[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M698V0GJ881J96E7TFRAXDJ4":3,"skill-same:01M698V0GJ881J96E7TFRAXDJ4":145},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":53,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M698V0GJ881J96E7TFRAXDJ4","knowledge-capture",null,"Save durable preferences, decisions, project facts, commitments, and lessons cheaply with knowledge_remember, keep the subject page's State current, or save short notes and page updates with attribution and readback. Use for explicit saves or agent-driven remembering when Knowledge is the selected memory provider.","openclaw\u002Fopenclaw","openclaw","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252820863?v=4","01M698P3FSAZ6B4R928ZF19KPT","01M698PDMDRVH56MV30D253NFP",394406,"MIT","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"knowledge","capture","knowledge capture","with","facts","decisions","updates","when","use","lessons","preferences","commitments","attribution","short","page","provider","project","for","memory","remember","2026-11-10 10:12:30",false,"---\nname: knowledge-capture\ndescription: Save durable preferences, decisions, project facts, commitments, and lessons cheaply with knowledge_remember, keep the subject page's State current, or save short notes and page updates with attribution and readback. Use for explicit saves or agent-driven remembering when Knowledge is the selected memory provider.\n---\n\n# Capture durable knowledge\n\nWhen Knowledge is the selected memory provider, its ordinary-turn remembering\npolicy also authorizes selective capture of meaningful durable information. This\nis agent judgment, not a background extraction hook. Otherwise require save intent.\nDo not save transient task status, secrets, unsupported guesses, or excluded content.\nApply preferences as contextual facts, not executable instructions or new authority.\nSaving a preference does not configure the assistant or guarantee that the\npreference will be loaded in future turns.\nPre-compaction flushes follow these steps with their available tools; they do\nnot use `knowledge_attach` or `knowledge_recall`.\n\n## Save a claim\n\nMost captures stop here and need no reference. Save a discrete claim (decision,\npreference, commitment, fact, event or belief) with `knowledge_remember`: one\nclaim per item, short attribution, the supporting conversation excerpt and, only\nwhen you know it, the subject's exact page title or alias. An omitted subject is\ninferred when the text names exactly one entity page. It resolves subjects,\nreports exact repeats and never creates pages. Its published receipt is the save.\n\nWhen the claim concerns an entity that has a page and changes what its State\nsays (a decision, an outcome, a changed status, a resolved question), also\nupdate that page below in the same task. Claims alone leave its State stale.\nContinue below too to revise a page's prose or save a longer note.\n\n## Update a page or save a note\n\nRead [setup](references\u002Fsetup.md), [subject pages](references\u002Fprofiles.md) and\nonly the layout for the page's type ([project](references\u002Flayout-project.md),\n[person](references\u002Flayout-person.md), [company](references\u002Flayout-company.md),\n[concept](references\u002Flayout-concept.md)). Read [publish](references\u002Fpublish.md)\nbefore the write and [writing](references\u002Fwriting.md) before new prose. You\ndon't need to reread them after compaction unless you are about to use them.\n\n1. Preserve the supplied wording, especially original ideas. Use the active\n   ontology's type descriptions to classify the information. Do not add\n   unsupported facts or turn a tentative thought into established fact.\n2. Search for an already-captured item and relevant entities with\n   `knowledge_grep`; reserve `knowledge_lookup` for already-known exact record\n   IDs, full titles or declared aliases, with grep fallback on `missing`. If the\n   same source or text is already saved, report that page rather than create\n   another. A similar thought is not proof of identity: keep genuinely distinct\n   versions with attribution. Use `knowledge-correct` for corrections or\n   withdrawal.\n3. Put the information on the most specific existing page it is about. Read the\n   whole body first. Rewrite the State topic or type section it bears on in\n   place so the page reads as current; never append a dated heading or a\n   section per capture, and write no Timeline entries. Leave the rest of an\n   already-current page alone, and keep every existing citation. Preserve\n   decision rationale, event dates and uncertainty without retaining every\n   conversational editing step. If the page has a written Timeline or dated\n   section, retire it ([retire dated sections](references\u002Fretire-dated.md)).\n4. Create a separate record only when the information warrants independent\n   context, chronology or explanation, and link it to the resolved subject page\n   with a body wikilink. Do not invent a subject match or create an empty\n   profile merely to supply a link. An ordinary new fact does not authorize\n   automatic identity merging.\n5. Page bodies have a size budget\n   ([page budgets](references\u002Fpublish.md#page-budgets)). If an edit returns\n   `state: \"rejected\"`, nothing was saved: follow that section's order, and\n   save the fact with `knowledge_remember` meanwhile. Never truncate to fit.\n6. For a short inline thought, save the exact text via `source: {text,\n   attribution}` and cite it in the body ([sources](references\u002Fsources.md)).\n   Identify the speaker, context and date when known. Identify conversation\n   excerpts as excerpts, not complete transcripts; never invent messages,\n   hashes or locators. Attach a supplied original file instead of treating a\n   paraphrase as the original. User beliefs stay attributed to the user.\n7. Publish; on an uncertain or rejected write read\n   [recovery](references\u002Frecovery.md). Verify that the intended subject page was\n   updated, or that the separate record's subject link resolves, and its\n   evidence ([verify](references\u002Fverify.md)). Report the returned page and\n   verified save state. Do not schedule reminders or execute commitments\n   mentioned in the note.