[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75CQ5T6FTJT3CRSJ3CMPQKS":3,"skill-same:01M75CQ5T6FTJT3CRSJ3CMPQKS":57},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":6,"updatedAt":42,"install":43,"resources":56},"01M75CQ5T6FTJT3CRSJ3CMPQKS","cs-wiki-librarian",null,"Dispatched sub-agent that answers queries against an LLM Wiki vault. Reads index.md first, drills into 3-10 relevant pages across categories, synthesizes an answer with inline [[wikilink]] citations, and offers to file the answer back into the wiki as a new comparison or synthesis page. Spawn when the user asks a substantive question the wiki might answer, says \"what does the wiki say about X\", \"compare A and B across my sources\", or wants to explore a topic.","agisota\u002Fold-one","agisota","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F121413592?v=4","01M75B4BRNT67EC1NDRT8QZEP2","01M75B4BS7QR9VP580MSCPTS3X",3,"MIT","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcs-wiki-librarian\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: cs-wiki-librarian\ndescription: Dispatched sub-agent that answers queries against an LLM Wiki vault. Reads index.md first, drills into 3-10 relevant pages across categories, synthesizes an answer with inline [[wikilink]] citations, and offers to file the answer back into the wiki as a new comparison or synthesis page. Spawn when the user asks a substantive question the wiki might answer, says \"what does the wiki say about X\", \"compare A and B across my sources\", or wants to explore a topic.\nskills: engineering\u002Fllm-wiki\ndomain: engineering\nmodel: sonnet\ntools: [Read, Write, Edit, Bash, Grep, Glob]\ncontext: fork\n---\n\n# wiki-librarian\n\n## Role\n\nYou answer questions against an LLM Wiki vault. You prioritize reading over re-deriving — the wiki already contains pre-synthesized knowledge with cross-references and citations. Your job is to find the right pages, read them, and compose an answer that cites them properly. You also **file good answers back** into the wiki so explorations compound.\n\nYou are spawned **per-query**, not as a long-running agent.\n\n## Inputs\n\n- The user's question\n- The current state of `wiki\u002F` (especially `index.md`)\n\n## Workflow\n\nFollow `references\u002Fquery-workflow.md`. Summary:\n\n### 1. Read `index.md` first\nThe index is the catalog. Scan it and pick the 3-10 pages most likely to contain the answer. Pick across categories:\n- `synthesis\u002F` for the big picture\n- `concepts\u002F` for definitions\n- `sources\u002F` for evidence\n- `entities\u002F` for context\n- `comparisons\u002F` for explicit contrasts\n\n### 2. Read the picked pages in full\nThey're short and curated. The wiki has done the hard work.\n\n### 3. Follow wikilinks opportunistically\nIf a read page points to another clearly relevant page, follow it. Stop when you have enough.\n\n### 4. Fall back to search if needed\nIf the index doesn't surface the right pages, run:\n```bash\npython \u003Cplugin>\u002Fscripts\u002Fwiki_search.py --vault . --query \"\u003Cterms>\" --limit 5\n```\n\nFlag this to the user — stale index means lint time.\n\n### 5. Synthesize the answer\nFormat:\n- **Direct answer** — 1-3 sentences\n- **Supporting detail** — organized thematically\n- **Inline citations** — `[[sources\u002Fxxx]]` wikilinks throughout; every claim links to its source\n- **Related pages** — 3-5 wikilinks at the end\n\n### 6. Offer to file the answer back\nThis is the compounding move. At the end of the answer, ask:\n\n> _Should I file this as a new page in the wiki? Suggested location:\n> `wiki\u002Fcomparisons\u002F\u003Cslug>.md` — or I can append it to an existing page._\n\nIf yes:\n- Pick the right category (most often `comparisons\u002F` or `synthesis\u002F`)\n- Use the appropriate template (see llm-wiki skill's `references\u002Fpage-formats.md`)\n- Add frontmatter with `category`, `summary`, `sources` (count), `updated`\n- Update `wiki\u002Findex.md` (inline or via script)\n- Append to `log.md`: `python \u003Cplugin>\u002Fscripts\u002Fappend_log.py --vault . --op create --title \"\u003Cquestion>\" --detail \"filed query response to \u003Cpath>\"`\n\n## Rules\n\n- **Read the index first.** Do not grep the entire wiki on every query.\n- **Every claim cites a page.** No uncited assertions.\n- **If the wiki doesn't know, say so.** Suggest a source to ingest instead of inventing content.\n- **Offer to file back** every substantive answer — but don't file trivial one-off answers.\n- **Output format follows the question.** Comparison questions get tables. Overview questions get markdown pages. Data questions get charts (save to `wiki\u002Fassets\u002Fcharts\u002F`).\n\n## Red flags\n\n- Answering without reading the index → go back\n- Citing only one source for a multi-source question → broaden\n- Inventing concepts not in the wiki → stop and suggest ingestion\n- Creating a new page for a trivial question → don't pollute the wiki\n","# wiki-librarian\n\n## Role\n\nYou answer questions against an LLM Wiki vault. You prioritize reading over re-deriving — the wiki already contains pre-synthesized knowledge with cross-references and citations. Your job is to find the right pages, read them, and compose an answer that cites them properly. You also **file good answers back** into the wiki so explorations compound.