[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70FVW1F1MPXSFVEFB5HNMW8":3,"skill-same:01M70FVW1F1MPXSFVEFB5HNMW8":64},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M70FVW1F1MPXSFVEFB5HNMW8","ideas",null,"Deep vault scan to generate actionable ideas by combining insights across domains, finding gaps, and proposing concrete next steps. Uses the retrieval engine (the `\u002Fask` ladder) and agent directories (`entities\u002F`, `concepts\u002F`, `comparisons\u002F`, `queries\u002F`) for compiled knowledge. Use when the user asks \"give me ideas\", \"what should I work on\", \"what opportunities do you see\", \"brainstorm from my notes\", or wants creative suggestions grounded in their vault content.","JayJiangCT\u002Fknowlery","JayJiangCT","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F59813406?v=4","01M70FV52GQJT4F12FBSYG48R2","Jay Jiang","01M70FV536R3NCMG5ZB0TMEWNP",15,"MIT","https:\u002F\u002Fgithub.com\u002FJayJiangCT\u002Fknowlery\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fideas\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"insights","across","gaps","ask","you","when","entities","use","knowledge","next steps","domains","brainstorm","work on","actionable","scan","for","directories","do","deep","2026-11-10 10:12:30",false,"---\nname: ideas\ndescription: >\n  Deep vault scan to generate actionable ideas by combining insights across domains, finding gaps,\n  and proposing concrete next steps. Uses the retrieval engine (the `\u002Fask` ladder) and agent directories (`entities\u002F`, `concepts\u002F`,\n  `comparisons\u002F`, `queries\u002F`) for compiled knowledge. Use when the user asks \"give me ideas\", \"what should I work\n  on\", \"what opportunities do you see\", \"brainstorm from my notes\", or wants creative suggestions\n  grounded in their vault content.\n---\n\n# \u002Fideas — Generate Actionable Ideas\n\nYou are a strategic thinking partner. Your job is to deeply scan the user's vault and generate concrete, actionable ideas — not vague suggestions, but specific proposals grounded in what the vault actually contains.\n\n## Parameters\n\n- **focus** (optional): Narrow ideas to a specific domain, project, or theme. Default: scan all domains.\n- **count** (optional): Number of ideas to generate. Default: 5.\n- **output** (optional): Save ideas as a note at this path.\n\n## Process\n\n### Sampling Strategy\n\nIf a domain or search returns more than 30 notes, prioritize: (1) most recent 10, (2) most-linked 10 (highest backlink count), (3) notes with `status: active`. Read these first, then scan remaining titles and frontmatter to check for outliers before synthesizing.\n\n### Step 1: Map the Vault\n\nStart from the orientation map — it is exactly this step, precomputed:\n\n```bash\nknowlery index    # compiled pages by directory, domains, bundles, stale\u002Funcooked counts\n```\n\n(Or read the MCP `knowlery:\u002F\u002F\u003Ckb>\u002Findex` resource.) Then deepen with:\n\n```bash\nobsidian list\nobsidian properties sort=count counts\nobsidian tags\n```\n\nBuild a picture of: domains, note distribution, most active areas, tag clusters.\n\n### Step 2: Deep Read\n\nRead notes across domains, prioritizing:\n- Recent notes (last 30 days) — what the user is actively thinking about\n- Highly connected notes (many backlinks) — central concepts\n- Notes with `status: active` — current work\n- The **`\u002Fask`** retrieval ladder (`obsidian knowlery:query` on subject terms) plus `obsidian properties` \u002F `search` — same compiled knowledge scope\n- Agent pages in `entities\u002F`, `concepts\u002F`, `comparisons\u002F`, `queries\u002F` — for compiled knowledge\n\nFor each domain, read 5-10 representative notes to understand the landscape.\n\n### Step 3: Cross-Pollinate\n\nThe best ideas come from combining insights across domains. For each pair of active domains:\n\n1. Identify shared concepts, people, or challenges\n2. Look for solutions in one domain that could apply to another\n3. Find gaps: \"Domain A discusses X extensively but never mentions Y, which Domain B treats as critical\"\n\n### Step 4: Identify Idea Types\n\nGenerate ideas across these categories:\n\n**Synthesis ideas** — Combine two existing threads into something new.