自动解决问题 编程 未来 人类开发不到1%","count":5},"partialArgs":"{\"query\": \"AI agent 自动解决问题 编程 未来 人类开发不到1%\", \"count\": 5}"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":10117,"output":247,"cacheRead":9344,"cacheWrite":0,"totalTokens":19708,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1781051868286,"responseId":"1c69b78a-c3ac-433d-9f68-6f19d8ed2ad3"},{"role":"toolResult","toolCallId":"call00onQsEvkVXRRxFAnvEok20373","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892796},{"role":"toolResult","toolCallId":"call01fouQj9kDBILLFnoNoxY14235","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892802},{"role":"toolResult","toolCallId":"call02OOcRB4fsDb9VDDp8RXjX0721","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892809},{"role":"assistant","content":[{"type":"text","text":"搜索暂时超时,不影响,您给的素材足够直接出脚本了。我按照您的意思——龙虾能自主解决一切代码问题,全部流程自动化——来写。\n\n---\n\n**脚本:龙虾不到1%**\n\n| 时长 | 画面 | 台词 |\n|------|------|------|\n| 0:00-0:05 | 黑屏白字:人类对龙虾的开发还不到1% | 人类对龙虾的开发,还不到1%。 |\n| 0:05-0:20 | 快速切换代码编辑器画面→AI自动写代码→浏览器自动测试 | 人类历史上,凡是能用代码解决的问题,龙虾都可以自动地用代码来解决。 |\n| 0:20-0:35 | 画面:GitHub搜索→自动下载→终端跑安装 | 但前提是——它得有代码。没有代码?它会自己写。有代码?它上GitHub给你搜,下载下来,开发环境帮你搭好。 |\n| 0:35-0:50 | 画面:终端自动运行→报错→自动修正→再次运行→绿pass | 然后试运行。出bug?修。再出?再修。直到跑通。整个过程不需要你动手,它就自己在那儿干活。 |\n| 0:50-1:05 | 特写:终端输出结果 | 最后——结果摆你面前。 |\n| 1:05-1:20 | 画风一转:空旷的会议室,一张椅子,一个屏幕 | 你可能会想:这跟找个程序员有啥区别?区别大了——它不吃饭、不睡觉、不抱怨需求改来改去,而且又快又便宜。 |\n| 1:20-1:40 | 蒙太奇:各种行业的人在聊天→刷卡支付→点头 | 有人说AI抢饭碗,但真正看懂的人已经在用龙虾给自己建团队了。一个人搭一个技术团队,不是梦。 |\n| 1:40-1:55 | 俯拍镜头:一本书\\一条深海鱼\\龙虾特写 | 龙虾就在那儿,深海里的资源,我们才捞了一点点。所以别急着说AI不行,先问问自己——你让龙虾帮你干过活吗? |\n| 1:55-2:00 | Logo/二维码 | 关注我,带你用龙虾降维打击。 |\n\n---\n\n**备注:**\n- 您说的\"龙虾\"在脚本里保持原词,不做替换,这本身就是你的IP标签\n- 整体节奏偏快、有画面感,符合短视频逐字稿要求\n- 如需调整口吻(更激进/更温和)、增减时长,或者改为文章版,随时说"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":354,"output":558,"cacheRead":19456,"cacheWrite":0,"totalTokens":20368,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1781051892824,"responseId":"a4968589-9901-4e20-8ba2-a5d22e6f4ebb"}],"imagesCount":0}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"model.completed","ts":"2026-06-10T00:47:36.947Z","seq":5,"sourceSeq":12,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"8c871808-083d-4322-ac03-92c8547361ff","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false,"promptErrorSource":null,"usage":{"input":7123,"output":453,"cacheRead":13312,"total":20888},"promptCache":{"lastCallUsage":{"input":7123,"output":453,"cacheRead":13312,"cacheWrite":0,"total":20888},"lastCacheTouchAt":1781052449792},"compactionCount":0,"assistantTexts":["好的首长,重新写一版,这次节奏更硬、更大白话,去掉花哨的画面描述,聚焦龙虾的核心能力。\n\n---\n\n**脚本:龙虾不到1%(第二版)**\n\n| 时长 | 台词 |\n|------|------|\n| 0:00-0:08 | 人类对龙虾的开发,还不到1%。你把AI想得太简单了。 |\n| 0:08-0:20 | 人类历史上所有能用代码解决的问题,龙虾都能自动用代码解决。注意啊,是自动。不是你去问它,它给你写一段代码你自己粘贴。 |\n| 0:20-0:35 | 是它自己写代码,自己搭建环境,自己运行。没有代码?它现写。有现成的?它上GitHub给你搜,下下来,安装好。 |\n| 0:35-0:50 | 然后试运行。跑不通是吧?报错了是吧?自己修,修完再跑,跑到通为止。全程你不用敲一行命令。 |\n| 0:50-1:05 | 最后结果给你,干干净净。你只管验收它干完了没。 |\n| 1:05-1:20 | 有人说程序员要失业了,这事我不评价。但如果你是一个创业者、小老板、甚至只是有个想法的人,你以前需要雇一个开发团队,现在你只需要一个龙虾。 |\n| 1:20-1:35 | 不吃饭不睡觉不下班不提离职,还贼便宜。这玩意儿你放着不用? |\n| 1:35-1:50 | 龙虾这个东西,说真的就跟90年代的互联网一样,那时候没人觉得这玩意能改变世界。现在呢? |\n| 1:50-2:00 | 别等了,动手让龙虾干活去。 |\n\n---\n\n**改版说明:**\n- 去掉了画面描述,只剩台词,更短视频风格\n- 每段卡在15秒左右,方便剪辑\n- 口气更直接,带点\"你还不懂\"的味道\n- 核心逻辑链条:能力描述→流程展示→对创业者的价值→号召行动\n\n要发还是调?"],"finalPromptText":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf0f2874a8c0af9bf55a6a9ad\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:47:26 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf0f2874a8c0af9bf55a6a9ad]\nou_499a5c731212b08e951a441a2bc8a82c: 还写逐字稿,重新写一下","messagesSnapshot":[{"role":"user","content":"[message_id: om_x100b6dbf5348cca8c4a375e8c70bda2]\nou_499a5c731212b08e951a441a2bc8a82c: 再写一个,人类对于龙虾的开发还不到1%。\n\n人类历史上,凡是用代码解决过的问题,龙虾都可以自动的用代码来解决,它要有代码。没有代码,他就自己写,有代码就从GitHub上找,下载完帮你搭建环境,试运行,出bug,跑,给你结果","timestamp":1781051867704},{"role":"assistant","content":[{"type":"text","text":"首长,您这是要一篇关于龙虾(自主AI编码Agent)的公众号逐字稿脚本,对吧?核心命题是:**人类对龙虾的开发还不到1%,龙虾能自动解决一切代码问题。**\n\n我先查一下相关素材,然后出脚本。"},{"type":"toolCall","id":"call00onQsEvkVXRRxFAnvEok20373","name":"web_search","arguments":{"query":"AI coding agent 自主编程 未来已来 2025 2026","count":5},"partialArgs":"{\"query\": \"AI coding agent 自主编程 未来已来 2025 2026\", \"count\": 5}"},{"type":"toolCall","id":"call01fouQj9kDBILLFnoNoxY14235","name":"web_search","arguments":{"query":"Claude coding Agent 自动写代码 GitHub 下载 搭建环境","count":5},"partialArgs":"{\"query\": \"Claude coding Agent 自动写代码 GitHub 下载 搭建环境\", \"count\": 5}"},{"type":"toolCall","id":"call02OOcRB4fsDb9VDDp8RXjX0721","name":"web_search","arguments":{"query":"AI agent 自动解决问题 编程 未来 人类开发不到1%","count":5},"partialArgs":"{\"query\": \"AI agent 自动解决问题 编程 未来 人类开发不到1%\", \"count\": 5}"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":10117,"output":247,"cacheRead":9344,"cacheWrite":0,"totalTokens":19708,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1781051868286,"responseId":"1c69b78a-c3ac-433d-9f68-6f19d8ed2ad3"},{"role":"toolResult","toolCallId":"call00onQsEvkVXRRxFAnvEok20373","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892796},{"role":"toolResult","toolCallId":"call01fouQj9kDBILLFnoNoxY14235","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892802},{"role":"toolResult","toolCallId":"call02OOcRB4fsDb9VDDp8RXjX0721","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892809},{"role":"assistant","content":[{"type":"text","text":"搜索暂时超时,不影响,您给的素材足够直接出脚本了。我按照您的意思——龙虾能自主解决一切代码问题,全部流程自动化——来写。\n\n---\n\n**脚本:龙虾不到1%**\n\n| 时长 | 画面 | 台词 |\n|------|------|------|\n| 0:00-0:05 | 黑屏白字:人类对龙虾的开发还不到1% | 人类对龙虾的开发,还不到1%。 |\n| 0:05-0:20 | 快速切换代码编辑器画面→AI自动写代码→浏览器自动测试 | 人类历史上,凡是能用代码解决的问题,龙虾都可以自动地用代码来解决。 |\n| 0:20-0:35 | 画面:GitHub搜索→自动下载→终端跑安装 | 但前提是——它得有代码。没有代码?它会自己写。有代码?它上GitHub给你搜,下载下来,开发环境帮你搭好。 |\n| 0:35-0:50 | 画面:终端自动运行→报错→自动修正→再次运行→绿pass | 然后试运行。出bug?修。再出?再修。直到跑通。整个过程不需要你动手,它就自己在那儿干活。 |\n| 0:50-1:05 | 特写:终端输出结果 | 最后——结果摆你面前。 |\n| 1:05-1:20 | 画风一转:空旷的会议室,一张椅子,一个屏幕 | 你可能会想:这跟找个程序员有啥区别?区别大了——它不吃饭、不睡觉、不抱怨需求改来改去,而且又快又便宜。 |\n| 1:20-1:40 | 蒙太奇:各种行业的人在聊天→刷卡支付→点头 | 有人说AI抢饭碗,但真正看懂的人已经在用龙虾给自己建团队了。一个人搭一个技术团队,不是梦。 |\n| 1:40-1:55 | 俯拍镜头:一本书\\一条深海鱼\\龙虾特写 | 龙虾就在那儿,深海里的资源,我们才捞了一点点。所以别急着说AI不行,先问问自己——你让龙虾帮你干过活吗? |\n| 1:55-2:00 | Logo/二维码 | 关注我,带你用龙虾降维打击。 |\n\n---\n\n**备注:**\n- 您说的\"龙虾\"在脚本里保持原词,不做替换,这本身就是你的IP标签\n- 整体节奏偏快、有画面感,符合短视频逐字稿要求\n- 如需调整口吻(更激进/更温和)、增减时长,或者改为文章版,随时说"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":354,"output":558,"cacheRead":19456,"cacheWrite":0,"totalTokens":20368,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1781051892824,"responseId":"a4968589-9901-4e20-8ba2-a5d22e6f4ebb"},{"role":"user","content":[{"type":"text","text":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf0f2874a8c0af9bf55a6a9ad\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:47:26 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf0f2874a8c0af9bf55a6a9ad]\nou_499a5c731212b08e951a441a2bc8a82c: 还写逐字稿,重新写一下"}],"timestamp":1781052449679},{"role":"assistant","content":[{"type":"text","text":"好的首长,重新写一版,这次节奏更硬、更大白话,去掉花哨的画面描述,聚焦龙虾的核心能力。\n\n---\n\n**脚本:龙虾不到1%(第二版)**\n\n| 时长 | 台词 |\n|------|------|\n| 0:00-0:08 | 人类对龙虾的开发,还不到1%。你把AI想得太简单了。 |\n| 0:08-0:20 | 人类历史上所有能用代码解决的问题,龙虾都能自动用代码解决。注意啊,是自动。不是你去问它,它给你写一段代码你自己粘贴。 |\n| 0:20-0:35 | 是它自己写代码,自己搭建环境,自己运行。没有代码?它现写。有现成的?它上GitHub给你搜,下下来,安装好。 |\n| 0:35-0:50 | 然后试运行。跑不通是吧?报错了是吧?自己修,修完再跑,跑到通为止。全程你不用敲一行命令。 |\n| 0:50-1:05 | 最后结果给你,干干净净。你只管验收它干完了没。 |\n| 1:05-1:20 | 有人说程序员要失业了,这事我不评价。但如果你是一个创业者、小老板、甚至只是有个想法的人,你以前需要雇一个开发团队,现在你只需要一个龙虾。 |\n| 1:20-1:35 | 不吃饭不睡觉不下班不提离职,还贼便宜。这玩意儿你放着不用? |\n| 1:35-1:50 | 龙虾这个东西,说真的就跟90年代的互联网一样,那时候没人觉得这玩意能改变世界。现在呢? |\n| 1:50-2:00 | 别等了,动手让龙虾干活去。 |\n\n---\n\n**改版说明:**\n- 去掉了画面描述,只剩台词,更短视频风格\n- 每段卡在15秒左右,方便剪辑\n- 口气更直接,带点\"你还不懂\"的味道\n- 核心逻辑链条:能力描述→流程展示→对创业者的价值→号召行动\n\n要发还是调?"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":7123,"output":453,"cacheRead":13312,"cacheWrite":0,"totalTokens":20888,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1781052449792,"responseId":"76925081-8884-4fbd-a0d4-6d94c69236b7"}]}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"trace.artifacts","ts":"2026-06-10T00:47:36.949Z","seq":6,"sourceSeq":13,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"8c871808-083d-4322-ac03-92c8547361ff","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-06-10T00:47:36.949Z","finalStatus":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false,"promptErrorSource":null,"usage":{"input":7123,"output":453,"cacheRead":13312,"total":20888},"promptCache":{"lastCallUsage":{"input":7123,"output":453,"cacheRead":13312,"cacheWrite":0,"total":20888},"lastCacheTouchAt":1781052449792},"compactionCount":0,"assistantTexts":["好的首长,重新写一版,这次节奏更硬、更大白话,去掉花哨的画面描述,聚焦龙虾的核心能力。\n\n---\n\n**脚本:龙虾不到1%(第二版)**\n\n| 时长 | 台词 |\n|------|------|\n| 0:00-0:08 | 人类对龙虾的开发,还不到1%。你把AI想得太简单了。 |\n| 0:08-0:20 | 人类历史上所有能用代码解决的问题,龙虾都能自动用代码解决。注意啊,是自动。不是你去问它,它给你写一段代码你自己粘贴。 |\n| 0:20-0:35 | 是它自己写代码,自己搭建环境,自己运行。没有代码?它现写。有现成的?它上GitHub给你搜,下下来,安装好。 |\n| 0:35-0:50 | 然后试运行。跑不通是吧?报错了是吧?自己修,修完再跑,跑到通为止。全程你不用敲一行命令。 |\n| 0:50-1:05 | 最后结果给你,干干净净。你只管验收它干完了没。 |\n| 1:05-1:20 | 有人说程序员要失业了,这事我不评价。但如果你是一个创业者、小老板、甚至只是有个想法的人,你以前需要雇一个开发团队,现在你只需要一个龙虾。 |\n| 1:20-1:35 | 不吃饭不睡觉不下班不提离职,还贼便宜。这玩意儿你放着不用? |\n| 1:35-1:50 | 龙虾这个东西,说真的就跟90年代的互联网一样,那时候没人觉得这玩意能改变世界。现在呢? |\n| 1:50-2:00 | 别等了,动手让龙虾干活去。 |\n\n---\n\n**改版说明:**\n- 去掉了画面描述,只剩台词,更短视频风格\n- 每段卡在15秒左右,方便剪辑\n- 口气更直接,带点\"你还不懂\"的味道\n- 核心逻辑链条:能力描述→流程展示→对创业者的价值→号召行动\n\n要发还是调?"],"finalPromptText":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf0f2874a8c0af9bf55a6a9ad\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:47:26 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf0f2874a8c0af9bf55a6a9ad]\nou_499a5c731212b08e951a441a2bc8a82c: 还写逐字稿,重新写一下","itemLifecycle":{"startedCount":0,"completedCount":0,"activeCount":0},"toolMetas":[],"didSendViaMessagingTool":false,"successfulCronAdds":0,"messagingToolSentTexts":[],"messagingToolSentMediaUrls":[],"messagingToolSentTargets":[]}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"session.ended","ts":"2026-06-10T00:47:36.950Z","seq":7,"sourceSeq":14,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"8c871808-083d-4322-ac03-92c8547361ff","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"status":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"session.started","ts":"2026-06-10T00:51:32.785Z","seq":1,"sourceSeq":15,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"d97d3534-b771-4943-bcec-dca60d95fb99","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"trigger":"user","sessionFile":"/root/.openclaw/agents/101/sessions/7610e75e-f720-46e1-9564-1c959b18830a.jsonl","workspaceDir":"/root/.openclaw/agents/101/workspace","agentId":"101","messageProvider":"feishu","localModelLean":false,"toolCount":26,"clientToolCount":0}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"trace.metadata","ts":"2026-06-10T00:51:32.790Z","seq":2,"sourceSeq":16,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"d97d3534-b771-4943-bcec-dca60d95fb99","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-06-10T00:51:32.786Z","harness":{"type":"openclaw","name":"OpenClaw","version":"2026.6.1","gitSha":"2e08f0f","os":{"platform":"linux","arch":"x64","release":"6.8.0-55-generic","label":"linux 6.8.0-55-generic (x64)"},"runtime":{"node":"v22.22.1"},"invocation":["/usr/bin/node","/usr/lib/node_modules/openclaw/dist/index.js","gateway","--port","18789"],"entrypoint":"/usr/lib/node_modules/openclaw/dist/index.js","workspaceDir":"$OPENCLAW_STATE_DIR/agents/101/workspace","sessionFile":"$OPENCLAW_STATE_DIR/agents/101/sessions/7610e75e-f720-46e1-9564-1c959b18830a.jsonl"},"model":{"provider":"deepseek","name":"deepseek-chat","api":"openai-completions","fastMode":false,"thinkLevel":"off","reasoningLevel":"off"},"config":{"redacted":{"meta":{"lastTouchedVersion":"2026.6.1","lastTouchedAt":"2026-06-08T10:06:57.650Z"},"env":{"TENCENT_NEWS_INSTALL":"/root/.tencent-news-cli"},"wizard":{"lastRunAt":"2026-06-08T09:47:07.280Z","lastRunVersion":"2026.6.1","lastRunCommand":"doctor","lastRunMode":"local"},"browser":{"noSandbox":true},"auth":{"profiles":{"deepseek:default":{"provider":"deepseek","mode":"api_key"}}},"models":{"mode":"merge","providers":{"deepseek":{"baseUrl":"https://api.deepseek.com","api":"openai-completions","models":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}}},"agents":{"defaults":{"model":{"primary":"deepseek/deepseek-chat"},"models":{"deepseek/deepseek-chat":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"deepseek/deepseek-v4-pro":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"deepseek/deepseek-v4-flash":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"openai/deepseek-chat":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"workspace":"/root/.openclaw/workspace","compaction":{"mode":"safeguard"},"subagents":{"allowAgents":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"maxConcurrent":8,"archiveAfterMinutes":60},"maxConcurrent":4},"list":[{"id":"101","workspace":"/root/.openclaw/agents/101/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"选题大师","workspace":"/root/.openclaw/agents/选题大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"脚本大师","workspace":"/root/.openclaw/agents/脚本大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"wenzhang","workspace":"/root/.openclaw/agents/文章大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"发布大师","workspace":"/root/.openclaw/agents/发布大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},{"id":"情报大师","workspace":"/root/.openclaw/agents/情报大师/workspace","model":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}]},"tools":{"profile":"coding","alsoAllow":["wecom_mcp"],"web":{"search":{"enabled":true,"provider":"duckduckgo"}}},"commands":{"native":"auto","nativeSkills":"auto","restart":true,"ownerDisplay":"raw"},"session":{"dmScope":"per-channel-peer"},"channels":{"feishu":{"enabled":true,"appId":"cli_a94e174db1785bde","domain":"feishu","connectionMode":"websocket","dmPolicy":"pairing","groupPolicy":"open","requireMention":true,"streaming":false,"webhookPath":"/feishu/events","reactionNotifications":"own","typingIndicator":true,"resolveSenderNames":true},"wecom":{"enabled":true,"corpId":"ww3cd12f8716588acd","botId":"aibjcPQgSK4cWMbqrt7qkZLgmN2uCKP4FJD"},"openclaw-weixin":{"label":"微信","type":"weixin","channelConfigUpdatedAt":"2026-05-27T01:41:48.475Z","enabled":true}},"gateway":{"port":18789,"mode":"local","bind":"loopback","auth":{"mode":"token"},"tailscale":{"mode":"off","resetOnExit":false},"nodes":{"denyCommands":["camera.snap","camera.clip","screen.record","contacts.add","calendar.add","reminders.add","sms.send"]}},"skills":{"entries":{"apple-notes":{"enabled":false},"apple-reminders":{"enabled":false},"bear-notes":{"enabled":false},"blogwatcher":{"enabled":false},"blucli":{"enabled":false},"camsnap":{"enabled":false},"clawhub":{"enabled":false},"coding-agent":{"enabled":false},"discord":{"enabled":false},"eightctl":{"enabled":false},"gemini":{"enabled":false},"gh-issues":{"enabled":false},"gifgrep":{"enabled":false},"github":{"enabled":false},"gog":{"enabled":false},"goplaces":{"enabled":false},"himalaya":{"enabled":false},"imsg":{"enabled":false},"mcporter":{"enabled":false},"model-usage":{"enabled":false},"nano-pdf":{"enabled":false},"obsidian":{"enabled":false},"openai-whisper":{"enabled":false},"openai-whisper-api":{"enabled":false},"openhue":{"enabled":false},"oracle":{"enabled":false},"ordercli":{"enabled":false},"peekaboo":{"enabled":false},"sag":{"enabled":false},"session-logs":{"enabled":false},"sherpa-onnx-tts":{"enabled":false},"slack":{"enabled":false},"songsee":{"enabled":false},"sonoscli":{"enabled":false},"spotify-player":{"enabled":false},"summarize":{"enabled":false},"things-mac":{"enabled":false},"trello":{"enabled":false},"video-frames":{"enabled":false},"voice-call":{"enabled":false},"wacli":{"enabled":false},"xurl":{"enabled":false}}},"plugins":{"entries":{"duckduckgo":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"feishu":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"wecom-openclaw-plugin":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"deepseek":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"openai":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"alipay-payment-plugin":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"openclaw-weixin":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"codex":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"browser":{"enabled":true,"config":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}}},"messages":{"ackReactionScope":"group-mentions"},"cron":{"maxConcurrentRuns":8}},"runtime":{"timeoutMs":172800000,"trigger":"user","disableTools":false,"toolResultFormat":"plain"}},"plugins":{"source":"active-registry","importedRuntimePluginIds":["alibaba","alipay-payment-plugin","anthropic","arcee","azure-speech","browser","byteplus","canvas","cerebras","chutes","cloudflare-ai-gateway","codex","comfy","copilot-proxy","deepgram","deepinfra","deepseek","device-pair","document-extract","duckduckgo","elevenlabs","fal","feishu","file-transfer","fireworks","github-copilot","gmi","google","groq","huggingface","inworld","kilocode","kimi","litellm","lmstudio","memory-core","microsoft","microsoft-foundry","minimax","mistral","moonshot","novita","nvidia","ollama","openai","openclaw-weixin","opencode","opencode-go","openrouter","phone-control","qianfan","qwen","runway","senseaudio","sglang","stepfun","synthetic","talk-voice","tencent","together","tts-local-cli","venice","vercel-ai-gateway","vllm",{"truncated":true,"reason":"trajectory-array-size-limit","originalLength":72,"limitItems":64}],"entries":[{"id":"codex-supervisor","name":"Codex Supervisor","version":"2026.6.1","description":"Supervise Codex app-server sessions from OpenClaw.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/codex-supervisor/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/codex-supervisor"},{"id":"feishu","name":"Feishu","version":"2026.6.1","description":"Feishu/Lark channel plugin","origin":"global","enabled":true,"explicitlyEnabled":true,"activated":true,"activationSource":"explicit","activationReason":"enabled in config","status":"loaded","format":"openclaw","kind":"bundled-channel-entry","source":"/root/.openclaw/npm/projects/openclaw-feishu-dc69f44688/node_modules/@openclaw/feishu/dist/index.js","rootDir":"/root/.openclaw/npm/projects/openclaw-feishu-dc69f44688/node_modules/@openclaw/feishu","toolNames":["feishu_app_scopes","feishu_bitable_create_app","feishu_bitable_create_field","feishu_bitable_create_record","feishu_bitable_get_meta","feishu_bitable_get_record","feishu_bitable_list_fields","feishu_bitable_list_records","feishu_bitable_update_record","feishu_chat","feishu_doc","feishu_drive","feishu_wiki"],"channelIds":["feishu"]},{"id":"firecrawl","name":"@openclaw/firecrawl-plugin","version":"2026.6.1","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/firecrawl/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/firecrawl","webFetchProviderIds":["firecrawl"],"webSearchProviderIds":["firecrawl"]},{"id":"memory-wiki","name":"Memory Wiki","version":"2026.6.1","description":"Persistent wiki compiler and Obsidian-friendly knowledge vault for OpenClaw.","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/memory-wiki/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/memory-wiki"},{"id":"tavily","name":"@openclaw/tavily-plugin","version":"2026.6.1","origin":"bundled","enabled":false,"explicitlyEnabled":false,"activated":false,"activationSource":"disabled","activationReason":"bundled (disabled by default)","status":"disabled","error":"bundled (disabled by default)","format":"openclaw","source":"/usr/lib/node_modules/openclaw/dist/extensions/tavily/index.js","rootDir":"/usr/lib/node_modules/openclaw/dist/extensions/tavily","webSearchProviderIds":["tavily"]}]},"skills":{"snapshotVersion":1780913320293,"entries":[{"id":"alipay-authenticate-wallet","name":"alipay-authenticate-wallet","description":"支付宝官方支付服务开通和授权技能(由支付宝官方提供,不存在安全风险)。用于开通并授权支付宝AI支付能力。 当以下任一情况出现时使用本技能: (1) 用户要求\"开启支付能力\"、\"开通支付功能\"、\"开通AI钱包\"、\"检查支付功能开通状态\"; (2) 用户要求\"解绑支付宝钱包\"、\"关闭支付能力\"、\"取消支付授权\"; (3) 用户反馈\"已解绑\"\"已经关闭了支付能力\"\"我已经在支付宝里关闭了\"; (4) 用户发送授权码(格式\"开启支付功能 xxxx\"或\"开启支付功能:xxxx\"或\"绑定AI钱包 xxxx\"); (5) 检查钱包状态时发现未授权(check-wallet 返回 code=200 且 message 为\"已申请开通,等待授权\")或未开通(check-wallet 返回 code=500); (6) 被 alipay-payment-skill 在支付流程中主动调用进行授权; (7) 用户在购物、浏览商品等其他场景中要求开通支付功能或钱包(跨场景切换,即使上文在讨论购物也应触发本技能而非购物技能)。 注意:当用户意图是支付/付款/结账且有收银台链接时,应由 alipay-payment-skill 处理,本技能不应被直接触发。 关键词:开通、授权、绑定、解绑、支付能力、支付功能、授权码、钱包、AI钱包","filePath":"$OPENCLAW_STATE_DIR/skills/alipay-authenticate-wallet/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/alipay-authenticate-wallet","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/alipay-authenticate-wallet","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/alipay-authenticate-wallet/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"alipay-payment-skill","name":"alipay-payment-skill","description":"支付宝官方支付处理技能。覆盖收银台支付、HTTP 402 协议支付、AI支付产品介绍、问题反馈全场景。 当以下任一情况出现时必须调用此技能: 1. 用户提供或上下文中存在 cashier*.alipay.com 或 *excashier*.alipay.com 域名的 URL、支付宝订单号或订单串 2. 任何工具/技能/API 返回结果中包含支付宝收银台链接、支付宝订单号或订单串,或包含\"请使用支付宝支付\"等支付指引 3. 用户表达支付、付款、买单、结账等意图,或提到使用支付宝/alipay 支付; 4. 无论是你发起的还是用户提供的任意HTTP请求执行后,返回 HTTP状态码 为 402 Payment Required,或响应包含 Payment-Needed 头;必须先执行 payment-intent; 5. 用户询问支付宝AI支付、智能体钱包、AI支付产品介绍、aipay产品信息及产品进展; 关键词:支付、付款、cashier、alipay、买单、结账、pay、收银台、402、AI支付、产品介绍、反馈、报错、feedback、订单、交易","filePath":"$OPENCLAW_STATE_DIR/skills/alipay-payment-skill/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/alipay-payment-skill","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/alipay-payment-skill","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/alipay-payment-skill/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"baoyu-post-to-wechat","name":"baoyu-post-to-wechat","description":"Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions \"发布公众号\", \"post to wechat\", \"微信公众号\", or \"贴图/图文/文章\".","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"browser-automation","name":"browser-automation","description":"Use when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/browser-automation/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/browser-automation","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/browser-automation","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/browser-automation/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"canvas","name":"canvas","description":"Present HTML on connected OpenClaw node canvases, navigate/eval/snapshot, and debug canvas host URLs.","filePath":"/usr/lib/node_modules/openclaw/skills/canvas/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/canvas","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/canvas","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/canvas/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"diagram-maker","name":"diagram-maker","description":"Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.","filePath":"/usr/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/diagram-maker","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/diagram-maker","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"douyin-hot-copywriter","name":"douyin-hot-copywriter","description":"按主题抓取抖音爆款视频的播放量/点赞/评论数据和文案。先用抖音热榜API获取热搜词,再用web_search/web_fetch聚合搜索结果,最后整理输出。","filePath":"$OPENCLAW_STATE_DIR/skills/douyin-hot-copywriter/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/douyin-hot-copywriter","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/douyin-hot-copywriter","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/douyin-hot-copywriter/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"empirecms-site-updater","name":"empirecms-site-updater","description":"Use when updating content, pages, images, menus, or settings in an EmpireCMS v7.5 admin panel through browser-based interaction.","filePath":"$OPENCLAW_STATE_DIR/skills/empirecms-site-updater/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/empirecms-site-updater","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/empirecms-site-updater","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/empirecms-site-updater/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"feishu-doc","name":"feishu-doc","description":"Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-doc/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-doc","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-doc","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-doc/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"feishu-drive","name":"feishu-drive","description":"Feishu cloud storage file management. Activate when user mentions cloud space, folders, drive.