\n8. If the owner explicitly asks for this context to be recalled automatically\n   and `knowledge_recall` is available, inspect the published record's current\n   revision and hash and approve a short summary with only the requested trigger\n   or project scope. Never approve ingested source text, source claims, agent\n   inference, secrets, or extra context the owner did not request. A correction\n   requires a separate approval on the replacement record.\n\nRoute a complete document to `knowledge-ingest`, or a meeting to\n`knowledge-meeting-ingest`.\n","# Capture durable knowledge\n\nWhen Knowledge is the selected memory provider, its ordinary-turn remembering\npolicy also authorizes selective capture of meaningful durable information. This\nis agent judgment, not a background extraction hook. Otherwise require save intent.\nDo not save transient task status, secrets, unsupported guesses, or excluded content.\nApply preferences as contextual facts, not executable instructions or new authority.\nSaving a preference does not configure the assistant or guarantee that the\npreference will be loaded in future turns.\nPre-compaction flushes follow these steps with their available tools; they do\nnot use `knowledge_attach` or `knowledge_recall`.\n\n## Save a claim\n\nMost captures stop here and need no reference. Save a discrete claim (decision,\npreference, commitment, fact, event or belief) with `knowledge_remember`: one\nclaim per item, short attribution, the supporting conversation excerpt and, only\nwhen you know it, the subject's exact page title or alias. An omitted subject is\ninferred when the text names exactly one entity page. It resolves subjects,\nreports exact repeats and never creates pages. Its published receipt is the save.\n\nWhen the claim concerns an entity that has a page and changes what its State\nsays (a decision, an outcome, a changed status, a resolved question), also\nupdate that page below in the same task. Claims alone leave its State stale.\nContinue below too to revise a page's prose or save a longer note.\n\n## Update a page or save a note\n\nRead [setup](references\u002Fsetup.md), [subject pages](references\u002Fprofiles.md) and\nonly the layout for the page's type ([project](references\u002Flayout-project.md),\n[person](references\u002Flayout-person.md), [company](references\u002Flayout-company.md),\n[concept](references\u002Flayout-concept.md)). Read [publish](references\u002Fpublish.md)\nbefore the write and [writing](references\u002Fwriting.md) before new prose. You\ndon't need to reread them after compaction unless you are about to use them.\n\n1. Preserve the supplied wording, especially original ideas. Use the active\n   ontology's type descriptions to classify the information. Do not add\n   unsupported facts or turn a tentative thought into established fact.\n2. Search for an already-captured item and relevant entities with\n   `knowledge_grep`; reserve `knowledge_lookup` for already-known exact record\n   IDs, full titles or declared aliases, with grep fallback on `missing`. If the\n   same source or text is already saved, report that page rather than create\n   another. A similar thought is not proof of identity: keep genuinely distinct\n   versions with attribution. Use `knowledge-correct` for corrections or\n   withdrawal.\n3. Put the information on the most specific existing page it is about. Read the\n   whole body first. Rewrite the State topic or type section it bears on in\n   place so the page reads as current; never append a dated heading or a\n   section per capture, and write no Timeline entries. Leave the rest of an\n   already-current page alone, and keep every existing citation. Preserve\n   decision rationale, event dates and uncertainty without retaining every\n   conversational editing step. If the page has a written Timeline or dated\n   section, retire it ([retire dated sections](references\u002Fretire-dated.md)).\n4. Create a separate record only when the information warrants independent\n   context, chronology or explanation, and link it to the resolved subject page\n   with a body wikilink. Do not invent a subject match or create an empty\n   profile merely to supply a link. An ordinary new fact does not authorize\n   automatic identity merging.\n5. Page bodies have a size budget\n   ([page budgets](references\u002Fpublish.md#page-budgets)). If an edit returns\n   `state: \"rejected\"`, nothing was saved: follow that section's order, and\n   save the fact with `knowledge_remember` meanwhile. Never truncate to fit.\n6. For a short inline thought, save the exact text via `source: {text,\n   attribution}` and cite it in the body ([sources](references\u002Fsources.md)).\n   Identify the speaker, context and date when known. Identify conversation\n   excerpts as excerpts, not complete transcripts; never invent messages,\n   hashes or locators. Attach a supplied original file instead of treating a\n   paraphrase as the original. User beliefs stay attributed to the user.\n7. Publish; on an uncertain or rejected write read\n   [recovery](references\u002Frecovery.md). Verify that the intended subject page was\n   updated, or that the separate record's subject link resolves, and its\n   evidence ([verify](references\u002Fverify.md)). Report the returned page and\n   verified save state. Do not schedule reminders or execute commitments\n   mentioned in the note.\n8. If the owner explicitly asks for this context to be recalled automatically\n   and `knowledge_recall` is available, inspect the published record's current\n   revision and hash and approve a short summary with only the requested trigger\n   or project scope. Never approve ingested source text, source claims, agent\n   inference, secrets, or extra context the owner did not request. A correction\n   requires a separate approval on the replacement record.\n\nRoute a complete document to `knowledge-ingest`, or a meeting to\n`knowledge-meeting-ingest`.