\n> \"Your notes on 'event sourcing' and 'audit compliance' both need immutable logs. A unified audit-event architecture could serve both.\"\n\n**Gap ideas** — Something the vault implies is needed but doesn't exist.\n> \"You have 15 notes about 'payment migration' but no rollback strategy document. Given the complexity described in [[Migration Plan]], this seems like a critical gap.\"\n\n**Connection ideas** — Two people\u002Fprojects should be talking to each other.\n> \"[[Alice]] is working on rate limiting and [[Bob]] on API gateway redesign. Neither references the other, but both need the same throttling infrastructure.\"\n\n**Amplification ideas** — Take something small and scale it.\n> \"Your daily note from March 15 mentions 'what if we exposed the internal API to partners?' — 4 other notes contain evidence this could work.\"\n\n**Challenge ideas** — Question an assumption the vault takes for granted.\n> \"Every note about the data pipeline assumes batch processing, but your meeting notes from February suggest the team wants real-time. Is batch still the right choice?\"\n\n**People ideas** — People the user should meet, reconnect with, or introduce to each other.\n> \"[[Alice]] keeps coming up in your infrastructure notes but you haven't had a 1:1 since February. Worth reconnecting.\"\n\n**Content ideas** — Things worth writing or publishing, based on depth of vault coverage.\n> \"You have 8 notes about 'event-driven architecture' spanning 4 months — enough material for an article or internal tech talk.\"\n\n### Step 5: Validate Each Idea\n\nFor each idea, verify:\n- Is the evidence actually in the vault? (cite specific notes with quotes)\n- Is this actionable? (what concrete step would the user take?)\n- Is this non-obvious? (would the user have thought of this on their own?)\n\nDiscard ideas that fail any of these checks.\n\n### Step 6: Present Ideas\n\n```markdown\n# Ideas: {focus or \"Across All Domains\"}\n\nGenerated from {N} notes across {M} domains.\n\n---\n\n### Idea 1: {Title}\n\n**Type**: {synthesis \u002F gap \u002F connection \u002F amplification \u002F challenge}\n\n**The insight**: {2-3 sentences explaining the idea}\n\n**Evidence**:\n- [[Note A]]: \"{relevant quote}\"\n- [[Note B]]: \"{relevant quote}\"\n- [[Note C]]: \"{relevant quote}\"\n\n**Concrete next step**: {exactly what to do — write a note, schedule a meeting, create a project, run \u002Fexplore on a topic}\n\n**Impact**: {why this matters — what it could unlock or prevent}\n\n---\n\n### Idea 2: {Title}\n...\n\n---\n\n## How These Ideas Connect\n\n{Brief paragraph on themes across the ideas — are they pointing in the same direction?}\n\n## Top 3 Do Now\n\nRank the three highest-impact, most immediately actionable ideas:\n\n1. **{Idea title}** — {one-sentence reason this is high-priority}\n2. **{Idea title}** — {reason}\n3. **{Idea title}** — {reason}\n\n## Suggested Follow-ups\n\n- Run `\u002Fexplore topic=\"X\"` to explore Idea 1 further\n- Run `\u002Fchallenge \"\u003Cclaim>\"` to pressure-test Idea 3\n- Run `\u002Fcook` to compile or refresh `entities\u002F`, `concepts\u002F`, `comparisons\u002F`, or `queries\u002F` pages when an idea exposes a knowledge gap\n- Add or extend a page under `queries\u002F` for Idea 5 if it is question-shaped knowledge worth keeping\n```\n\n### Step 7: Save (Optional)\n\nAt the end of your ideas, ask:\n\n> \"Would you like me to save this as a note?\"\n\nIf the user confirms, save with frontmatter:\n\n```yaml\n---\ntitle: \"Ideas: {focus}\"\ndate: \u003Ctoday>\ntags: [ideas, proactive]\n---\n```\n\nAsk the user where they'd like it saved, then write the note there. A saved\nanswer is a full page — write the `.md` file directly (Obsidian indexes new\nfiles automatically); `obsidian create path=\"...\"` is fine for short answers.\nSee **vault-conventions** for the writing-tool rules and frontmatter.