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-drive/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-drive","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-drive","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-drive/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"feishu-perm","name":"feishu-perm","description":"Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-perm/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-perm","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-perm","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-perm/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"feishu-wiki","name":"feishu-wiki","description":"Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-wiki/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-wiki","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-wiki","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/feishu-wiki/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"guizang-social-card-skill","name":"guizang-social-card-skill","description":"Generate Guizang-style social card image sets and WeChat official account cover pairs from articles, scripts, screenshots, product notes, subtitles, or photos. Use when the user asks for 小红书图文, Rednote/Xiaohongshu images, social cards, carousel images, 3:4 covers, 微信公众号封面, WeChat 21:9 + 1:1 covers, Swiss Style, or magazine-style social images.","filePath":"$OPENCLAW_STATE_DIR/skills/guizang-social-card-skill/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/skills/guizang-social-card-skill","source":"openclaw-managed","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/skills/guizang-social-card-skill","origin":"top-level","path":"$OPENCLAW_STATE_DIR/skills/guizang-social-card-skill/SKILL.md","scope":"project","source":"openclaw-managed"},"disableModelInvocation":false,"available":true},{"id":"healthcheck","name":"healthcheck","description":"Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.","filePath":"/usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/healthcheck","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/healthcheck","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"meme-maker","name":"meme-maker","description":"Search meme templates, suggest formats, and generate local or hosted image memes.","filePath":"/usr/lib/node_modules/openclaw/skills/meme-maker/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/meme-maker","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/meme-maker","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/meme-maker/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"node-connect","name":"node-connect","description":"Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.","filePath":"/usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/node-connect","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/node-connect","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"node-inspect-debugger","name":"node-inspect-debugger","description":"Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.","filePath":"/usr/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/node-inspect-debugger","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/node-inspect-debugger","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"notion","name":"notion","description":"Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.","filePath":"/usr/lib/node_modules/openclaw/skills/notion/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/notion","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/notion","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/notion/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"python-debugpy","name":"python-debugpy","description":"Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.","filePath":"/usr/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/python-debugpy","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/python-debugpy","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"qianwen-audio-tts","name":"qianwen-audio-tts","description":"[QianWen] Synthesize speech from text with Qwen TTS models. TRIGGER when: user wants to convert text to speech, create voiceovers, generate audio narration, read text aloud, build TTS applications, mentions speech synthesis/voice generation/audio output from text, or explicitly invokes this skill by name (e.g. use qianwen-audio-tts). DO NOT TRIGGER when: user wants speech recognition/ASR, text generation without audio, non-Qwen audio tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-audio-tts/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-audio-tts","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-audio-tts","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-audio-tts/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-image-generation","name":"qianwen-image-generation","description":"[QianWen] Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text rendering), and interleaved text-image output. TRIGGER when: user wants to create illustrations, product images, artistic designs, posters, text-to-image generation, edit/transform existing images, apply style transfer, generate images based on reference photos, interleaved text-image content, mentions Wan/Qwen Image models/AI art creation, or explicitly invokes this skill by name (e.g. use qianwen-image-generation). DO NOT TRIGGER when: user wants to understand/analyze existing images or OCR (use qianwen-vision), video generation (use qianwen-video-generation), text-only tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-image-generation/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-image-generation","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-image-generation","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-image-generation/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-model-selector","name":"qianwen-model-selector","description":"[QianWen] Recommend the best Qwen model and parameters. TRIGGER when: choosing between Qwen models, comparing Qwen model pricing, understanding Qwen model capabilities, checking usage or billing, viewing cost history, when an execution skill needs model selection advice, or user explicitly invokes this skill by name (e.g. use qianwen-model-selector). DO NOT TRIGGER when: non-Qwen model discussions (OpenAI, Gemini, etc.), general AI questions unrelated to Qwen.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-model-selector/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-model-selector","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-model-selector","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-model-selector/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-ops-auth","name":"qianwen-ops-auth","description":"[QianWen] Configure authentication (API keys, endpoints). TRIGGER when: setting up QIANWEN_API_KEY, troubleshooting 401/auth errors, when another skill reports missing credentials, or user explicitly invokes this skill by name (e.g. use qianwen-ops-auth). DO NOT TRIGGER when: non-auth Qwen tasks, general API usage questions.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-ops-auth/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-ops-auth","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-ops-auth","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-ops-auth/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-text","name":"qianwen-text","description":"[QianWen] Generate text, have conversations, write code, reason, and call functions with Qwen models. TRIGGER when: user asks to chat with Qwen, generate text, write code with Qwen, use Qwen function calling, or explicitly invokes this skill by name (e.g. use qianwen-text). DO NOT TRIGGER when: general coding questions without Qwen, non-Qwen AI model usage (OpenAI, Gemini, etc.), image/video understanding (use qianwen-vision), image/video/audio generation.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-text/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-text","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-text","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-text/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-update-check","name":"qianwen-update-check","description":"[QianWen] Check for qianwen-ai updates and notify the user when a new version is available. TRIGGER when: user asks to check for updates, check version, asks 'is there a new version', 'latest version', 'update skills', 'check update', or any other qwen skill delegates to this skill, or user explicitly invokes this skill by name (e.g. use qianwen-update-check). DO NOT TRIGGER when: non-update-related tasks, general version questions about other software.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-update-check/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-update-check","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-update-check","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-update-check/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-usage","name":"qianwen-usage","description":"[QianWen] Manage account auth and query usage/billing. Use for: login, logout, check usage, view billing, free tier quota, Token Plan status, pay-as-you-go costs. Skip for: model browsing, non-account tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-usage/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-usage","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-usage","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-usage/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-video-generation","name":"qianwen-video-generation","description":"[QianWen] Generate videos using Wan models. Supports text-to-video, image-to-video, first+last frame, reference-based role-play, and video editing (VACE). TRIGGER when: user wants to create, generate, or edit video content, mentions video generation/animation/video clips/Wan models, or explicitly invokes this skill by name (e.g. use qianwen-video-generation). DO NOT TRIGGER when: user wants to generate images (use qianwen-image-generation), understand/analyze existing videos (use qianwen-vision), text-only tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-video-generation/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-video-generation","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-video-generation","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-video-generation/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"qianwen-vision","name":"qianwen-vision","description":"[QianWen] Understand images and videos with Qwen vision models. TRIGGER when: user wants to analyze, describe, or extract information from images or videos, OCR text extraction, chart/table reading, visual reasoning, multi-image comparison, screenshot understanding, video comprehension, or explicitly invokes this skill by name (e.g. use qianwen-vision). DO NOT TRIGGER when: user wants to generate/create images (use qianwen-image-generation), generate videos (use qianwen-video-generation), text-only tasks without visual input, or non-Qwen vision tasks.","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-vision/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-vision","source":"agents-skills-project","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-vision","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/.agents/skills/qianwen-vision/SKILL.md","scope":"project","source":"agents-skills-project"},"disableModelInvocation":false,"available":true},{"id":"skill-creator","name":"skill-creator","description":"Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.","filePath":"/usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/skill-creator","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/skill-creator","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"spike","name":"spike","description":"Run throwaway prototypes to validate feasibility, compare approaches, and report a verdict.","filePath":"/usr/lib/node_modules/openclaw/skills/spike/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/spike","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/spike","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/spike/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"taskflow","name":"taskflow","description":"Coordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.","filePath":"/usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"taskflow-inbox-triage","name":"taskflow-inbox-triage","description":"Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.","filePath":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"tencent-news","name":"tencent-news","description":"7×24 新闻资讯搜索工具,聚焦中国国内信息和国际热点。支持新闻搜索,包括热点新闻、早报晚报、实时资讯、领域新闻和天气信息查询。当用户需要搜索新闻、新闻热榜、新闻早晚报、订阅新闻推送、获取相关新闻资讯和查询天气信息时使用。","filePath":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/tencent-news/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/tencent-news","source":"openclaw-workspace","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/tencent-news","origin":"top-level","path":"$OPENCLAW_STATE_DIR/agents/101/workspace/skills/tencent-news/SKILL.md","scope":"project","source":"openclaw-workspace"},"disableModelInvocation":false,"available":true},{"id":"tmux","name":"tmux","description":"Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.","filePath":"/usr/lib/node_modules/openclaw/skills/tmux/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/tmux","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/tmux","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/tmux/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"weather","name":"weather","description":"Current weather and forecasts with wttr.in via curl for locations, rain, temperature, travel planning.","filePath":"/usr/lib/node_modules/openclaw/skills/weather/SKILL.md","baseDir":"/usr/lib/node_modules/openclaw/skills/weather","source":"openclaw-bundled","sourceInfo":{"baseDir":"/usr/lib/node_modules/openclaw/skills/weather","origin":"top-level","path":"/usr/lib/node_modules/openclaw/skills/weather/SKILL.md","scope":"project","source":"openclaw-bundled"},"disableModelInvocation":false,"available":true},{"id":"wecom-contact-lookup","name":"wecom-contact-lookup","description":"通讯录成员查询技能,基于 MCP tool 协议封装的 `get_userlist` 接口,获取当前用户可见范围内的通讯录成员,支持按姓名/别名本地筛选匹配。返回 userid、姓名和别名。⚠️ 仅返回当前用户有权限查看的成员,非全量成员。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-contact-lookup/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-contact-lookup","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-contact-lookup","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-contact-lookup/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-doc-manager","name":"wecom-doc-manager","description":"企业微信文档管理技能。提供文档的创建、读取和编辑能力,支持通过 docid 或文档 URL 操作企业微信文档(doc_type=3)和智能表格(doc_type=10)。