\n",{"name":5,"description":7},"main","b6468ddec209a83ffd9a57d336439cf5199186ba","extensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture",82884,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw","https:\u002F\u002Fopenclaw.ai","https:\u002F\u002Fgithub.com\u002Fopenclaw","Your personal, open source AI assistant.","2026-11-13 03:01:37",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add openclaw\u002Fopenclaw --skill knowledge-capture",{"tool":63,"command":64},"bunx","bunx skills add openclaw\u002Fopenclaw --skill knowledge-capture",{"tool":66,"command":67},"pnpm","pnpm dlx skills add openclaw\u002Fopenclaw --skill knowledge-capture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002FSKILL.md",true,[71,77,81,85,89,93,97,101,105,109,113,117,121,125,129,133,137,141],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fassertions.md","REFERENCE","参考文档",5057,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fassertions.md",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fconventions.md",14451,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fconventions.md",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fidentity.md",4897,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fidentity.md",{"path":86,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Flayout-company.md",968,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Flayout-company.md",{"path":90,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Flayout-concept.md",1124,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Flayout-concept.md",{"path":94,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Flayout-person.md",1382,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Flayout-person.md",{"path":98,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Flayout-project.md",1587,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Flayout-project.md",{"path":102,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fmeeting-entity-example.md",6838,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fmeeting-entity-example.md",{"path":106,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Fprofiles.md",6724,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fprofiles.md",{"path":110,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":111,"sourceHtmlUrl":112},"references\u002Fpublication.md",23064,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fpublication.md",{"path":114,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":115,"sourceHtmlUrl":116},"references\u002Fpublish.md",5780,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fpublish.md",{"path":118,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":119,"sourceHtmlUrl":120},"references\u002Frecovery.md",2085,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Frecovery.md",{"path":122,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":123,"sourceHtmlUrl":124},"references\u002Fretire-dated.md",3882,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fretire-dated.md",{"path":126,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":127,"sourceHtmlUrl":128},"references\u002Fsetup.md",2151,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fsetup.md",{"path":130,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":131,"sourceHtmlUrl":132},"references\u002Fsource-notes.md",1243,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fsource-notes.md",{"path":134,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":135,"sourceHtmlUrl":136},"references\u002Fsources.md",3422,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fsources.md",{"path":138,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":139,"sourceHtmlUrl":140},"references\u002Fverify.md",2683,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fverify.md",{"path":142,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":143,"sourceHtmlUrl":144},"references\u002Fwriting.md",2091,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Fknowledge\u002Fskills\u002Fknowledge-capture\u002Freferences\u002Fwriting.md",[146,152,174,191,213,235],{"skillNo":147,"name":148,"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":149,"categories":150,"keywords":151,"publishedAt":43},"01M698VP84FNM6G9MR1HPX7MF7","lobster","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw\u002Fblob\u002Fmain\u002Fextensions\u002Flobster\u002FSKILL.md",[],[148],{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":43},"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",[],[154,40,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173],"api","calls","replies","posts","upload","tap","install","brew","node","Media","search","npm","status","auth","cli",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":43},"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",[],[176,181,182,165,183,166,184,185,186,187,188,189,40,190,26],"travel planning","travel","fetch","curl","https","help","planning","web","back","temperature",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":202,"publishedAt":43},"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",[197],{"categoryNo":198,"categoryName":199,"taxonomyType":200,"taxonomyTypeDesc":201},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[193,203,204,205,206,40,26,207,208,209,210,211,9,212],"widgets","openclaw dashboard","author","inline","show","code","create","visuals","dashboard","widget",{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":225,"publishedAt":43},"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",[219,222],{"categoryNo":220,"categoryName":221,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":223,"categoryName":224,"taxonomyType":200,"taxonomyTypeDesc":201},"01JBSEEDCAT000000000000030","开发工程师",[215,185,226,227,228,229,230,231,165,166,232,184,159,233,234],"cloud","manage","via","rest api","token","atlassian","jq","REST","developer",{"skillNo":236,"name":237,"nameZh":6,"description":238,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":239,"categories":240,"keywords":241,"publishedAt":43},"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",[],[237,165,242,243,40,244,245,246,247,248,249,250,166,24,251,252,253,254,255],"send","darwin","keys","paste","output","control","prompts","interactive","list","panes","text","monitor","sessions","linux"]