\n\n## Key Principles\n\n- **Actionable over interesting**: Every idea must have a concrete next step. \"Interesting observation\" is not an idea.\n- **Evidence-based**: Every idea must cite 2+ vault notes. No general knowledge ideas.\n- **Non-obvious**: If the user would have thought of it without AI, it's not worth presenting.\n- **Respect priorities**: Don't suggest ideas that contradict the user's stated direction unless explicitly framed as a challenge.\n- **Quality over quantity**: 3 strong ideas beat 10 weak ones. Filter aggressively.\n","# \u002Fideas — Generate Actionable Ideas\n\nYou are a strategic thinking partner. Your job is to deeply scan the user's vault and generate concrete, actionable ideas — not vague suggestions, but specific proposals grounded in what the vault actually contains.\n\n## Parameters\n\n- **focus** (optional): Narrow ideas to a specific domain, project, or theme. Default: scan all domains.\n- **count** (optional): Number of ideas to generate. Default: 5.\n- **output** (optional): Save ideas as a note at this path.\n\n## Process\n\n### Sampling Strategy\n\nIf a domain or search returns more than 30 notes, prioritize: (1) most recent 10, (2) most-linked 10 (highest backlink count), (3) notes with `status: active`. Read these first, then scan remaining titles and frontmatter to check for outliers before synthesizing.\n\n### Step 1: Map the Vault\n\nStart from the orientation map — it is exactly this step, precomputed:\n\n```bash\nknowlery index    # compiled pages by directory, domains, bundles, stale\u002Funcooked counts\n```\n\n(Or read the MCP `knowlery:\u002F\u002F\u003Ckb>\u002Findex` resource.) Then deepen with:\n\n```bash\nobsidian list\nobsidian properties sort=count counts\nobsidian tags\n```\n\nBuild a picture of: domains, note distribution, most active areas, tag clusters.\n\n### Step 2: Deep Read\n\nRead notes across domains, prioritizing:\n- Recent notes (last 30 days) — what the user is actively thinking about\n- Highly connected notes (many backlinks) — central concepts\n- Notes with `status: active` — current work\n- The **`\u002Fask`** retrieval ladder (`obsidian knowlery:query` on subject terms) plus `obsidian properties` \u002F `search` — same compiled knowledge scope\n- Agent pages in `entities\u002F`, `concepts\u002F`, `comparisons\u002F`, `queries\u002F` — for compiled knowledge\n\nFor each domain, read 5-10 representative notes to understand the landscape.\n\n### Step 3: Cross-Pollinate\n\nThe best ideas come from combining insights across domains. For each pair of active domains:\n\n1. Identify shared concepts, people, or challenges\n2. Look for solutions in one domain that could apply to another\n3. Find gaps: \"Domain A discusses X extensively but never mentions Y, which Domain B treats as critical\"\n\n### Step 4: Identify Idea Types\n\nGenerate ideas across these categories:\n\n**Synthesis ideas** — Combine two existing threads into something new.\n> \"Your notes on 'event sourcing' and 'audit compliance' both need immutable logs. A unified audit-event architecture could serve both.\"\n\n**Gap ideas** — Something the vault implies is needed but doesn't exist.\n> \"You have 15 notes about 'payment migration' but no rollback strategy document. Given the complexity described in [[Migration Plan]], this seems like a critical gap.\"\n\n**Connection ideas** — Two people\u002Fprojects should be talking to each other.\n> \"[[Alice]] is working on rate limiting and [[Bob]] on API gateway redesign. Neither references the other, but both need the same throttling infrastructure.\"\n\n**Amplification ideas** — Take something small and scale it.\n> \"Your daily note from March 15 mentions 'what if we exposed the internal API to partners?' — 4 other notes contain evidence this could work.\"\n\n**Challenge ideas** — Question an assumption the vault takes for granted.\n> \"Every note about the data pipeline assumes batch processing, but your meeting notes from February suggest the team wants real-time. Is batch still the right choice?