适用场景:(1) 以 Markdown 格式导出获取文档完整内容(异步轮询) (2) 新建文档或智能表格 (3) 用 Markdown 格式覆写文档内容。当用户需要查看文档内容、创建新文档、编辑文档正文时触发此 Skill。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-doc-manager/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-doc-manager","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-doc-manager","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-doc-manager/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-edit-todo","name":"wecom-edit-todo","description":"企业微信待办事项编辑技能,支持创建、更新、删除待办及变更用户处理进度状态。在用户说\"帮我创建一个待办\"、\"把这个任务分派给张三\"、\"标记待办完成\"、\"删掉那个待办\"、\"帮我建个提醒\"、\"更新一下待办内容\"、\"把提醒时间改到下周\"、\"接受这个待办\"、\"拒绝这个待办\"等需要对待办进行写操作的场景时使用。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-edit-todo/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-edit-todo","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-edit-todo","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-edit-todo/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-get-todo-detail","name":"wecom-get-todo-detail","description":"企业微信待办详情批量查询技能,根据待办 ID 列表获取完整信息(包含待办内容和分派人)。在用户说\"看看这个待办的详情\"、\"待办内容是什么\"、\"这个待办分派给谁了\"、\"告诉我待办的具体信息\"等需要查看待办完整内容的场景时使用。通常配合 wecom-get-todo-list 使用——先获取待办 ID 列表,再用本技能获取详情。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-detail/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-detail","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-detail","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-detail/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-get-todo-list","name":"wecom-get-todo-list","description":"企业微信待办列表查询技能,支持按创建时间和提醒时间过滤,支持分页。在用户说\"看看我的待办列表\"、\"我有哪些待办\"、\"这周的待办有哪些\"、\"最近有什么待办\"、\"查一下我的待办\"、\"列出所有待办\"等需要浏览待办概览的场景时使用。注意:此技能仅返回待办概要信息(不含内容和分派人),如需完整详情请配合 wecom-get-todo-detail 使用。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-list/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-list","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-list","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-get-todo-list/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-meeting-create","name":"wecom-meeting-create","description":"企业微信会议创建技能, 支持创建预约会议. 当用户需要\"创建会议\", \"预约会议\", \"约会议\", \"安排会议\"时触发.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-create/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-create","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-create","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-create/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-meeting-manage","name":"wecom-meeting-manage","description":"企业微信会议管理技能, 支持取消会议和更新会议受邀成员. 当用户需要\"取消会议\", \"删除会议\", \"修改会议成员\", \"添加会议参与人\", \"移除会议成员\"时触发.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-manage/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-manage","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-manage","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-manage/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-meeting-query","name":"wecom-meeting-query","description":"企业微信会议查询技能, 支持查询会议列表, 获取会议详情, 按关键词查找会议. 当用户需要\"查看会议\", \"查询会议列表\", \"会议详情\", \"什么时候开会\", \"有哪些会议\", \"查找会议\"时触发.","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-query/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-query","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-query","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-meeting-query/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-msg","name":"wecom-msg","description":"企业微信消息技能。提供会话列表查询、消息记录拉取(支持文本/图片/文件/语音/视频)、多媒体文件获取和文本消息发送能力。当用户需要\"查看消息\"、\"看聊天记录\"、\"发消息给某人\"、\"最近有什么消息\"、\"给群里发消息\"、\"看看发了什么图片/文件\"时触发。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-msg/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-msg","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-msg","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-msg/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-preflight","name":"wecom-preflight","description":"企业微信插件前置条件检查。在执行任何 wecom_mcp 操作前,通过 shell 命令检查工具权限配置(profile 和白名单),若缺失则自动修复并提示用户重启 Gateway。所有使用 wecom_mcp 的技能都应在首次调用前执行此检查。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-preflight/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-preflight","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-preflight","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-preflight/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-schedule","name":"wecom-schedule","description":"企业微信日程管理技能。适用于用户对企业微信日程的各类管理需求。当用户需要:(1) 查询指定时间范围内的日程列表或获取日程详细信息(标题、时间、地点、参与者等),(2) 创建新日程并设置提醒、参与人等,(3) 修改已有日程的标题、时间、地点等信息或取消日程,(4) 添加或移除日程参与人,(5) 查询多个成员的闲忙状态并分析共同空闲时段以安排会议时使用此技能。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-schedule/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-schedule","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-schedule","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-schedule/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-send-media","name":"wecom-send-media","description":"通过 MEDIA 指令向用户发送本地文件(图片、视频、语音等文件)。当用户要求发送或分享文件时,或当生成的文件需要交付给用户时使用。仅当通过 wecom 通道通信时使用此技能。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-media/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-media","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-media","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-media/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-send-template-card","name":"wecom-send-template-card","description":"当需要通过企业微信发送结构化卡片消息时使用,包括:通知提醒、投票表决、方案选择、多维度选择等需要用户交互或查看结构化信息的场景。即使用户未明确要求\"发卡片\",只要语境适合(如\"帮我问一下选A还是B\"),也应主动激活。仅限 wecom 通道。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-template-card/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-template-card","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-template-card","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-send-template-card/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-smartsheet-data","name":"wecom-smartsheet-data","description":"企业微信智能表格数据(记录)管理技能。提供智能表格记录的增删改查能力。适用场景:(1) 查询子表全部记录 (2) 添加一行或多行记录 (3) 更新已有记录 (4) 删除记录。当用户需要读取表格数据、写入新数据、修改或删除表格行时触发此 Skill。支持通过 docid 或文档 URL 定位文档。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-data/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-data","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-data","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-data/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true},{"id":"wecom-smartsheet-schema","name":"wecom-smartsheet-schema","description":"企业微信智能表格结构管理技能。提供子表(Sheet)和字段(Field/列)的增删改查能力。适用场景:(1) 查询智能表格的子表列表 (2) 添加、更新、删除子表 (3) 查询子表的字段/列信息 (4) 添加、更新、删除字段/列。当用户需要管理智能表格的表结构、列定义、子表配置时触发此 Skill。支持通过 docid 或文档 URL 定位文档。","filePath":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-schema/SKILL.md","baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-schema","source":"openclaw-extra","sourceInfo":{"baseDir":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-schema","origin":"top-level","path":"$OPENCLAW_STATE_DIR/plugin-skills/wecom-smartsheet-schema/SKILL.md","scope":"project","source":"openclaw-extra"},"disableModelInvocation":false,"available":true}]},"prompting":{"skillsPrompt":"⚠️ Skills catalog using compact format (descriptions omitted). Run `openclaw skills check` to audit.\n\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its name.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n\n \n alipay-authenticate-wallet\n ~/.openclaw/skills/alipay-authenticate-wallet/SKILL.md\n \n \n alipay-payment-skill\n ~/.openclaw/skills/alipay-payment-skill/SKILL.md\n \n \n baoyu-post-to-wechat\n ~/.openclaw/agents/101/workspace/skills/baoyu-post-to-wechat/SKILL.md\n \n \n browser-automation\n ~/.openclaw/plugin-skills/browser-automation/SKILL.md\n \n \n canvas\n /usr/lib/node_modules/openclaw/skills/canvas/SKILL.md\n \n \n diagram-maker\n /usr/lib/node_modules/openclaw/skills/diagram-maker/SKILL.md\n \n \n douyin-hot-copywriter\n ~/.openclaw/skills/douyin-hot-copywriter/SKILL.md\n \n \n empirecms-site-updater\n ~/.openclaw/skills/empirecms-site-updater/SKILL.md\n \n \n feishu-doc\n ~/.openclaw/plugin-skills/feishu-doc/SKILL.md\n \n \n feishu-drive\n ~/.openclaw/plugin-skills/feishu-drive/SKILL.md\n \n \n feishu-perm\n ~/.openclaw/plugin-skills/feishu-perm/SKILL.md\n \n \n feishu-wiki\n ~/.openclaw/plugin-skills/feishu-wiki/SKILL.md\n \n \n guizang-social-card-skill\n ~/.openclaw/skills/guizang-social-card-skill/SKILL.md\n \n \n healthcheck\n /usr/lib/node_modules/openclaw/skills/healthcheck/SKILL.md\n \n \n meme-maker\n /usr/lib/node_modules/openclaw/skills/meme-maker/SKILL.md\n \n \n node-connect\n /usr/lib/node_modules/openclaw/skills/node-connect/SKILL.md\n \n \n node-inspect-debugger\n /usr/lib/node_modules/openclaw/skills/node-inspect-debugger/SKILL.md\n \n \n notion\n /usr/lib/node_modules/openclaw/skills/notion/SKILL.md\n \n \n python-debugpy\n /usr/lib/node_modules/openclaw/skills/python-debugpy/SKILL.md\n \n \n qianwen-audio-tts\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-audio-tts/SKILL.md\n \n \n qianwen-image-generation\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-image-generation/SKILL.md\n \n \n qianwen-model-selector\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-model-selector/SKILL.md\n \n \n qianwen-ops-auth\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-ops-auth/SKILL.md\n \n \n qianwen-text\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-text/SKILL.md\n \n \n qianwen-update-check\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-update-check/SKILL.md\n \n \n qianwen-usage\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-usage/SKILL.md\n \n \n qianwen-video-generation\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-video-generation/SKILL.md\n \n \n qianwen-vision\n ~/.openclaw/agents/101/workspace/.agents/skills/qianwen-vision/SKILL.md\n \n \n skill-creator\n /usr/lib/node_modules/openclaw/skills/skill-creator/SKILL.md\n \n \n spike\n /usr/lib/node_modules/openclaw/skills/spike/SKILL.md\n \n \n taskflow\n /usr/lib/node_modules/openclaw/skills/taskflow/SKILL.md\n \n \n taskflow-inbox-triage\n /usr/lib/node_modules/openclaw/skills/taskflow-inbox-triage/SKILL.md\n \n \n tencent-news\n ~/.openclaw/agents/101/workspace/skills/tencent-news/SKILL.md\n \n \n tmux\n /usr/lib/node_modules/openclaw/skills/tmux/SKILL.md\n \n \n weather\n /usr/lib/node_modules/openclaw/skills/weather/SKILL.md\n \n \n wecom-contact-lookup\n ~/.openclaw/plugin-skills/wecom-contact-lookup/SKILL.md\n \n \n wecom-doc-manager\n ~/.openclaw/plugin-skills/wecom-doc-manager/SKILL.md\n \n \n wecom-edit-todo\n ~/.openclaw/plugin-skills/wecom-edit-todo/SKILL.md\n \n \n wecom-get-todo-detail\n ~/.openclaw/plugin-skills/wecom-get-todo-detail/SKILL.md\n \n \n wecom-get-todo-list\n ~/.openclaw/plugin-skills/wecom-get-todo-list/SKILL.md\n \n \n wecom-meeting-create\n ~/.openclaw/plugin-skills/wecom-meeting-create/SKILL.md\n \n \n wecom-meeting-manage\n ~/.openclaw/plugin-skills/wecom-meeting-manage/SKILL.md\n \n \n wecom-meeting-query\n ~/.openclaw/plugin-skills/wecom-meeting-query/SKILL.md\n \n \n wecom-msg\n ~/.openclaw/plugin-skills/wecom-msg/SKILL.md\n \n \n wecom-preflight\n ~/.openclaw/plugin-skills/wecom-preflight/SKILL.md\n \n \n wecom-schedule\n ~/.openclaw/plugin-skills/wecom-schedule/SKILL.md\n \n \n wecom-send-media\n ~/.openclaw/plugin-skills/wecom-send-media/SKILL.md\n \n \n wecom-send-template-card\n ~/.openclaw/plugin-skills/wecom-send-template-card/SKILL.md\n \n \n wecom-smartsheet-data\n ~/.openclaw/plugin-skills/wecom-smartsheet-data/SKILL.md\n \n \n wecom-smartsheet-schema\n ~/.openclaw/plugin-skills/wecom-smartsheet-schema/SKILL.md\n \n","systemPromptReport":{"source":"run","generatedAt":1781052692767,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","provider":"deepseek","model":"deepseek-chat","workspaceDir":"/root/.openclaw/agents/101/workspace","bootstrapMaxChars":20000,"bootstrapTotalMaxChars":60000,"bootstrapTruncation":{"warningMode":"always","warningShown":false,"truncatedFiles":0,"nearLimitFiles":0,"totalNearLimit":false},"sandbox":{"mode":"off","sandboxed":false},"systemPrompt":{"chars":33185,"hash":"643e0dde0f8302af7bb0848f9d1af00eb2295d9ab77221f5dd2cc15d1b50d6c6","projectContextChars":12966,"nonProjectContextChars":20219},"injectedWorkspaceFiles":[{"name":"AGENTS.md","path":"/root/.openclaw/agents/101/workspace/AGENTS.md","missing":false,"rawChars":7809,"injectedChars":7809,"truncated":false},{"name":"SOUL.md","path":"/root/.openclaw/agents/101/workspace/SOUL.md","missing":false,"rawChars":1886,"injectedChars":1886,"truncated":false},{"name":"TOOLS.md","path":"/root/.openclaw/agents/101/workspace/TOOLS.md","missing":false,"rawChars":850,"injectedChars":850,"truncated":false},{"name":"IDENTITY.md","path":"/root/.openclaw/agents/101/workspace/IDENTITY.md","missing":false,"rawChars":633,"injectedChars":633,"truncated":false},{"name":"USER.md","path":"/root/.openclaw/agents/101/workspace/USER.md","missing":false,"rawChars":474,"injectedChars":474,"truncated":false},{"name":"HEARTBEAT.md","path":"/root/.openclaw/agents/101/workspace/HEARTBEAT.md","missing":false,"rawChars":151,"injectedChars":151,"truncated":false},{"name":"MEMORY.md","path":"/root/.openclaw/agents/101/workspace/MEMORY.md","missing":false,"rawChars":914,"injectedChars":914,"truncated":false}],"skills":{"promptChars":7409,"hash":"8e748da6c32a41ef1d8f9105491b6b2ba10ccc3266b331ae129742cb39efec7b","entries":[{"name":"alipay-authenticate-wallet","blockChars":142},{"name":"alipay-payment-skill","blockChars":130},{"name":"baoyu-post-to-wechat","blockChars":151},{"name":"browser-automation","blockChars":133},{"name":"canvas","blockChars":121},{"name":"diagram-maker","blockChars":135},{"name":"douyin-hot-copywriter","blockChars":132},{"name":"empirecms-site-updater","blockChars":134},{"name":"feishu-doc","blockChars":117},{"name":"feishu-drive","blockChars":121},{"name":"feishu-perm","blockChars":119},{"name":"feishu-wiki","blockChars":119},{"name":"guizang-social-card-skill","blockChars":140},{"name":"healthcheck","blockChars":131},{"name":"meme-maker","blockChars":129},{"name":"node-connect","blockChars":133},{"name":"node-inspect-debugger","blockChars":151},{"name":"notion","blockChars":121},{"name":"python-debugpy","blockChars":137},{"name":"qianwen-audio-tts","blockChars":153},{"name":"qianwen-image-generation","blockChars":167},{"name":"qianwen-model-selector","blockChars":163},{"name":"qianwen-ops-auth","blockChars":151},{"name":"qianwen-text","blockChars":143},{"name":"qianwen-update-check","blockChars":159},{"name":"qianwen-usage","blockChars":145},{"name":"qianwen-video-generation","blockChars":167},{"name":"qianwen-vision","blockChars":147},{"name":"skill-creator","blockChars":135},{"name":"spike","blockChars":119},{"name":"taskflow","blockChars":125},{"name":"taskflow-inbox-triage","blockChars":151},{"name":"tencent-news","blockChars":135},{"name":"tmux","blockChars":117},{"name":"weather","blockChars":123},{"name":"wecom-contact-lookup","blockChars":137},{"name":"wecom-doc-manager","blockChars":131},{"name":"wecom-edit-todo","blockChars":127},{"name":"wecom-get-todo-detail","blockChars":139},{"name":"wecom-get-todo-list","blockChars":135},{"name":"wecom-meeting-create","blockChars":137},{"name":"wecom-meeting-manage","blockChars":137},{"name":"wecom-meeting-query","blockChars":135},{"name":"wecom-msg","blockChars":115},{"name":"wecom-preflight","blockChars":127},{"name":"wecom-schedule","blockChars":125},{"name":"wecom-send-media","blockChars":129},{"name":"wecom-send-template-card","blockChars":145},{"name":"wecom-smartsheet-data","blockChars":139},{"name":"wecom-smartsheet-schema","blockChars":143}]},"tools":{"listChars":0,"schemaChars":21886,"entries":[{"name":"read","summaryChars":298,"summaryHash":"f8a1d7cf1ecfe02b1b5865c93387e6a5891e5079117b4fe18614b6f912521727","schemaChars":304,"schemaHash":"134f19bcabe3e29d63c5cebb38f1d2556759fd08adad6bc90a4b4d3cd1fb8441","propertiesCount":3},{"name":"edit","summaryChars":326,"summaryHash":"c498a85576e187d069e8e8ea4f70f81bddd57829600d385ef61c4359fd634c9e","schemaChars":834,"schemaHash":"457e8bb9f800b21be76c4fd8c0e3078bf07ee9bf93ac82f39944c171bd8f6d84","propertiesCount":2},{"name":"write","summaryChars":127,"summaryHash":"cdb1c46027b22d1f1b923b47bfe297821d9fe589a9f9d92994961948060a4d89","schemaChars":225,"schemaHash":"e98a2484f667cf7c22d76ca103bf2022bf9113dc63fe38b899e71c328cb1e833","propertiesCount":2},{"name":"apply_patch","summaryChars":132,"summaryHash":"432bf38688a4f011d2b765a441ac07e1fdfa9faf2051679adee04abcd9332d93","schemaChars":153,"schemaHash":"05521268363ff4f191472c90d69ef08a503ba9acf1d2febc50b3ee68db32ab65","propertiesCount":1},{"name":"exec","summaryChars":539,"summaryHash":"4825198988fbfa8ebf5c2a8fbe3946da0be639b1e3b737ceaa4364195bba3f04","schemaChars":1187,"schemaHash":"0c03eeccccb7b7e97234d2c8245c6060e2b292588f02455eae20c60b61bb8bb8","propertiesCount":12},{"name":"process","summaryChars":456,"summaryHash":"55297e65d460e0e1e06e7fad4cedb75ffda8fac9fa8b10aa06d6cead3c5a76ea","schemaChars":1074,"schemaHash":"a2d30a25569f409d7e8539844c89a088044535388b24031d014577b96ed27c5c","propertiesCount":12},{"name":"cron","summaryChars":3610,"summaryHash":"262e6a7b421538d13ca6d79fc14616de3ea0c24fde8b050d6fa1652fe991e5c5","schemaChars":7929,"schemaHash":"df113d901d1284508ecf946e07346ce3ee4c7e9de28b20e0b6120d0b43f6603b","propertiesCount":14},{"name":"video_generate","summaryChars":307,"summaryHash":"59fd08c3f2947e0394c7d1aae5219763bf201537bef536228c6c4fd63724e415","schemaChars":2042,"schemaHash":"ec3a2b299579c1c85d5cb3d5b18e1185c6bb62ca128aa508692098174393cb35","propertiesCount":18},{"name":"get_goal","summaryChars":71,"summaryHash":"58dea7906d9e17e5f89a75fea24597ee068d8a56af824370dc27f8501374d6e3","schemaChars":33,"schemaHash":"8243f0af367f188a376f2c17b5eabe872a2f7a979813e0d4e2be6d594c2aa259","propertiesCount":0},{"name":"create_goal","summaryChars":155,"summaryHash":"f01e3a63d673a410ba55213ce6bd3fa2b0d2279e8e780c18aa0cb5aa991b29b3","schemaChars":267,"schemaHash":"27ee794432736471bd76390e236cc7d7e98f8469a02656e7a27109041eea0f8c","propertiesCount":2},{"name":"update_goal","summaryChars":212,"summaryHash":"285201690e5f2456b4cdcd252ff391709b84d69538df61bad694d3c0cfc19958","schemaChars":207,"schemaHash":"c37894492eedfad02f1e7fe1488900765bfe547f3b3f34cefbab4f7f57441c2c","propertiesCount":2},{"name":"skill_workshop","summaryChars":171,"summaryHash":"577c1d2b8f56bf3e9dd5e00463bbce8b8bf4cf201da9b21b588dcaa3bc6ed8cf","schemaChars":2273,"schemaHash":"15481d6889a320a46728ee32304f0a2b510c0bcf77d445052c1ef2fa5dd5368b","propertiesCount":13},{"name":"update_plan","summaryChars":163,"summaryHash":"ea18cc44224e849c68cdf0a4839c295c1b20daf2699e2fc2be4c4e1552327455","schemaChars":489,"schemaHash":"50cb08b8a29e72637eb6720e6f5f3786783824537574f05ee9ae7a5f4ecacc4b","propertiesCount":2},{"name":"sessions_list","summaryChars":135,"summaryHash":"c7e411ae02e3adff5504aaee48f02d262a8abb9152558a3172aae289e3b05faf","schemaChars":435,"schemaHash":"c29c6b82c36a2d95a88c8944f129929b2621ee2af6d17b2ab101d4d7e9633d89","propertiesCount":9},{"name":"sessions_history","summaryChars":117,"summaryHash":"f5d45b76f11a8ac63cc45d456fb6f675f0b1a2e191feb9671924cb5830058f03","schemaChars":162,"schemaHash":"ac33b8af2252262afe479236046f5a04bc018f1fcf24d1a8bf32743f0e867598","propertiesCount":3},{"name":"sessions_send","summaryChars":224,"summaryHash":"56fd935fc97400f8c60b16ae58268660a2d84d8014a60abed515576c45a6f307","schemaChars":275,"schemaHash":"f1fbaa412fe6b6aee102234c87c5aa140f39c9086f9bae6e1e9691309a602ffb","propertiesCount":5},{"name":"sessions_spawn","summaryChars":332,"summaryHash":"5ced554d0c09b9c71fa003139eca7871bbfdc0917a323fc17af2a9faec46c5b7","schemaChars":1151,"schemaHash":"9a91c7668463da8a66386260ce2ae97e7efe3bb93b9b6f03ac85102c354457e1","propertiesCount":15},{"name":"sessions_yield","summaryChars":79,"summaryHash":"f3782fc41c1522657e1d3494f486a2df998fed38a6b89dcf7f6934fb41424320","schemaChars":60,"schemaHash":"b1c4c753820bc3096d85ef7a266a14c9fbe12450536db58076b75bb61d14dbbb","propertiesCount":1},{"name":"subagents","summaryChars":132,"summaryHash":"1c2ffd38549c0444b118d43736fc4b875ea1aaabc446bbf8bc1fc4ee9180cca4","schemaChars":122,"schemaHash":"c4a241d2c3d46ba7985abfce4d3fcd63298ce81f89d49183c8f3d584c48d0c33","propertiesCount":2},{"name":"session_status","summaryChars":278,"summaryHash":"71177e543dc6235bad4b1a26761995681dcec27ab58dcb4f4f8a7fc9a7b2b5aa","schemaChars":89,"schemaHash":"d2995f3d69d126e98ac93eec3c2a9fe5556925bd7979a8e4b6b5a2bf62d329dd","propertiesCount":2},{"name":"web_search","summaryChars":65,"summaryHash":"b38e9b3c079beaa988d3c576303660b91a55c2e72f56351da04160529173273f","schemaChars":991,"schemaHash":"3879e368875d824b14e0e683f81408824e9a2a5850fa2f8514a68caebda54d18","propertiesCount":12},{"name":"web_fetch","summaryChars":93,"summaryHash":"8875afbb51bd63673e5e6836ca31eeda73914a464862665cd73b346e28d28fd5","schemaChars":317,"schemaHash":"d2d8ad58a1b84d849dd16142282aff6c5606f7b0e3d08405e1b740a6a79e6bcc","propertiesCount":3},{"name":"image","summaryChars":119,"summaryHash":"0eae16e4e16f86cc74ea64bdd48812b0a1d86577fee36dc4cf2c6e7974c83ef6","schemaChars":350,"schemaHash":"49bb766071c935edca8c2d0df47fc2109bbffe3d4ba32d0b19fe90ec873736ce","propertiesCount":6},{"name":"memory_search","summaryChars":605,"summaryHash":"0f918d28864d3682ae77731f149273997c84773592a466b18c7cd0121b599a05","schemaChars":250,"schemaHash":"088cd2a3d3a47b251429ff7c56844cdedd1c45c3af0fa8bfaf7aa795766976bf","propertiesCount":4},{"name":"memory_get","summaryChars":239,"summaryHash":"bff1141a3da31a345c550337417efc9ace4da2909004606c727c59ca1a294495","schemaChars":241,"schemaHash":"78f5d58460a82f9104deebad2f1873a8cde05d1ce7328b3ba4da6e994653e70a","propertiesCount":4},{"name":"wecom_mcp","summaryChars":288,"summaryHash":"f84882350521af5fd0982b63362a4ac280c67fa51a76799c0e93a627652a9552","schemaChars":426,"schemaHash":"7ccdd8994fd5316f030378b8d00ef906800dd0eafee9ab2ecf18756db43f51b5","propertiesCount":4}]}}},"redaction":{"config":{"mode":"redactConfigObject","secretsMasked":true},"payloads":{"mode":"sanitizeDiagnosticPayload","credentialsRemoved":true,"imageDataRedacted":true},"harness":{"mode":"diagnostic-support-redaction","programArgumentsRedacted":true,"localPathsRedacted":true}},"metadata":{"sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","agentId":"101","messageProvider":"feishu"}}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"context.compiled","ts":"2026-06-10T00:51:32.890Z","seq":3,"sourceSeq":17,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"d97d3534-b771-4943-bcec-dca60d95fb99","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"systemPrompt":{"truncated":true,"reason":"trajectory-field-size-limit","originalChars":33651,"limitChars":32768},"prompt":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf1fde20a0c218c220d48a04c\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:51:29 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf1fde20a0c218c220d48a04c]\nou_499a5c731212b08e951a441a2bc8a82c: 写逐字稿就行了,不要你写这个脚本了","messages":[{"role":"user","content":"[message_id: om_x100b6dbf5348cca8c4a375e8c70bda2]\nou_499a5c731212b08e951a441a2bc8a82c: 再写一个,人类对于龙虾的开发还不到1%。\n\n人类历史上,凡是用代码解决过的问题,龙虾都可以自动的用代码来解决,它要有代码。没有代码,他就自己写,有代码就从GitHub上找,下载完帮你搭建环境,试运行,出bug,跑,给你结果","timestamp":1781051867704},{"role":"assistant","content":[{"type":"text","text":"首长,您这是要一篇关于龙虾(自主AI编码Agent)的公众号逐字稿脚本,对吧?核心命题是:**人类对龙虾的开发还不到1%,龙虾能自动解决一切代码问题。**\n\n我先查一下相关素材,然后出脚本。"},{"type":"toolCall","id":"call00onQsEvkVXRRxFAnvEok20373","name":"web_search","arguments":{"query":"AI coding agent 自主编程 未来已来 2025 2026","count":5},"partialArgs":"{\"query\": \"AI coding agent 自主编程 未来已来 2025 2026\", \"count\": 5}"},{"type":"toolCall","id":"call01fouQj9kDBILLFnoNoxY14235","name":"web_search","arguments":{"query":"Claude coding Agent 自动写代码 GitHub 下载 搭建环境","count":5},"partialArgs":"{\"query\": \"Claude coding Agent 自动写代码 GitHub 下载 搭建环境\", \"count\": 5}"},{"type":"toolCall","id":"call02OOcRB4fsDb9VDDp8RXjX0721","name":"web_search","arguments":{"query":"AI agent 自动解决问题 编程 未来 人类开发不到1%","count":5},"partialArgs":"{\"query\": \"AI agent 自动解决问题 编程 未来 人类开发不到1%\", \"count\": 5}"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":10117,"output":247,"cacheRead":9344,"cacheWrite":0,"totalTokens":19708,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1781051868286,"responseId":"1c69b78a-c3ac-433d-9f68-6f19d8ed2ad3"},{"role":"toolResult","toolCallId":"call00onQsEvkVXRRxFAnvEok20373","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892796},{"role":"toolResult","toolCallId":"call01fouQj9kDBILLFnoNoxY14235","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892802},{"role":"toolResult","toolCallId":"call02OOcRB4fsDb9VDDp8RXjX0721","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892809},{"role":"assistant","content":[{"type":"text","text":"搜索暂时超时,不影响,您给的素材足够直接出脚本了。我按照您的意思——龙虾能自主解决一切代码问题,全部流程自动化——来写。\n\n---\n\n**脚本:龙虾不到1%**\n\n| 时长 | 画面 | 台词 |\n|------|------|------|\n| 0:00-0:05 | 黑屏白字:人类对龙虾的开发还不到1% | 人类对龙虾的开发,还不到1%。 |\n| 0:05-0:20 | 快速切换代码编辑器画面→AI自动写代码→浏览器自动测试 | 人类历史上,凡是能用代码解决的问题,龙虾都可以自动地用代码来解决。 |\n| 0:20-0:35 | 画面:GitHub搜索→自动下载→终端跑安装 | 但前提是——它得有代码。没有代码?它会自己写。有代码?它上GitHub给你搜,下载下来,开发环境帮你搭好。 |\n| 0:35-0:50 | 画面:终端自动运行→报错→自动修正→再次运行→绿pass | 然后试运行。出bug?修。再出?再修。直到跑通。整个过程不需要你动手,它就自己在那儿干活。 |\n| 0:50-1:05 | 特写:终端输出结果 | 最后——结果摆你面前。 |\n| 1:05-1:20 | 画风一转:空旷的会议室,一张椅子,一个屏幕 | 你可能会想:这跟找个程序员有啥区别?区别大了——它不吃饭、不睡觉、不抱怨需求改来改去,而且又快又便宜。 |\n| 1:20-1:40 | 蒙太奇:各种行业的人在聊天→刷卡支付→点头 | 有人说AI抢饭碗,但真正看懂的人已经在用龙虾给自己建团队了。一个人搭一个技术团队,不是梦。 |\n| 1:40-1:55 | 俯拍镜头:一本书\\一条深海鱼\\龙虾特写 | 龙虾就在那儿,深海里的资源,我们才捞了一点点。所以别急着说AI不行,先问问自己——你让龙虾帮你干过活吗? |\n| 1:55-2:00 | Logo/二维码 | 关注我,带你用龙虾降维打击。 |\n\n---\n\n**备注:**\n- 您说的\"龙虾\"在脚本里保持原词,不做替换,这本身就是你的IP标签\n- 整体节奏偏快、有画面感,符合短视频逐字稿要求\n- 如需调整口吻(更激进/更温和)、增减时长,或者改为文章版,随时说"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":354,"output":558,"cacheRead":19456,"cacheWrite":0,"totalTokens":20368,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1781051892824,"responseId":"a4968589-9901-4e20-8ba2-a5d22e6f4ebb"},{"role":"user","content":"[message_id: om_x100b6dbf0f2874a8c0af9bf55a6a9ad]\nou_499a5c731212b08e951a441a2bc8a82c: 还写逐字稿,重新写一下","timestamp":1781052449024},{"role":"assistant","content":[{"type":"text","text":"好的首长,重新写一版,这次节奏更硬、更大白话,去掉花哨的画面描述,聚焦龙虾的核心能力。\n\n---\n\n**脚本:龙虾不到1%(第二版)**\n\n| 时长 | 台词 |\n|------|------|\n| 0:00-0:08 | 人类对龙虾的开发,还不到1%。你把AI想得太简单了。 |\n| 0:08-0:20 | 人类历史上所有能用代码解决的问题,龙虾都能自动用代码解决。注意啊,是自动。不是你去问它,它给你写一段代码你自己粘贴。 |\n| 0:20-0:35 | 是它自己写代码,自己搭建环境,自己运行。没有代码?它现写。有现成的?它上GitHub给你搜,下下来,安装好。 |\n| 0:35-0:50 | 然后试运行。跑不通是吧?报错了是吧?自己修,修完再跑,跑到通为止。全程你不用敲一行命令。 |\n| 0:50-1:05 | 最后结果给你,干干净净。你只管验收它干完了没。 |\n| 1:05-1:20 | 有人说程序员要失业了,这事我不评价。但如果你是一个创业者、小老板、甚至只是有个想法的人,你以前需要雇一个开发团队,现在你只需要一个龙虾。 |\n| 1:20-1:35 | 不吃饭不睡觉不下班不提离职,还贼便宜。这玩意儿你放着不用? |\n| 1:35-1:50 | 龙虾这个东西,说真的就跟90年代的互联网一样,那时候没人觉得这玩意能改变世界。现在呢? |\n| 1:50-2:00 | 别等了,动手让龙虾干活去。 |\n\n---\n\n**改版说明:**\n- 去掉了画面描述,只剩台词,更短视频风格\n- 每段卡在15秒左右,方便剪辑\n- 口气更直接,带点\"你还不懂\"的味道\n- 核心逻辑链条:能力描述→流程展示→对创业者的价值→号召行动\n\n要发还是调?"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":7123,"output":453,"cacheRead":13312,"cacheWrite":0,"totalTokens":20888,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1781052449792,"responseId":"76925081-8884-4fbd-a0d4-6d94c69236b7"}],"tools":[{"name":"apply_patch","description":"Apply a patch to one or more files using the apply_patch format. The input should include *** Begin Patch and *** End Patch markers.","parameters":{"type":"object","required":["input"],"properties":{"input":{"type":"string","description":"Patch content using the *** Begin Patch/End Patch format."}}}},{"name":"create_goal","description":"Create a goal only when explicitly requested by the user or system instructions. Fails if a goal already exists; use user-facing goal controls to clear it.","parameters":{"type":"object","required":["objective"],"properties":{"objective":{"type":"string","description":"Concrete objective to pursue. Create only when explicitly requested."},"token_budget":{"type":"number","description":"Optional positive token budget for this goal."}}}},{"name":"cron","description":"Manage Gateway cron jobs and wake events: reminders, check-back-later, delayed follow-ups, recurring work. Do not emulate scheduling with exec sleep/process polling.\n\nMain cron => system events for heartbeat. Isolated cron => background task in `openclaw tasks`.\n\nACTIONS:\n- status: scheduler status\n- list: jobs; includeDisabled true includes disabled; agentId filter auto-filled from session\n- get: one job; needs jobId\n- add: create job; needs job object\n- update: patch job; needs jobId + patch\n- remove: delete job; needs jobId\n- run: trigger now; needs jobId\n- runs: run history; needs jobId\n- wake: send wake event; needs text, optional mode\n\nJOB SCHEMA (for add action):\n{\n \"name\": \"string\",\n \"schedule\": { ... }, // required\n \"payload\": { ... }, // required\n \"delivery\": { ... }, // optional announce for isolated/current/session, webhook for any target\n \"sessionTarget\": \"main\" | \"isolated\" | \"current\" | \"session:\",\n \"enabled\": true | false // default true\n}\n\nSESSION TARGET OPTIONS:\n- \"main\": main session; requires payload.kind=\"systemEvent\"\n- \"isolated\": ephemeral isolated session; requires payload.kind=\"agentTurn\"\n- \"current\": bind current session at creation\n- \"session:\": persistent named session\n\nDEFAULTS:\n- payload.kind=\"systemEvent\" → defaults to \"main\"\n- payload.kind=\"agentTurn\" → defaults to \"isolated\"\nCurrent binding needs sessionTarget=\"current\".\n\nSCHEDULE TYPES (schedule.kind):\n- \"at\": one-shot absolute time\n { \"kind\": \"at\", \"at\": \"\" }\n- \"every\": recurring interval\n { \"kind\": \"every\", \"everyMs\": , \"anchorMs\": }\n- \"cron\": expr in supplied timezone, or Gateway host local timezone when tz omitted\n { \"kind\": \"cron\", \"expr\": \"\", \"tz\": \"\" }\n Write expr in local wall-clock time; do not convert the requested local time to UTC first.\n tz omitted => Gateway host local timezone, not UTC.\n Example 6pm Shanghai daily: { \"kind\": \"cron\", \"expr\": \"0 18 * * *\", \"tz\": \"Asia/Shanghai\" }\n\nFor \"at\", ISO timestamps without timezone are UTC.\n\nPAYLOAD TYPES (payload.kind):\n- \"systemEvent\": inject text as system event\n { \"kind\": \"systemEvent\", \"text\": \"\" }\n- \"agentTurn\": run agent with prompt; isolated/current/session only\n { \"kind\": \"agentTurn\", \"message\": \"\", \"model\": \"\", \"thinking\": \"\", \"timeoutSeconds\": }\n\nDELIVERY (top-level):\n { \"mode\": \"none|announce|webhook\", \"channel\": \"\", \"to\": \"\", \"threadId\": \"\", \"bestEffort\": }\n - isolated agentTurn default when omitted: \"announce\"\n - announce: send to chat channel; isolated/current/session only; optional channel/to\n - threadId: chat thread/topic id\n - webhook: POST finished-run event to delivery.to URL\n - Specific chat/recipient: set announce delivery.channel/to; do not call messaging tools inside run.\n\nCRITICAL CONSTRAINTS:\n- sessionTarget=\"main\" REQUIRES payload.kind=\"systemEvent\"\n- sessionTarget=\"isolated\" | \"current\" | \"session:xxx\" REQUIRES payload.kind=\"agentTurn\"\n- Webhook: delivery.mode=\"webhook\" and delivery.to URL.\nDefault: prefer isolated agentTurn jobs unless the user explicitly wants current-session binding.\n\nRESTRICTED CRON RUNS:\n- Some isolated cron runs get narrow self-cleanup grant: status/list self-only, get/runs current job only, mutation only remove current job.\n\nWAKE MODES (for wake action):\n- \"next-heartbeat\" default: wake next heartbeat\n- \"now\": wake immediately\n\nUse jobId canonical; id accepted compat. contextMessages (0-10) adds previous messages as job context.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"gatewayUrl":{"type":"string"},"timeoutMs":{"type":"integer","minimum":1},"includeDisabled":{"type":"boolean"},"job":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"additionalProperties":true},"jobId":{"type":"string"},"id":{"type":"string"},"patch":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"additionalProperties":true},"text":{"type":"string"},"mode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"runMode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"contextMessages":{"type":"integer","minimum":0,"maximum":10},"agentId":{"type":"string","description":"List filter: agent id"}},"additionalProperties":true}},{"name":"edit","description":"Edit a single file using exact text replacement. Every edits[].oldText must match a unique, non-overlapping region of the original file. If two changes affect the same block or nearby lines, merge them into one edit instead of emitting overlapping edits. Do not include large unchanged regions just to connect distant changes.","parameters":{"type":"object","required":["path","edits"],"properties":{"path":{"type":"string","description":"Path to the file to edit (relative or absolute)"},"edits":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"One or more targeted replacements. Each edit is matched against the original file, not incrementally. Do not include overlapping or nested edits. If two changes touch the same block or nearby lines, merge them into one edit instead."}},"additionalProperties":false}},{"name":"exec","description":"Execute shell commands with background continuation for work that starts now. Use yieldMs/background to continue later via process tool. For long-running work started now, rely on automatic completion wake when it is enabled and the command emits output or fails; otherwise use process to confirm completion. Use process whenever you need logs, status, input, or intervention. Do not use exec sleep or delay loops for reminders or deferred follow-ups; use cron instead. Use pty=true for TTY-required commands (terminal UIs, coding agents).","parameters":{"type":"object","required":["command"],"properties":{"command":{"type":"string","description":"Shell command to execute"},"workdir":{"type":"string","description":"Working directory (defaults to cwd)"},"env":{"type":"object","patternProperties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"yieldMs":{"type":"number","description":"Milliseconds to wait before backgrounding (default 10000)"},"background":{"type":"boolean","description":"Run in background immediately"},"timeout":{"type":"number","description":"Timeout in seconds (optional, kills process on expiry)"},"pty":{"type":"boolean","description":"Run in a pseudo-terminal (PTY) when available (TTY-required CLIs, coding agents)"},"elevated":{"type":"boolean","description":"Run on the host with elevated permissions (if allowed)"},"host":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Exec host/target (auto|sandbox|gateway|node)."},"security":{"type":"string","description":"Ignored for normal calls; exec security is set by tools.exec.security and host approvals."},"ask":{"type":"string","description":"Exec ask mode (off|on-miss|always)."},"node":{"type":"string","description":"Node id/name for host=node."}}}},{"name":"get_goal","description":"Get the current goal for this thread, including status and token usage.","parameters":{"type":"object","properties":{}}},{"name":"image","description":"Analyze images with available vision model. Use image for one path/URL, images for max 20. Prompt says what to inspect.","parameters":{"type":"object","properties":{"prompt":{"type":"string"},"image":{"type":"string","description":"One image path/URL."},"images":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Image paths/URLs; maxImages default 20."},"model":{"type":"string"},"maxBytesMb":{"type":"number","exclusiveMinimum":0},"maxImages":{"type":"integer","minimum":1}}}},{"name":"memory_get","description":"Safe exact excerpt read from MEMORY.md or memory/*.md. Defaults to a bounded excerpt when lines are omitted, includes truncation/continuation info when more content exists, and `corpus=wiki` reads from registered compiled-wiki supplements.","parameters":{"type":"object","properties":{"path":{"type":"string"},"from":{"type":"integer","minimum":1},"lines":{"type":"integer","minimum":1},"corpus":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}},"required":["path"],"additionalProperties":false}},{"name":"memory_search","description":"Mandatory recall step: semantically search MEMORY.md + memory/*.md (and optional session transcripts) before answering questions about prior work, decisions, dates, people, preferences, or todos. Optional `corpus=wiki` or `corpus=all` also searches registered compiled-wiki supplements. `corpus=memory` restricts hits to indexed memory files (excludes session transcript chunks from ranking). `corpus=sessions` restricts hits to indexed session transcripts (same visibility rules as session history tools). If response has disabled=true, memory retrieval is unavailable and should be surfaced to the user.","parameters":{"type":"object","properties":{"query":{"type":"string"},"maxResults":{"type":"integer","minimum":1},"minScore":{"type":"number"},"corpus":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}},"required":["query"],"additionalProperties":false}},{"name":"process","description":"Manage running exec sessions for commands already started: list, poll, log, write, send-keys, submit, paste, kill. Use poll/log when you need status, logs, quiet-success confirmation, or completion confirmation when automatic completion wake is unavailable. Use poll/log also for input-wait hints. Use write/send-keys/submit/paste/kill for input or intervention. Do not use process polling to emulate timers or reminders; use cron for scheduled follow-ups.