[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M698QRVD3VZH10Z0F701JRGW":3,"skill-same:01M698QRVD3VZH10Z0F701JRGW":76},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":52,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M698QRVD3VZH10Z0F701JRGW","openclaw-debugging",null,"Debug OpenClaw model\u002Fprovider\u002Ftool-surface\u002Fcode-mode\u002Fstreaming and live\u002FCrabbox behavior; choose logs, probes, proof path before code changes; fetch stored sessions, transcripts, attachments as evidence.","openclaw\u002Fopenclaw","openclaw","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252820863?v=4","01M698P3FSAZ6B4R928ZF19KPT","01M698PDMDRVH56MV30D253NFP",394452,"MIT","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fopenclaw-debugging\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[9,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"openclaw debugging","debugging","changes","crabbox","mode","as","provider","evidence","fetch","behavior","choose","model","tool","attachments","logs","streaming","code","debug","sessions","2026-11-10 10:12:30",false,"---\nname: openclaw-debugging\ndescription: Debug OpenClaw model\u002Fprovider\u002Ftool-surface\u002Fcode-mode\u002Fstreaming and live\u002FCrabbox behavior; choose logs, probes, proof path before code changes; fetch stored sessions, transcripts, attachments as evidence.\n---\n\n# OpenClaw Debugging\n\nBehavior differs between local tests, live models, providers, code mode, Tool\nSearch, Crabbox, CI: get debug signal before guessing.\n\n## Read First\n\n- `docs\u002Flogging.md`: log files, `openclaw logs`, targeted debug flags.\n- `docs\u002Freference\u002Ftest.md`: local test commands.\n- `docs\u002Ftools\u002Fcode-mode.md`: code-mode exec\u002Fwait + tool catalog rules.\n- `$openclaw-testing`: test-lane choice.\n- `$crabbox`: broad, Docker, package, Linux, live-key, CI-parity proof.\n\n## Default Loop\n\n1. State suspected boundary: config, tool construction, provider payload, fetch,\n   stream\u002FSSE, transcript replay, worker\u002Fruntime, package\u002Fdist, CI.\n2. Add\u002Fenable narrowest signal proving boundary.\n3. Reproduce with same provider\u002Fmodel\u002Fconfig. Never randomly switch models\n   unless model itself = tested variable.\n4. Compare configured state with actual run activation.\n5. Patch root cause.\n6. Rerun exact failing probe; broaden only if contract requires.\n\n## Model Transport Logs\n\nModel request shape\u002Fstream timing: targeted env flags over global debug:\n\n```bash\nOPENCLAW_DEBUG_MODEL_TRANSPORT=1 openclaw gateway\nOPENCLAW_DEBUG_MODEL_PAYLOAD=tools OPENCLAW_DEBUG_SSE=events openclaw gateway\nOPENCLAW_DEBUG_MODEL_PAYLOAD=full-redacted OPENCLAW_DEBUG_SSE=peek openclaw gateway\n```\n\nUseful flags:\n\n- `OPENCLAW_DEBUG_MODEL_TRANSPORT=1`: request start, fetch response, SDK\n  headers, first SSE event, stream done, transport errors at `info`.\n- `OPENCLAW_DEBUG_MODEL_PAYLOAD=summary`: bounded payload summary.\n- `OPENCLAW_DEBUG_MODEL_PAYLOAD=tools`: all model-facing tool names.\n- `OPENCLAW_DEBUG_MODEL_PAYLOAD=full-redacted`: capped, redacted JSON payload.\n  Only while debugging; prompts\u002Fmessage text may still appear.\n- `OPENCLAW_DEBUG_SSE=events`: first-event + stream-completion timing.\n- `OPENCLAW_DEBUG_SSE=peek`: first five redacted SSE events.\n- `OPENCLAW_DEBUG_CODE_MODE=1`: code-mode tool-surface diagnostics.\n\nWatch logs:\n\n```bash\nopenclaw logs --follow\n```\n\n## Common Boundaries\n\n- **Config vs activation:** enabled config can coexist with disabled run tools,\n  raw run, empty allowlist, missing model tool support. Check actual visible\n  tools before enforcing provider payload invariants.\n- **Tool surface:** inspect final model-visible tool names, not only registry\u002F\n  config. Code mode = exactly `exec` + `wait` only after actual activation.\n- **Provider payload:** before SDK call, log fields, model id, service tier,\n  reasoning, input size, metadata keys, prompt-cache key presence, tool names.