\"\n\n**People ideas** — People the user should meet, reconnect with, or introduce to each other.\n> \"[[Alice]] keeps coming up in your infrastructure notes but you haven't had a 1:1 since February. Worth reconnecting.\"\n\n**Content ideas** — Things worth writing or publishing, based on depth of vault coverage.\n> \"You have 8 notes about 'event-driven architecture' spanning 4 months — enough material for an article or internal tech talk.\"\n\n### Step 5: Validate Each Idea\n\nFor each idea, verify:\n- Is the evidence actually in the vault? (cite specific notes with quotes)\n- Is this actionable? (what concrete step would the user take?)\n- Is this non-obvious? (would the user have thought of this on their own?)\n\nDiscard ideas that fail any of these checks.\n\n### Step 6: Present Ideas\n\n```markdown\n# Ideas: {focus or \"Across All Domains\"}\n\nGenerated from {N} notes across {M} domains.\n\n---\n\n### Idea 1: {Title}\n\n**Type**: {synthesis \u002F gap \u002F connection \u002F amplification \u002F challenge}\n\n**The insight**: {2-3 sentences explaining the idea}\n\n**Evidence**:\n- [[Note A]]: \"{relevant quote}\"\n- [[Note B]]: \"{relevant quote}\"\n- [[Note C]]: \"{relevant quote}\"\n\n**Concrete next step**: {exactly what to do — write a note, schedule a meeting, create a project, run \u002Fexplore on a topic}\n\n**Impact**: {why this matters — what it could unlock or prevent}\n\n---\n\n### Idea 2: {Title}\n...\n\n---\n\n## How These Ideas Connect\n\n{Brief paragraph on themes across the ideas — are they pointing in the same direction?}\n\n## Top 3 Do Now\n\nRank the three highest-impact, most immediately actionable ideas:\n\n1. **{Idea title}** — {one-sentence reason this is high-priority}\n2. **{Idea title}** — {reason}\n3. **{Idea title}** — {reason}\n\n## Suggested Follow-ups\n\n- Run `\u002Fexplore topic=\"X\"` to explore Idea 1 further\n- Run `\u002Fchallenge \"\u003Cclaim>\"` to pressure-test Idea 3\n- Run `\u002Fcook` to compile or refresh `entities\u002F`, `concepts\u002F`, `comparisons\u002F`, or `queries\u002F` pages when an idea exposes a knowledge gap\n- Add or extend a page under `queries\u002F` for Idea 5 if it is question-shaped knowledge worth keeping\n```\n\n### Step 7: Save (Optional)\n\nAt the end of your ideas, ask:\n\n> \"Would you like me to save this as a note?\"\n\nIf the user confirms, save with frontmatter:\n\n```yaml\n---\ntitle: \"Ideas: {focus}\"\ndate: \u003Ctoday>\ntags: [ideas, proactive]\n---\n```\n\nAsk the user where they'd like it saved, then write the note there. A saved\nanswer is a full page — write the `.md` file directly (Obsidian indexes new\nfiles automatically); `obsidian create path=\"...\"` is fine for short answers.\nSee **vault-conventions** for the writing-tool rules and frontmatter.\n\n## Key Principles\n\n- **Actionable over interesting**: Every idea must have a concrete next step. \"Interesting observation\" is not an idea.\n- **Evidence-based**: Every idea must cite 2+ vault notes. No general knowledge ideas.\n- **Non-obvious**: If the user would have thought of it without AI, it's not worth presenting.\n- **Respect priorities**: Don't suggest ideas that contradict the user's stated direction unless explicitly framed as a challenge.\n- **Quality over quantity**: 3 strong ideas beat 10 weak ones. Filter aggressively.\n",{"name":5,"description":7},"main","0e53802c0c332ab23445b83651f15999e1ac89b8","plugin\u002Fskills\u002Fideas",1,"https:\u002F\u002Fgithub.com\u002FJayJiangCT\u002Fknowlery","https:\u002F\u002Fgithub.com\u002FJayJiangCT","2026-11-09 16:04:29",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add JayJiangCT\u002Fknowlery --skill ideas",{"tool":56,"command":57},"bunx","bunx skills add JayJiangCT\u002Fknowlery --skill ideas",{"tool":59,"command":60},"pnpm","pnpm dlx skills add JayJiangCT\u002Fknowlery --skill ideas","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJayJiangCT\u002Fknowlery\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fideas\u002FSKILL.md",true,[],[65,81,102,123,154,170],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":38},"01M70FWHK80WMW5C9Y12KEZ8RG","vault-conventions","Use