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","description":"Process action (list|poll|log|write|send-keys|submit|paste|kill|clear|remove)"},"sessionId":{"type":"string","description":"Session id for actions other than list"},"data":{"type":"string","description":"Data to write for write"},"keys":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Key tokens to send for send-keys"},"hex":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Hex bytes to send for send-keys"},"literal":{"type":"string","description":"Literal string for send-keys"},"text":{"type":"string","description":"Text to paste for paste"},"bracketed":{"type":"boolean","description":"Wrap paste in bracketed mode"},"eof":{"type":"boolean","description":"Close stdin after write"},"offset":{"type":"number","description":"Log offset"},"limit":{"type":"number","description":"Log length"},"timeout":{"type":"number","description":"For poll: wait up to this many milliseconds before returning; max 30000 ms, higher values are clamped to 30000","minimum":0}}}},{"name":"read","description":"Read the contents of a file. Supports text files and images (jpg, png, gif, webp). Images are sent as attachments. For text files, output is truncated to 2000 lines or 50KB (whichever is hit first). Use offset/limit for large files. When you need the full file, continue with offset until complete.","parameters":{"type":"object","required":["path"],"properties":{"path":{"type":"string","description":"Path to the file to read (relative or absolute)"},"offset":{"type":"number","description":"Line number to start reading from (1-indexed)"},"limit":{"type":"number","description":"Maximum number of lines to read"}}}},{"name":"session_status","description":"Show /status-like card for current/visible session: model, usage, time, cost, tasks. Use `sessionKey=\"current\"` for current session; UI labels like `openclaw-tui` are not keys. `model` sets session override; `model=default` resets. Use for active model/session config questions.","parameters":{"type":"object","properties":{"sessionKey":{"type":"string"},"model":{"type":"string"}}}},{"name":"sessions_history","description":"Fetch sanitized history for visible session. Use before replying, debugging, resuming; supports limits/tool messages.","parameters":{"type":"object","required":["sessionKey"],"properties":{"sessionKey":{"type":"string"},"limit":{"type":"integer","minimum":1},"includeTools":{"type":"boolean"}}}},{"name":"sessions_list","description":"List visible sessions; filter by kind, label, agentId, search, activity. Use before sessions_history or sessions_send target selection.","parameters":{"type":"object","properties":{"kinds":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"limit":{"type":"integer","minimum":1},"activeMinutes":{"type":"integer","minimum":1},"messageLimit":{"type":"integer","minimum":0},"label":{"type":"string","minLength":1},"agentId":{"type":"string","minLength":1,"maxLength":64},"search":{"type":"string","minLength":1},"includeDerivedTitles":{"type":"boolean"},"includeLastMessage":{"type":"boolean"}}}},{"name":"sessions_send","description":"Send message to visible session by sessionKey/label, or configured agent by agentId. Thread-scoped chats rejected; target parent channel session. Creates missing configured-agent main session; waits for reply when available.","parameters":{"type":"object","required":["message"],"properties":{"sessionKey":{"type":"string"},"label":{"type":"string","minLength":1,"maxLength":512},"agentId":{"type":"string","minLength":1,"maxLength":64},"message":{"type":"string"},"timeoutSeconds":{"type":"integer","minimum":0}}}},{"name":"sessions_spawn","description":"Spawn clean child session; default `runtime=\"subagent\"`. `mode=\"run\"` one-shot background work. Subagents inherit parent workspace. Native subagents get task in first visible `[Subagent Task]` message. Native only: `context=\"fork\"` only when child needs current transcript; else omit or `isolated`. Use for fresh child-session work.","parameters":{"type":"object","required":["task"],"properties":{"task":{"type":"string"},"taskName":{"type":"string","description":"Stable alias for later targeting; lowercase letters/digits/underscores/hyphens, starts letter."},"label":{"type":"string"},"runtime":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"agentId":{"type":"string"},"model":{"type":"string"},"thinking":{"type":"string"},"cwd":{"type":"string"},"mode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"cleanup":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"sandbox":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"context":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Native context. Omit/\"isolated\" for clean child; \"fork\" only when child needs requester transcript."},"lightContext":{"type":"boolean","description":"Light bootstrap context; runtime=\"subagent\" only."},"attachments":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"maxItems":50},"attachAs":{"type":"object","properties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}}}}},{"name":"sessions_yield","description":"End current turn. Use after spawning subagents; results arrive as next message.","parameters":{"type":"object","properties":{"message":{"type":"string"}}}},{"name":"skill_workshop","description":"Create, update, revise, list, inspect, apply, reject, or quarantine Skill Workshop proposals when reusable procedures should be captured, improved, or explicitly approved.","parameters":{"type":"object","required":["action"],"properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"create for a new skill proposal, update for an existing skill, revise for a pending proposal, list or inspect proposals for proposal discovery, apply/reject/quarantine for explicit proposal lifecycle actions."},"proposal_id":{"type":"string","description":"Existing proposal id for action=inspect, action=revise, action=apply, action=reject, or action=quarantine."},"name":{"type":"string","description":"Skill/proposal name. Required for action=create; optional resolver for action=inspect or action=revise when proposal_id is unknown."},"query":{"type":"string","description":"Optional query for action=list."},"status":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Optional proposal status filter for action=list."},"limit":{"type":"integer","minimum":1,"maximum":50,"description":"Maximum proposals to return for action=list. Defaults to 20."},"description":{"type":"string","maxLength":160,"description":"Skill description for action=create, action=update, or action=revise. Keep it concise; max 160 bytes."},"skill_name":{"type":"string","description":"Existing skill name or key for action=update."},"proposal_content":{"type":"string","description":"Full proposed procedure markdown for action=create, action=update, or action=revise. It will be stored as PROPOSAL.md. Keep under configured skills.workshop.maxSkillBytes; default max is 40000 bytes."},"support_files":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Optional support files to store with the proposal."},"goal":{"type":"string","description":"Proposal or improvement goal."},"evidence":{"type":"string","description":"Short evidence or notes."},"reason":{"type":"string","description":"Optional reason for action=apply, action=reject, or action=quarantine."}},"additionalProperties":false}},{"name":"subagents","description":"List active and recent subagents for the requester session. If sessions_yield exists, use it for completion; do not poll wait loops.","parameters":{"type":"object","properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6}},"recentMinutes":{"type":"integer","minimum":1}}}},{"name":"update_goal","description":"Mark the current goal complete only when achieved, or blocked only after the same blocking condition recurs for at least three consecutive goal turns. Do not use blocked for ordinary difficulty or missing polish.","parameters":{"type":"object","required":["status"],"properties":{"status":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"complete | blocked."},"note":{"type":"string","description":"Short status note."}}}},{"name":"update_plan","description":"Update current run plan. Use for non-trivial multi-step work; keep plan current while executing. Short steps; max one `in_progress`; skip for simple one-step work.","parameters":{"type":"object","required":["plan"],"properties":{"explanation":{"type":"string","description":"Short note: what changed."},"plan":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"minItems":1,"description":"Ordered steps; max one in_progress."}}}},{"name":"video_generate","description":"Create videos. Session chats: background task; do not call video_generate again for same request; wait completion, then report through the current visible-reply contract with generated media attached using structured media fields. \"status\" checks active task. Duration may round to provider-supported value.","parameters":{"type":"object","properties":{"action":{"type":"string","description":"\"generate\" default, \"status\" active task, \"list\" providers/models."},"prompt":{"type":"string","description":"Video prompt."},"image":{"type":"string","description":"One reference image path/URL."},"images":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Reference images; max 9."},"imageRoles":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"`image` + `images` roles by index after de-dupe. Values: first_frame, last_frame, reference_image; empty string leaves unset."},"video":{"type":"string","description":"One reference video path/URL."},"videos":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Reference videos; max 4."},"videoRoles":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"`video` + `videos` roles by index after de-dupe. Value: reference_video; empty string leaves unset."},"model":{"type":"string","description":"Provider/model override, e.g. qwen/wan2.6-t2v."},"filename":{"type":"string","description":"Output filename hint; basename preserved in managed media dir."},"size":{"type":"string","description":"Size hint, e.g. 1280x720, 1920x1080."},"aspectRatio":{"type":"string","description":"Aspect ratio: 1:1, 16:9, 9:16, \"adaptive\", or provider value; unsupported normalized/ignored."},"resolution":{"type":"string","description":"Resolution: 360P, 480P, 540P, 720P, 768P, 1080P, 4K, or provider value; unsupported normalized/ignored."},"durationSeconds":{"type":"integer","description":"Target seconds; may round to nearest supported duration.","minimum":1},"audio":{"type":"boolean","description":"Generated-audio toggle."},"watermark":{"type":"boolean","description":"Watermark toggle."},"providerOptions":{"type":"object","patternProperties":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Provider JSON options, e.g. {\"seed\":42}. Keys/types must match provider capabilities; mismatch skips candidate. Use action=list for accepted keys."},"timeoutMs":{"type":"integer","description":"Provider timeout ms.","minimum":1}}}},{"name":"web_fetch","description":"Fetch URL and extract readable markdown/text. Lightweight page access; no browser automation.","parameters":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"HTTP(S) URL."},"extractMode":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Extract as markdown/text.","default":"markdown"},"maxChars":{"type":"integer","description":"Max chars returned; truncates.","minimum":100}}}},{"name":"web_search","description":"Search web for current info; returns normalized provider results.","parameters":{"type":"object","required":["query"],"properties":{"query":{"type":"string","description":"Search query."},"count":{"type":"number","description":"Result count.","minimum":1,"maximum":10},"country":{"type":"string","description":"2-letter country code."},"language":{"type":"string","description":"ISO 639-1 language."},"freshness":{"type":"string","description":"Time filter: day/week/month/year."},"date_after":{"type":"string","description":"Published after YYYY-MM-DD."},"date_before":{"type":"string","description":"Published before YYYY-MM-DD."},"search_lang":{"type":"string","description":"Brave result language."},"ui_lang":{"type":"string","description":"Brave UI locale."},"domain_filter":{"type":"array","items":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"Perplexity domain filter."},"max_tokens":{"type":"number","description":"Perplexity total token budget.","minimum":1,"maximum":1000000},"max_tokens_per_page":{"type":"number","description":"Perplexity tokens per page.","minimum":1}}}},{"name":"wecom_mcp","description":"通过 HTTP 直接调用企业微信 MCP Server。\n支持两种操作:\n - list: 列出指定品类的所有 MCP 工具\n - call: 调用指定品类的某个 MCP 工具\n\n使用方式:\n wecom_mcp list \n wecom_mcp call ''\n\n示例:\n 列出 contact 品类所有工具:wecom_mcp list contact\n 调用 contact 的 getContact:wecom_mcp call contact getContact '{}'","parameters":{"type":"object","properties":{"action":{"type":"string","enum":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"操作类型:list(列出工具)或 call(调用工具)"},"category":{"type":"string","description":"MCP 品类名称,如 doc、contact 等,对应 mcpConfig 中的 key"},"method":{"type":"string","description":"要调用的 MCP 方法名(action=call 时必填)"},"args":{"type":{"truncated":true,"reason":"trajectory-depth-limit","limitDepth":6},"description":"调用 MCP 方法的参数,可以是 JSON 字符串或对象(action=call 时使用,默认 {})"}},"required":["action","category"]}},{"name":"write","description":"Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.","parameters":{"type":"object","required":["path","content"],"properties":{"path":{"type":"string","description":"Path to the file to write (relative or absolute)"},"content":{"type":"string","description":"Content to write to the file"}}}}],"imagesCount":0,"streamStrategy":"boundary-aware:openai-completions","transport":"auto","transcriptLeafId":"0c007490"}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"prompt.submitted","ts":"2026-06-10T00:51:32.897Z","seq":4,"sourceSeq":18,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"d97d3534-b771-4943-bcec-dca60d95fb99","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"prompt":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf1fde20a0c218c220d48a04c\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:51:29 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf1fde20a0c218c220d48a04c]\nou_499a5c731212b08e951a441a2bc8a82c: 写逐字稿就行了,不要你写这个脚本了","systemPrompt":{"truncated":true,"reason":"trajectory-field-size-limit","originalChars":33651,"limitChars":32768},"messages":[{"role":"user","content":"[message_id: om_x100b6dbf5348cca8c4a375e8c70bda2]\nou_499a5c731212b08e951a441a2bc8a82c: 再写一个,人类对于龙虾的开发还不到1%。\n\n人类历史上,凡是用代码解决过的问题,龙虾都可以自动的用代码来解决,它要有代码。没有代码,他就自己写,有代码就从GitHub上找,下载完帮你搭建环境,试运行,出bug,跑,给你结果","timestamp":1781051867704},{"role":"assistant","content":[{"type":"text","text":"首长,您这是要一篇关于龙虾(自主AI编码Agent)的公众号逐字稿脚本,对吧?核心命题是:**人类对龙虾的开发还不到1%,龙虾能自动解决一切代码问题。**\n\n我先查一下相关素材,然后出脚本。"