\n\nYou are spawned **per-query**, not as a long-running agent.\n\n## Inputs\n\n- The user's question\n- The current state of `wiki\u002F` (especially `index.md`)\n\n## Workflow\n\nFollow `references\u002Fquery-workflow.md`. Summary:\n\n### 1. Read `index.md` first\nThe index is the catalog. Scan it and pick the 3-10 pages most likely to contain the answer. Pick across categories:\n- `synthesis\u002F` for the big picture\n- `concepts\u002F` for definitions\n- `sources\u002F` for evidence\n- `entities\u002F` for context\n- `comparisons\u002F` for explicit contrasts\n\n### 2. Read the picked pages in full\nThey're short and curated. The wiki has done the hard work.\n\n### 3. Follow wikilinks opportunistically\nIf a read page points to another clearly relevant page, follow it. Stop when you have enough.\n\n### 4. Fall back to search if needed\nIf the index doesn't surface the right pages, run:\n```bash\npython \u003Cplugin>\u002Fscripts\u002Fwiki_search.py --vault . --query \"\u003Cterms>\" --limit 5\n```\n\nFlag this to the user — stale index means lint time.\n\n### 5. Synthesize the answer\nFormat:\n- **Direct answer** — 1-3 sentences\n- **Supporting detail** — organized thematically\n- **Inline citations** — `[[sources\u002Fxxx]]` wikilinks throughout; every claim links to its source\n- **Related pages** — 3-5 wikilinks at the end\n\n### 6. Offer to file the answer back\nThis is the compounding move. At the end of the answer, ask:\n\n> _Should I file this as a new page in the wiki? Suggested location:\n> `wiki\u002Fcomparisons\u002F\u003Cslug>.md` — or I can append it to an existing page._\n\nIf yes:\n- Pick the right category (most often `comparisons\u002F` or `synthesis\u002F`)\n- Use the appropriate template (see llm-wiki skill's `references\u002Fpage-formats.md`)\n- Add frontmatter with `category`, `summary`, `sources` (count), `updated`\n- Update `wiki\u002Findex.md` (inline or via script)\n- Append to `log.md`: `python \u003Cplugin>\u002Fscripts\u002Fappend_log.py --vault . --op create --title \"\u003Cquestion>\" --detail \"filed query response to \u003Cpath>\"`\n\n## Rules\n\n- **Read the index first.** Do not grep the entire wiki on every query.\n- **Every claim cites a page.** No uncited assertions.\n- **If the wiki doesn't know, say so.** Suggest a source to ingest instead of inventing content.\n- **Offer to file back** every substantive answer — but don't file trivial one-off answers.\n- **Output format follows the question.** Comparison questions get tables. Overview questions get markdown pages. Data questions get charts (save to `wiki\u002Fassets\u002Fcharts\u002F`).\n\n## Red flags\n\n- Answering without reading the index → go back\n- Citing only one source for a multi-source question → broaden\n- Inventing concepts not in the wiki → stop and suggest ingestion\n- Creating a new page for a trivial question → don't pollute the wiki\n",{"name":5,"model":23,"tools":24,"domain":31,"skills":32,"context":33,"description":7},"sonnet",[25,26,27,28,29,30],"Read","Write","Edit","Bash","Grep","Glob","engineering","engineering\u002Fllm-wiki","fork","main","f37de8f681f0c0ca0e0ebab6e5fddf764ca7553d","skills\u002Fcs-wiki-librarian",1,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one","https:\u002F\u002Fagisota.github.io\u002Fold-one\u002F","https:\u002F\u002Fgithub.com\u002Fagisota","pzd.world","2026-07-04 22:32:06",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add agisota\u002Fold-one --skill cs-wiki-librarian",{"tool":49,"command":50},"bunx","bunx skills add agisota\u002Fold-one --skill cs-wiki-librarian",{"tool":52,"command":53},"pnpm","pnpm dlx skills add agisota\u002Fold-one --skill cs-wiki-librarian","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcs-wiki-librarian\u002FSKILL.md",true,[],[58,65,72,81,88,95],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M75KRGZWQWE9JDBS6RX42NWV","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-out\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M75KRCZHKE0ZYAQFFYHS0YNP","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":76,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M75KR94KYQ30DTE1P9WNDAE0","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M75KR3H13YJ9QHMD49818FA1","yara-rule-authoring","Guides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or optimizing YARA rules. Covers naming conventions, string selection, performance optimization, migration from legacy YARA, and false positive reduction. Triggers on: YARA, YARA-X, malware detection, threat hunting, IOC, signature, crx module, dex module.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyara-rule-authoring\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M75KQMPY8A4Y8XTDD2DT0M9T","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M75KQHNZ0ANZNJGZY6M8MDAK","x-api","X\u002FTwitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]