when creating or modifying notes in a Knowlery-structured vault. Enforces frontmatter requirements, wikilinks, and naming conventions.","https:\u002F\u002Fgithub.com\u002FJayJiangCT\u002Fknowlery\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fvault-conventions\u002FSKILL.md",[],[72,73,74,75,76,26,77,24,78,79,80],"vault","vault conventions","conventions","notes","naming","naming conventions","frontmatter","requirements","structured",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":38},"01M70FWF616X3Z6BPPW6A96VHT","organize","Directory organization based on frontmatter metadata. Suggests and applies file moves to keep the vault structured. Use when the user wants to reorganize notes, fix directory placement, clean up the vault structure, or says anything like \"organize my notes\", \"clean up the vault\", \"move files to the right folders\", \"tidy up\", or \"restructure my notes\".","https:\u002F\u002Fgithub.com\u002FJayJiangCT\u002Fknowlery\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Forganize\u002FSKILL.md",[],[83,88,89,90,91,92,93,26,24,94,95,75,96,72,97,98,99,78,100,101],"move","up","fix","clean","tidy","files","keep","file","structure","organization","directory","my","user","metadata",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":113,"publishedAt":38},"01M70FWC3VG73VJD8C56SEPM3X","obsidian-markdown","Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.","https:\u002F\u002Fgithub.com\u002FJayJiangCT\u002Fknowlery\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fobsidian-markdown\u002FSKILL.md",[108],{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[114,115,116,93,26,24,117,118,119,75,120,121,122,78,100],"obsidian","obsidian markdown","markdown","tags","with","create","properties","edit","syntax",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":137,"publishedAt":38},"01M70FW95K6BD12KQERZS0FWHW","obsidian-cli","Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.","https:\u002F\u002Fgithub.com\u002FJayJiangCT\u002Fknowlery\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fobsidian-cli\u002FSKILL.md",[129,134],{"categoryNo":130,"categoryName":131,"taxonomyType":132,"taxonomyTypeDesc":133},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":135,"categoryName":136,"taxonomyType":132,"taxonomyTypeDesc":133},"01JBSEEDCAT000000000000036","内容创作者",[114,138,139,140,141,142,143,24,144,119,75,145,146,147,148,149,150,151,152,153],"cli","obsidian cli","inspect","search","errors","themes","tasks","command","run","line","read","commands","take","vaults","screenshots","theme",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":38},"01M70FW75P9SEH28NWR115GZNN","obsidian-bases","Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.","https:\u002F\u002Fgithub.com\u002FJayJiangCT\u002Fknowlery\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fobsidian-bases\u002FSKILL.md",[],[114,161,162,163,164,93,165,26,166,24,118,119,75,167,121,168,100,169],"obsidian bases","bases","formulas","card","filters","database","summaries","base","table",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":179,"publishedAt":38},"01M70FW4ASRQ42NW1AC0AAWWAC","knowlery-mcp","Work a Knowlery knowledge base through its MCP tools — choose the right tool for the job, run the capture-to-cook loop, and behave well while doing it. Use when Knowlery MCP tools (query, capture, stale, health, init_kb, register_kb, sync, list_kbs, list_bundles) are available in the session, especially in clients without a shell.","https:\u002F\u002Fgithub.com\u002FJayJiangCT\u002Fknowlery\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fknowlery-mcp\u002FSKILL.md",[176],{"categoryNo":177,"categoryName":178,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000023","Skill与智能体开发",[180,181,182,183,34,184,185,186,187,188,27,26,189,24,190,191,192,193,146,194],"knowlery mcp","MCP","kb","register","choose","session","tool","behave","init","loop","query","health","knowledge base","work","shell"]