\n- **Fetch vs SSE:** fetch response proves HTTP headers arrived; first SSE event\n  proves provider body progress. Gap here = stream\u002Fbody\u002Fprovider issue, not\n  tool execution.\n- **Worker\u002Fdist:** touching workers, dynamic imports, package exports, lazy\n  runtime boundaries, published paths → `pnpm build`.\n- **Live keys:** missing provider keys → configured secret workflow before\n  declaring live proof blocked. Env checks presence-only; never print secrets.\n\n## Fetching Sessions and Transcripts\n\nChat-session bug report: fetch actual transcript, sender attribution,\nattachments as evidence.\n\nCLI first (needs configured install; safe against live gateway):\n\n```bash\nopenclaw sessions list --agent \u003CagentId> --json\nopenclaw sessions tail\nopenclaw sessions export-trajectory\n```\n\nDocs: store layout `docs\u002Freference\u002Fdatabase-schemas.md`;\nCLI https:\u002F\u002Fdocs.openclaw.ai\u002Fcli\u002Fsessions.\n\nRaw store: CLI unavailable (e.g. remote host over SSH) or event-level detail needed:\n\n- Per-agent data plane: `~\u002F.openclaw\u002Fagents\u002F\u003CagentId>\u002Fagent\u002Fopenclaw-agent.sqlite`.\n  Canonical schema: `src\u002Fstate\u002Fopenclaw-agent-schema.sql`.\n- Hosted\u002Fsystemd state: service user's home (e.g. `\u002Fhome\u002Fopenclaw\u002F.openclaw\u002F...`),\n  not root's. Root may have separate stray install with different agents.\n  Expected agent dir missing: locate real DB with\n  `find \u002F -maxdepth 6 -name openclaw-agent.sqlite`.\n- Web chat URL session-id fragment: `\u002Fchat\u002F\u003CagentId>\u002F\u003Cslug>-\u003Chex>`.\n  Resolve in `session_nodes`: `session_key LIKE '%\u003Chex>%'` →\n  `current_session_id`, `display_name`. Key shape:\n  `agent:\u003CagentId>:\u003Csurface>:\u003Cuuid>`; subagent sessions use surface `subagent`.\n- Transcript: `transcript_events` (`session_id`, `seq`, `event_json`).\n  `event_json.message`: `role` (`user`\u002F`assistant`\u002F`toolResult`) +\n  `content` (string or parts of type `text`\u002F`toolCall`\u002F`image`).\n- Sender provenance: real user messages carry `message.__openclaw`\n  (`senderId`, `senderName`, `senderIsOwner`); runtime-synthesized inputs do not.\n  Distinguish operator-authored text from injected prompts with this.\n- Full-text transcript search: `session_transcript_fts`.\n- Attachments: `media:\u002F\u002Finbound\u002F\u003Cfile>` URLs → `\u003Cstate-dir>\u002Fmedia\u002Finbound\u002F\u003Cfile>`.\n- User-attached images ≠ `image` content parts. Message envelope carries\n  `message.__openclaw.media[]` entries: `url` (`media:\u002F\u002Finbound\u002F\u003Cfile>`),\n  `contentType`, `kind`, `fileName`. Parts-only extractor misses every image;\n  grep raw `event_json` for `media:\u002F\u002F`. Remote host: scp files locally\n  (one remote path per scp argument); read there.\n\nHosts without `sqlite3` binary still have Node: `node:sqlite` needs no dependencies.\n\n```bash\nnode -e 'const {DatabaseSync}=require(\"node:sqlite\");\nconst db=new DatabaseSync(process.argv[1],{readOnly:true});\nconsole.log(JSON.stringify(db.prepare(\n  \"SELECT seq,event_json FROM transcript_events WHERE session_id=? ORDER BY seq\"\n).all(process.argv[2])))' \u003Cdb-path> \u003Csession-id>\n```\n\n- Always open live stores `readOnly: true`; never write running gateway's state\n  (root `AGENTS.md` Validation rules).\n- Realistic-data work: copy DB into dev state dir first.\n\n## Code Pointers\n\n- Model payload + Responses stream:\n  `src\u002Fagents\u002Fopenai-transport-stream.ts`\n- Guarded fetch\u002Ftiming:\n  `src\u002Fagents\u002Fprovider-transport-fetch.ts`\n- OpenAI\u002FCodex provider wrappers:\n  `src\u002Fllm\u002Fproviders\u002Fstream-wrappers\u002Fopenai.ts`\n- Tool construction, Tool Search, code-mode activation:\n  `src\u002Fagents\u002Fembedded-agent-runner\u002Frun\u002Fattempt.ts`\n- Code-mode runtime and worker:\n  `src\u002Fagents\u002Fcode-mode.ts`\n  `src\u002Fagents\u002Fcode-mode.worker.ts`\n- Tool Search catalog:\n  `src\u002Fagents\u002Ftool-search.ts`\n\n## Proof Choice\n\n- Single helper\u002Fpayload bug: local targeted Vitest.