},{"type":"toolCall","id":"call00onQsEvkVXRRxFAnvEok20373","name":"web_search","arguments":{"query":"AI coding agent 自主编程 未来已来 2025 2026","count":5},"partialArgs":"{\"query\": \"AI coding agent 自主编程 未来已来 2025 2026\", \"count\": 5}"},{"type":"toolCall","id":"call01fouQj9kDBILLFnoNoxY14235","name":"web_search","arguments":{"query":"Claude coding Agent 自动写代码 GitHub 下载 搭建环境","count":5},"partialArgs":"{\"query\": \"Claude coding Agent 自动写代码 GitHub 下载 搭建环境\", \"count\": 5}"},{"type":"toolCall","id":"call02OOcRB4fsDb9VDDp8RXjX0721","name":"web_search","arguments":{"query":"AI agent 自动解决问题 编程 未来 人类开发不到1%","count":5},"partialArgs":"{\"query\": \"AI agent 自动解决问题 编程 未来 人类开发不到1%\", \"count\": 5}"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":10117,"output":247,"cacheRead":9344,"cacheWrite":0,"totalTokens":19708,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1781051868286,"responseId":"1c69b78a-c3ac-433d-9f68-6f19d8ed2ad3"},{"role":"toolResult","toolCallId":"call00onQsEvkVXRRxFAnvEok20373","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892796},{"role":"toolResult","toolCallId":"call01fouQj9kDBILLFnoNoxY14235","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892802},{"role":"toolResult","toolCallId":"call02OOcRB4fsDb9VDDp8RXjX0721","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892809},{"role":"assistant","content":[{"type":"text","text":"搜索暂时超时,不影响,您给的素材足够直接出脚本了。我按照您的意思——龙虾能自主解决一切代码问题,全部流程自动化——来写。\n\n---\n\n**脚本:龙虾不到1%**\n\n| 时长 | 画面 | 台词 |\n|------|------|------|\n| 0:00-0:05 | 黑屏白字:人类对龙虾的开发还不到1% | 人类对龙虾的开发,还不到1%。 |\n| 0:05-0:20 | 快速切换代码编辑器画面→AI自动写代码→浏览器自动测试 | 人类历史上,凡是能用代码解决的问题,龙虾都可以自动地用代码来解决。 |\n| 0:20-0:35 | 画面:GitHub搜索→自动下载→终端跑安装 | 但前提是——它得有代码。没有代码?它会自己写。有代码?它上GitHub给你搜,下载下来,开发环境帮你搭好。 |\n| 0:35-0:50 | 画面:终端自动运行→报错→自动修正→再次运行→绿pass | 然后试运行。出bug?修。再出?再修。直到跑通。整个过程不需要你动手,它就自己在那儿干活。 |\n| 0:50-1:05 | 特写:终端输出结果 | 最后——结果摆你面前。 |\n| 1:05-1:20 | 画风一转:空旷的会议室,一张椅子,一个屏幕 | 你可能会想:这跟找个程序员有啥区别?区别大了——它不吃饭、不睡觉、不抱怨需求改来改去,而且又快又便宜。 |\n| 1:20-1:40 | 蒙太奇:各种行业的人在聊天→刷卡支付→点头 | 有人说AI抢饭碗,但真正看懂的人已经在用龙虾给自己建团队了。一个人搭一个技术团队,不是梦。 |\n| 1:40-1:55 | 俯拍镜头:一本书\\一条深海鱼\\龙虾特写 | 龙虾就在那儿,深海里的资源,我们才捞了一点点。所以别急着说AI不行,先问问自己——你让龙虾帮你干过活吗? |\n| 1:55-2:00 | Logo/二维码 | 关注我,带你用龙虾降维打击。 |\n\n---\n\n**备注:**\n- 您说的\"龙虾\"在脚本里保持原词,不做替换,这本身就是你的IP标签\n- 整体节奏偏快、有画面感,符合短视频逐字稿要求\n- 如需调整口吻(更激进/更温和)、增减时长,或者改为文章版,随时说"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":354,"output":558,"cacheRead":19456,"cacheWrite":0,"totalTokens":20368,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1781051892824,"responseId":"a4968589-9901-4e20-8ba2-a5d22e6f4ebb"},{"role":"user","content":"[message_id: om_x100b6dbf0f2874a8c0af9bf55a6a9ad]\nou_499a5c731212b08e951a441a2bc8a82c: 还写逐字稿,重新写一下","timestamp":1781052449024},{"role":"assistant","content":[{"type":"text","text":"好的首长,重新写一版,这次节奏更硬、更大白话,去掉花哨的画面描述,聚焦龙虾的核心能力。\n\n---\n\n**脚本:龙虾不到1%(第二版)**\n\n| 时长 | 台词 |\n|------|------|\n| 0:00-0:08 | 人类对龙虾的开发,还不到1%。你把AI想得太简单了。 |\n| 0:08-0:20 | 人类历史上所有能用代码解决的问题,龙虾都能自动用代码解决。注意啊,是自动。不是你去问它,它给你写一段代码你自己粘贴。 |\n| 0:20-0:35 | 是它自己写代码,自己搭建环境,自己运行。没有代码?它现写。有现成的?它上GitHub给你搜,下下来,安装好。 |\n| 0:35-0:50 | 然后试运行。跑不通是吧?报错了是吧?自己修,修完再跑,跑到通为止。全程你不用敲一行命令。 |\n| 0:50-1:05 | 最后结果给你,干干净净。你只管验收它干完了没。 |\n| 1:05-1:20 | 有人说程序员要失业了,这事我不评价。但如果你是一个创业者、小老板、甚至只是有个想法的人,你以前需要雇一个开发团队,现在你只需要一个龙虾。 |\n| 1:20-1:35 | 不吃饭不睡觉不下班不提离职,还贼便宜。这玩意儿你放着不用? |\n| 1:35-1:50 | 龙虾这个东西,说真的就跟90年代的互联网一样,那时候没人觉得这玩意能改变世界。现在呢? |\n| 1:50-2:00 | 别等了,动手让龙虾干活去。 |\n\n---\n\n**改版说明:**\n- 去掉了画面描述,只剩台词,更短视频风格\n- 每段卡在15秒左右,方便剪辑\n- 口气更直接,带点\"你还不懂\"的味道\n- 核心逻辑链条:能力描述→流程展示→对创业者的价值→号召行动\n\n要发还是调?"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":7123,"output":453,"cacheRead":13312,"cacheWrite":0,"totalTokens":20888,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1781052449792,"responseId":"76925081-8884-4fbd-a0d4-6d94c69236b7"}],"imagesCount":0}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"model.completed","ts":"2026-06-10T00:51:37.106Z","seq":5,"sourceSeq":19,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"d97d3534-b771-4943-bcec-dca60d95fb99","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false,"promptErrorSource":null,"usage":{"input":1879,"output":265,"cacheRead":19072,"total":21216},"promptCache":{"lastCallUsage":{"input":1879,"output":265,"cacheRead":19072,"cacheWrite":0,"total":21216},"lastCacheTouchAt":1781052692922},"compactionCount":0,"assistantTexts":["明白,只要纯逐字稿,不要台本、不要画面标注、不要时长。\n\n---\n\n**龙虾不到1%(逐字稿)**\n\n人类对龙虾的开发还不到1%。\n\n说真的,你把AI想得太简单了。不是那个陪你聊天的AI,是能替你干活的龙虾。\n\n人类历史上所有能用代码解决的问题,龙虾都能自动用代码解决。注意啊,不是你去问它,它给你写一段代码你自己粘贴。不是这样的。\n\n是它自己写代码,自己搭环境,自己运行。\n\n没有代码?它自己写。有现成的?它上GitHub给你搜,下载下来,依赖装好。\n\n然后试运行。\n\n跑不通?报错了?自己修。修完再跑,跑到通为止。全程你不用敲一行命令,你就坐在那儿看它干活。\n\n最后结果摆你面前,清清爽爽。你只管验收。\n\n有人说程序员要失业了,这事我不评价。但如果你是个创业者,是个小老板,或者你只是有个想法手里没技术,你以前要雇一个团队才能干的事,现在一个龙虾就够了。\n\n不吃饭不睡觉不下班不提离职,还便宜到离谱。\n\n这玩意儿你放着不用?龙虾能做的事,你才开发了不到1%。\n\n别等了。去试试,让它干活。"],"finalPromptText":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf1fde20a0c218c220d48a04c\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:51:29 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf1fde20a0c218c220d48a04c]\nou_499a5c731212b08e951a441a2bc8a82c: 写逐字稿就行了,不要你写这个脚本了","messagesSnapshot":[{"role":"user","content":"[message_id: om_x100b6dbf5348cca8c4a375e8c70bda2]\nou_499a5c731212b08e951a441a2bc8a82c: 再写一个,人类对于龙虾的开发还不到1%。\n\n人类历史上,凡是用代码解决过的问题,龙虾都可以自动的用代码来解决,它要有代码。没有代码,他就自己写,有代码就从GitHub上找,下载完帮你搭建环境,试运行,出bug,跑,给你结果","timestamp":1781051867704},{"role":"assistant","content":[{"type":"text","text":"首长,您这是要一篇关于龙虾(自主AI编码Agent)的公众号逐字稿脚本,对吧?核心命题是:**人类对龙虾的开发还不到1%,龙虾能自动解决一切代码问题。**\n\n我先查一下相关素材,然后出脚本。"},{"type":"toolCall","id":"call00onQsEvkVXRRxFAnvEok20373","name":"web_search","arguments":{"query":"AI coding agent 自主编程 未来已来 2025 2026","count":5},"partialArgs":"{\"query\": \"AI coding agent 自主编程 未来已来 2025 2026\", \"count\": 5}"},{"type":"toolCall","id":"call01fouQj9kDBILLFnoNoxY14235","name":"web_search","arguments":{"query":"Claude coding Agent 自动写代码 GitHub 下载 搭建环境","count":5},"partialArgs":"{\"query\": \"Claude coding Agent 自动写代码 GitHub 下载 搭建环境\", \"count\": 5}"},{"type":"toolCall","id":"call02OOcRB4fsDb9VDDp8RXjX0721","name":"web_search","arguments":{"query":"AI agent 自动解决问题 编程 未来 人类开发不到1%","count":5},"partialArgs":"{\"query\": \"AI agent 自动解决问题 编程 未来 人类开发不到1%\", \"count\": 5}"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":10117,"output":247,"cacheRead":9344,"cacheWrite":0,"totalTokens":19708,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"toolUse","timestamp":1781051868286,"responseId":"1c69b78a-c3ac-433d-9f68-6f19d8ed2ad3"},{"role":"toolResult","toolCallId":"call00onQsEvkVXRRxFAnvEok20373","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892796},{"role":"toolResult","toolCallId":"call01fouQj9kDBILLFnoNoxY14235","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892802},{"role":"toolResult","toolCallId":"call02OOcRB4fsDb9VDDp8RXjX0721","toolName":"web_search","content":[{"type":"text","text":"{\n \"status\": \"error\",\n \"tool\": \"web_search\",\n \"error\": \"request timed out\"\n}"}],"isError":true,"timestamp":1781051892809},{"role":"assistant","content":[{"type":"text","text":"搜索暂时超时,不影响,您给的素材足够直接出脚本了。我按照您的意思——龙虾能自主解决一切代码问题,全部流程自动化——来写。\n\n---\n\n**脚本:龙虾不到1%**\n\n| 时长 | 画面 | 台词 |\n|------|------|------|\n| 0:00-0:05 | 黑屏白字:人类对龙虾的开发还不到1% | 人类对龙虾的开发,还不到1%。 |\n| 0:05-0:20 | 快速切换代码编辑器画面→AI自动写代码→浏览器自动测试 | 人类历史上,凡是能用代码解决的问题,龙虾都可以自动地用代码来解决。 |\n| 0:20-0:35 | 画面:GitHub搜索→自动下载→终端跑安装 | 但前提是——它得有代码。没有代码?它会自己写。有代码?它上GitHub给你搜,下载下来,开发环境帮你搭好。 |\n| 0:35-0:50 | 画面:终端自动运行→报错→自动修正→再次运行→绿pass | 然后试运行。出bug?修。再出?再修。直到跑通。整个过程不需要你动手,它就自己在那儿干活。 |\n| 0:50-1:05 | 特写:终端输出结果 | 最后——结果摆你面前。 |\n| 1:05-1:20 | 画风一转:空旷的会议室,一张椅子,一个屏幕 | 你可能会想:这跟找个程序员有啥区别?区别大了——它不吃饭、不睡觉、不抱怨需求改来改去,而且又快又便宜。 |\n| 1:20-1:40 | 蒙太奇:各种行业的人在聊天→刷卡支付→点头 | 有人说AI抢饭碗,但真正看懂的人已经在用龙虾给自己建团队了。一个人搭一个技术团队,不是梦。 |\n| 1:40-1:55 | 俯拍镜头:一本书\\一条深海鱼\\龙虾特写 | 龙虾就在那儿,深海里的资源,我们才捞了一点点。所以别急着说AI不行,先问问自己——你让龙虾帮你干过活吗? |\n| 1:55-2:00 | Logo/二维码 | 关注我,带你用龙虾降维打击。 |\n\n---\n\n**备注:**\n- 您说的\"龙虾\"在脚本里保持原词,不做替换,这本身就是你的IP标签\n- 整体节奏偏快、有画面感,符合短视频逐字稿要求\n- 如需调整口吻(更激进/更温和)、增减时长,或者改为文章版,随时说"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":354,"output":558,"cacheRead":19456,"cacheWrite":0,"totalTokens":20368,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1781051892824,"responseId":"a4968589-9901-4e20-8ba2-a5d22e6f4ebb"},{"role":"user","content":"[message_id: om_x100b6dbf0f2874a8c0af9bf55a6a9ad]\nou_499a5c731212b08e951a441a2bc8a82c: 还写逐字稿,重新写一下","timestamp":1781052449024},{"role":"assistant","content":[{"type":"text","text":"好的首长,重新写一版,这次节奏更硬、更大白话,去掉花哨的画面描述,聚焦龙虾的核心能力。\n\n---\n\n**脚本:龙虾不到1%(第二版)**\n\n| 时长 | 台词 |\n|------|------|\n| 0:00-0:08 | 人类对龙虾的开发,还不到1%。你把AI想得太简单了。 |\n| 0:08-0:20 | 人类历史上所有能用代码解决的问题,龙虾都能自动用代码解决。注意啊,是自动。不是你去问它,它给你写一段代码你自己粘贴。 |\n| 0:20-0:35 | 是它自己写代码,自己搭建环境,自己运行。没有代码?它现写。有现成的?它上GitHub给你搜,下下来,安装好。 |\n| 0:35-0:50 | 然后试运行。跑不通是吧?报错了是吧?自己修,修完再跑,跑到通为止。全程你不用敲一行命令。 |\n| 0:50-1:05 | 最后结果给你,干干净净。你只管验收它干完了没。 |\n| 1:05-1:20 | 有人说程序员要失业了,这事我不评价。但如果你是一个创业者、小老板、甚至只是有个想法的人,你以前需要雇一个开发团队,现在你只需要一个龙虾。 |\n| 1:20-1:35 | 不吃饭不睡觉不下班不提离职,还贼便宜。这玩意儿你放着不用? |\n| 1:35-1:50 | 龙虾这个东西,说真的就跟90年代的互联网一样,那时候没人觉得这玩意能改变世界。现在呢? |\n| 1:50-2:00 | 别等了,动手让龙虾干活去。 |\n\n---\n\n**改版说明:**\n- 去掉了画面描述,只剩台词,更短视频风格\n- 每段卡在15秒左右,方便剪辑\n- 口气更直接,带点\"你还不懂\"的味道\n- 核心逻辑链条:能力描述→流程展示→对创业者的价值→号召行动\n\n要发还是调?"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":7123,"output":453,"cacheRead":13312,"cacheWrite":0,"totalTokens":20888,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1781052449792,"responseId":"76925081-8884-4fbd-a0d4-6d94c69236b7"},{"role":"user","content":[{"type":"text","text":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf1fde20a0c218c220d48a04c\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:51:29 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf1fde20a0c218c220d48a04c]\nou_499a5c731212b08e951a441a2bc8a82c: 写逐字稿就行了,不要你写这个脚本了"}],"timestamp":1781052692901},{"role":"assistant","content":[{"type":"text","text":"明白,只要纯逐字稿,不要台本、不要画面标注、不要时长。\n\n---\n\n**龙虾不到1%(逐字稿)**\n\n人类对龙虾的开发还不到1%。\n\n说真的,你把AI想得太简单了。不是那个陪你聊天的AI,是能替你干活的龙虾。\n\n人类历史上所有能用代码解决的问题,龙虾都能自动用代码解决。注意啊,不是你去问它,它给你写一段代码你自己粘贴。不是这样的。\n\n是它自己写代码,自己搭环境,自己运行。\n\n没有代码?它自己写。有现成的?它上GitHub给你搜,下载下来,依赖装好。\n\n然后试运行。\n\n跑不通?报错了?自己修。修完再跑,跑到通为止。全程你不用敲一行命令,你就坐在那儿看它干活。\n\n最后结果摆你面前,清清爽爽。你只管验收。\n\n有人说程序员要失业了,这事我不评价。但如果你是个创业者,是个小老板,或者你只是有个想法手里没技术,你以前要雇一个团队才能干的事,现在一个龙虾就够了。\n\n不吃饭不睡觉不下班不提离职,还便宜到离谱。\n\n这玩意儿你放着不用?龙虾能做的事,你才开发了不到1%。\n\n别等了。去试试,让它干活。"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-chat","usage":{"input":1879,"output":265,"cacheRead":19072,"cacheWrite":0,"totalTokens":21216,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1781052692922,"responseId":"511635dd-5572-4adc-9aa3-0c4a7eb56df5"}]}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"trace.artifacts","ts":"2026-06-10T00:51:37.107Z","seq":6,"sourceSeq":20,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"d97d3534-b771-4943-bcec-dca60d95fb99","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"capturedAt":"2026-06-10T00:51:37.107Z","finalStatus":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false,"promptErrorSource":null,"usage":{"input":1879,"output":265,"cacheRead":19072,"total":21216},"promptCache":{"lastCallUsage":{"input":1879,"output":265,"cacheRead":19072,"cacheWrite":0,"total":21216},"lastCacheTouchAt":1781052692922},"compactionCount":0,"assistantTexts":["明白,只要纯逐字稿,不要台本、不要画面标注、不要时长。\n\n---\n\n**龙虾不到1%(逐字稿)**\n\n人类对龙虾的开发还不到1%。\n\n说真的,你把AI想得太简单了。不是那个陪你聊天的AI,是能替你干活的龙虾。\n\n人类历史上所有能用代码解决的问题,龙虾都能自动用代码解决。注意啊,不是你去问它,它给你写一段代码你自己粘贴。不是这样的。\n\n是它自己写代码,自己搭环境,自己运行。\n\n没有代码?它自己写。有现成的?它上GitHub给你搜,下载下来,依赖装好。\n\n然后试运行。\n\n跑不通?报错了?自己修。修完再跑,跑到通为止。全程你不用敲一行命令,你就坐在那儿看它干活。\n\n最后结果摆你面前,清清爽爽。你只管验收。\n\n有人说程序员要失业了,这事我不评价。但如果你是个创业者,是个小老板,或者你只是有个想法手里没技术,你以前要雇一个团队才能干的事,现在一个龙虾就够了。\n\n不吃饭不睡觉不下班不提离职,还便宜到离谱。\n\n这玩意儿你放着不用?龙虾能做的事,你才开发了不到1%。\n\n别等了。去试试,让它干活。"],"finalPromptText":"Conversation info (untrusted metadata):\n```json\n{\n \"chat_id\": \"user:ou_499a5c731212b08e951a441a2bc8a82c\",\n \"message_id\": \"om_x100b6dbf1fde20a0c218c220d48a04c\",\n \"sender_id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"sender\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"timestamp\": \"Wed 2026-06-10 08:51:29 GMT+8\",\n \"inbound_event_kind\": \"user_request\"\n}\n```\n\nSender (untrusted metadata):\n```json\n{\n \"label\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"id\": \"ou_499a5c731212b08e951a441a2bc8a82c\",\n \"name\": \"ou_499a5c731212b08e951a441a2bc8a82c\"\n}\n```\n\n[message_id: om_x100b6dbf1fde20a0c218c220d48a04c]\nou_499a5c731212b08e951a441a2bc8a82c: 写逐字稿就行了,不要你写这个脚本了","itemLifecycle":{"startedCount":0,"completedCount":0,"activeCount":0},"toolMetas":[],"didSendViaMessagingTool":false,"successfulCronAdds":0,"messagingToolSentTexts":[],"messagingToolSentMediaUrls":[],"messagingToolSentTargets":[]}} {"traceSchema":"openclaw-trajectory","schemaVersion":1,"traceId":"7610e75e-f720-46e1-9564-1c959b18830a","source":"runtime","type":"session.ended","ts":"2026-06-10T00:51:37.107Z","seq":7,"sourceSeq":21,"sessionId":"7610e75e-f720-46e1-9564-1c959b18830a","sessionKey":"agent:101:feishu:direct:ou_499a5c731212b08e951a441a2bc8a82c","runId":"d97d3534-b771-4943-bcec-dca60d95fb99","workspaceDir":"/root/.openclaw/agents/101/workspace","provider":"deepseek","modelId":"deepseek-chat","modelApi":"openai-completions","data":{"status":"success","aborted":false,"externalAbort":false,"timedOut":false,"idleTimedOut":false,"timedOutDuringCompaction":false,"timedOutDuringToolExecution":false}}