\n- Docs\u002Flogging-only: `pnpm check:docs` + `git diff --check`.\n- Worker\u002Fdist\u002Flazy import\u002Fpackage surface: targeted tests + `pnpm build`.\n- Live provider\u002Fmodel behavior: same provider\u002Fmodel, debug flags, real key if available.\n- Docker\u002Fpackage\u002FLinux\u002FCI-parity: current dedicated Linux worker when capable;\n  otherwise `$crabbox`.\n- CI failure: exact SHA, relevant job only; logs only after failure\u002Fcompletion.\n\n## Output Habit\n\nReport:\n\n- boundary tested\n- exact command\u002Fenv shape, redacted\n- observed signal, e.g. tool names or first SSE event timing\n- fix location\n- narrow proof + remaining risk\n","# OpenClaw Debugging\n\nBehavior differs between local tests, live models, providers, code mode, Tool\nSearch, Crabbox, CI: get debug signal before guessing.\n\n## Read First\n\n- `docs\u002Flogging.md`: log files, `openclaw logs`, targeted debug flags.\n- `docs\u002Freference\u002Ftest.md`: local test commands.\n- `docs\u002Ftools\u002Fcode-mode.md`: code-mode exec\u002Fwait + tool catalog rules.\n- `$openclaw-testing`: test-lane choice.\n- `$crabbox`: broad, Docker, package, Linux, live-key, CI-parity proof.\n\n## Default Loop\n\n1. State suspected boundary: config, tool construction, provider payload, fetch,\n   stream\u002FSSE, transcript replay, worker\u002Fruntime, package\u002Fdist, CI.\n2. Add\u002Fenable narrowest signal proving boundary.\n3. Reproduce with same provider\u002Fmodel\u002Fconfig. Never randomly switch models\n   unless model itself = tested variable.\n4. Compare configured state with actual run activation.\n5. Patch root cause.\n6. Rerun exact failing probe; broaden only if contract requires.\n\n## Model Transport Logs\n\nModel request shape\u002Fstream timing: targeted env flags over global debug:\n\n```bash\nOPENCLAW_DEBUG_MODEL_TRANSPORT=1 openclaw gateway\nOPENCLAW_DEBUG_MODEL_PAYLOAD=tools OPENCLAW_DEBUG_SSE=events openclaw gateway\nOPENCLAW_DEBUG_MODEL_PAYLOAD=full-redacted OPENCLAW_DEBUG_SSE=peek openclaw gateway\n```\n\nUseful flags:\n\n- `OPENCLAW_DEBUG_MODEL_TRANSPORT=1`: request start, fetch response, SDK\n  headers, first SSE event, stream done, transport errors at `info`.\n- `OPENCLAW_DEBUG_MODEL_PAYLOAD=summary`: bounded payload summary.\n- `OPENCLAW_DEBUG_MODEL_PAYLOAD=tools`: all model-facing tool names.\n- `OPENCLAW_DEBUG_MODEL_PAYLOAD=full-redacted`: capped, redacted JSON payload.\n  Only while debugging; prompts\u002Fmessage text may still appear.\n- `OPENCLAW_DEBUG_SSE=events`: first-event + stream-completion timing.\n- `OPENCLAW_DEBUG_SSE=peek`: first five redacted SSE events.\n- `OPENCLAW_DEBUG_CODE_MODE=1`: code-mode tool-surface diagnostics.\n\nWatch logs:\n\n```bash\nopenclaw logs --follow\n```\n\n## Common Boundaries\n\n- **Config vs activation:** enabled config can coexist with disabled run tools,\n  raw run, empty allowlist, missing model tool support. Check actual visible\n  tools before enforcing provider payload invariants.\n- **Tool surface:** inspect final model-visible tool names, not only registry\u002F\n  config. Code mode = exactly `exec` + `wait` only after actual activation.\n- **Provider payload:** before SDK call, log fields, model id, service tier,\n  reasoning, input size, metadata keys, prompt-cache key presence, tool names.\n- **Fetch vs SSE:** fetch response proves HTTP headers arrived; first SSE event\n  proves provider body progress. Gap here = stream\u002Fbody\u002Fprovider issue, not\n  tool execution.\n- **Worker\u002Fdist:** touching workers, dynamic imports, package exports, lazy\n  runtime boundaries, published paths → `pnpm build`.\n- **Live keys:** missing provider keys → configured secret workflow before\n  declaring live proof blocked. Env checks presence-only; never print secrets.\n\n## Fetching Sessions and Transcripts\n\nChat-session bug report: fetch actual transcript, sender attribution,\nattachments as evidence.\n\nCLI first (needs configured install; safe against live gateway):\n\n```bash\nopenclaw sessions list --agent \u003CagentId> --json\nopenclaw sessions tail\nopenclaw sessions export-trajectory\n```\n\nDocs: store layout `docs\u002Freference\u002Fdatabase-schemas.md`;\nCLI https:\u002F\u002Fdocs.openclaw.ai\u002Fcli\u002Fsessions.\n\nRaw store: CLI unavailable (e.g. remote host over SSH) or event-level detail needed:\n\n- Per-agent data plane: `~\u002F.openclaw\u002Fagents\u002F\u003CagentId>\u002Fagent\u002Fopenclaw-agent.sqlite`.\n  Canonical schema: `src\u002Fstate\u002Fopenclaw-agent-schema.sql`.\n- Hosted\u002Fsystemd state: service user's home (e.g. `\u002Fhome\u002Fopenclaw\u002F.openclaw\u002F...`),\n  not root's. Root may have separate stray install with different agents.\n  Expected agent dir missing: locate real DB with\n  `find \u002F -maxdepth 6 -name openclaw-agent.sqlite`.\n- Web chat URL session-id fragment: `\u002Fchat\u002F\u003CagentId>\u002F\u003Cslug>-\u003Chex>`.\n  Resolve in `session_nodes`: `session_key LIKE '%\u003Chex>%'` →\n  `current_session_id`, `display_name`. Key shape:\n  `agent:\u003CagentId>:\u003Csurface>:\u003Cuuid>`; subagent sessions use surface `subagent`.\n- Transcript: `transcript_events` (`session_id`, `seq`, `event_json`).\n  `event_json.message`: `role` (`user`\u002F`assistant`\u002F`toolResult`) +\n  `content` (string or parts of type `text`\u002F`toolCall`\u002F`image`).\n- Sender provenance: real user messages carry `message.__openclaw`\n  (`senderId`, `senderName`, `senderIsOwner`); runtime-synthesized inputs do not.\n  Distinguish operator-authored text from injected prompts with this.\n- Full-text transcript search: `session_transcript_fts`.\n- Attachments: `media:\u002F\u002Finbound\u002F\u003Cfile>` URLs → `\u003Cstate-dir>\u002Fmedia\u002Finbound\u002F\u003Cfile>`.\n- User-attached images ≠ `image` content parts. Message envelope carries\n  `message.__openclaw.media[]` entries: `url` (`media:\u002F\u002Finbound\u002F\u003Cfile>`),\n  `contentType`, `kind`, `fileName`. Parts-only extractor misses every image;\n  grep raw `event_json` for `media:\u002F\u002F`. Remote host: scp files locally\n  (one remote path per scp argument); read there.\n\nHosts without `sqlite3` binary still have Node: `node:sqlite` needs no dependencies.\n\n```bash\nnode -e 'const {DatabaseSync}=require(\"node:sqlite\");\nconst db=new DatabaseSync(process.argv[1],{readOnly:true});\nconsole.log(JSON.stringify(db.prepare(\n  \"SELECT seq,event_json FROM transcript_events WHERE session_id=? ORDER BY seq\"\n).all(process.argv[2])))' \u003Cdb-path> \u003Csession-id>\n```\n\n- Always open live stores `readOnly: true`; never write running gateway's state\n  (root `AGENTS.md` Validation rules).\n- Realistic-data work: copy DB into dev state dir first.\n\n## Code Pointers\n\n- Model payload + Responses stream:\n  `src\u002Fagents\u002Fopenai-transport-stream.ts`\n- Guarded fetch\u002Ftiming:\n  `src\u002Fagents\u002Fprovider-transport-fetch.ts`\n- OpenAI\u002FCodex provider wrappers:\n  `src\u002Fllm\u002Fproviders\u002Fstream-wrappers\u002Fopenai.ts`\n- Tool construction, Tool Search, code-mode activation:\n  `src\u002Fagents\u002Fembedded-agent-runner\u002Frun\u002Fattempt.ts`\n- Code-mode runtime and worker:\n  `src\u002Fagents\u002Fcode-mode.ts`\n  `src\u002Fagents\u002Fcode-mode.worker.ts`\n- Tool Search catalog:\n  `src\u002Fagents\u002Ftool-search.ts`\n\n## Proof Choice\n\n- Single helper\u002Fpayload bug: local targeted Vitest.\n- Docs\u002Flogging-only: `pnpm check:docs` + `git diff --check`.\n- Worker\u002Fdist\u002Flazy import\u002Fpackage surface: targeted tests + `pnpm build`.\n- Live provider\u002Fmodel behavior: same provider\u002Fmodel, debug flags, real key if available.\n- Docker\u002Fpackage\u002FLinux\u002FCI-parity: current dedicated Linux worker when capable;\n  otherwise `$crabbox`.\n- CI failure: exact SHA, relevant job only; logs only after failure\u002Fcompletion.\n\n## Output Habit\n\nReport:\n\n- boundary tested\n- exact command\u002Fenv shape, redacted\n- observed signal, e.g. tool names or first SSE event timing\n- fix location\n- narrow proof + remaining risk\n",{"name":5,"description":7},"main","f1c93577085244aa96aa87b53a2df9b59d293bd7",".agents\u002Fskills\u002Fopenclaw-debugging",82888,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw","https:\u002F\u002Fopenclaw.ai","https:\u002F\u002Fgithub.com\u002Fopenclaw","Your personal, open source AI assistant.","2026-11-15 03:04:02",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add openclaw\u002Fopenclaw --skill openclaw-debugging",{"tool":62,"command":63},"bunx","bunx skills add openclaw\u002Fopenclaw --skill openclaw-debugging",{"tool":65,"command":66},"pnpm","pnpm dlx skills add openclaw\u002Fopenclaw --skill openclaw-debugging","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fopenclaw-debugging\u002FSKILL.md",true,[70],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"agents\u002Fopenai.yaml","REFERENCE","参考文档",279,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fopenclaw-debugging\u002Fagents\u002Fopenai.yaml",[77,83,106,123,142,164],{"skillNo":78,"name":79,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":42},"01M698VP84FNM6G9MR1HPX7MF7","lobster","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Flobster\u002FSKILL.md",[],[79],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":42},"01M698YY8QGQ7S8TJNKJG6VTPH","xurl","xurl CLI for authenticated X posts, replies, reads\u002Fsearch, DMs, media upload, followers, auth status, or raw v2 API calls.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fskills\u002Fxurl\u002FSKILL.md",[],[85,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105],"for","api","calls","replies","posts","upload","tap","install","brew","node","Media","search","npm","status","auth","cli",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":42},"01M698YWT1CJ0WK88WB909R9RT","weather","Current weather and forecasts with web_fetch, falling back to wttr.in curl for locations, rain, temperature, travel planning.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fskills\u002Fweather\u002FSKILL.md",[],[108,113,114,97,31,98,115,116,117,118,119,120,90,121,122],"travel planning","travel","curl","https","help","planning","web","back","temperature","with",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":132,"publishedAt":42},"01M698YV2Q0R0JJKAWGFS21K0N","visualize","Create inline visuals for code and explanations, or author persistent OpenClaw dashboard widgets with show_widget.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fskills\u002Fvisualize\u002FSKILL.md",[129],{"categoryNo":130,"categoryName":131,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000033","数据分析师",[125,133,134,135,136,90,122,137,39,138,139,140,9,141],"widgets","openclaw dashboard","author","inline","show","create","visuals","dashboard","widget",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":154,"publishedAt":42},"01M698YS2TRJH9ENG28HD9CD87","trello","Manage Trello boards, lists, and cards via the Trello REST API.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fskills\u002Ftrello\u002FSKILL.md",[148,153],{"categoryNo":149,"categoryName":150,"taxonomyType":151,"taxonomyTypeDesc":152},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[144,116,155,156,157,158,159,160,97,98,161,115,91,162,163],"cloud","manage","via","rest api","token","atlassian","jq","REST","developer",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":170,"publishedAt":42},"01M698YQ9Q3M4W78EWV2KSCSVW","tmux","Control tmux sessions\u002Fpanes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fskills\u002Ftmux\u002FSKILL.md",[],[166,97,171,172,90,173,174,175,176,177,178,179,98,180,181,182,183,41,184],"send","darwin","keys","paste","output","control","prompts","interactive","list","capture","panes","text","monitor","linux"]