[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M753XKBKBW3ENRFYYFV6EDYV":3,"skill-same:01M753XKBKBW3ENRFYYFV6EDYV":60},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M753XKBKBW3ENRFYYFV6EDYV","spec-browser",null,"Use when there are many tech specs under specs\u002F and you need to navigate them as one doc site, generate a catalog agents can reference, or answer \"what specs do we have \u002F where is the spec for X\". Triggers include \"browse specs\", \"spec index\", \"list all specs\", \"spec site\", \"navigate specs\".","jabworks\u002Fagentic-toolkit","jabworks","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F159094119?v=4","01M753P4JBZBTT7WN1PJBPZJZP","JAB Works","01M753P4K5KDGEWGXWT811BZET",2,"MIT","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fspec-browser\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: spec-browser\ndescription: Use when there are many tech specs under specs\u002F and you need to navigate them as one doc site, generate a catalog agents can reference, or answer \"what specs do we have \u002F where is the spec for X\". Triggers include \"browse specs\", \"spec index\", \"list all specs\", \"spec site\", \"navigate specs\".\nwhen_to_use: Reach for this once a repo accumulates several specs and a single spec folder view (technical-spec's own preview) is no longer enough — you want the whole specs\u002F tree at once, plus a plain-markdown catalog for agents that have no search plugin. Not for an approve\u002Frevise decision on one plan; use plan-review.\nargument-hint: \"[specs-root]\"\neffort: low\n---\n\n# \u002Fspec-browser\n\nTurn a growing `specs\u002F` tree into (1) a plain-markdown **catalog** any agent\ncan read or grep, and (2) a **browsable doc site** across every spec, reusing\nplan-review's renderer and folder-grouped navigation. No external services,\nno plugins, no build step.\n\n## Two outputs, two audiences\n\n| Output | Audience | Form |\n|---|---|---|\n| `specs\u002Findex.md` | agents + humans | one markdown table: spec title, purpose, path |\n| plan-review viewer | humans | live doc site over the whole `specs\u002F` tree |\n\nThe catalog is the portable, dependency-free way for an agent to discover and\nreference specs — read or `grep` one file. It is deliberately not tied to any\nsearch MCP, so it works in plain Claude Code, Codex, or any compatible agent.\n\n## Steps\n\n### 1. Build \u002F refresh the catalog\n\nLocate this skill's generator and run it against the specs root (default\n`specs`):\n\n```bash\nnode \u003Cpath-to>\u002Fspec-browser\u002Freferences\u002Fbuild-index.js [specs-root]\n```\n\nIt walks the tree, treats every directory containing an `index.md` as a spec,\nextracts the title (`# heading`) and purpose (first `>` note or first line),\nand writes `\u003Cspecs-root>\u002Findex.md`. Re-run it whenever specs are added or\nrenamed — it overwrites the catalog in place.\n\n### 2. Browse the tree (optional)\n\nTo read\u002Fannotate the whole set in the browser, launch the plan-review server\nin directory mode against the specs root — it now recurses the tree and groups\nthe Contents nav by spec folder, with `index.md` (the catalog) as the landing\npage:\n\nThis step needs the **condux plugin's plan-review skill installed** — the\nserver ships with it, not with spec-browser. Step 1 (the catalog) works\nwithout it.\n\n```bash\n# find the server shipped with the plan-review skill\nfind ~\u002F.claude ~\u002F.codex ~\u002F.agents -name annotate-server.js -path '*plan-review*' 2>\u002Fdev\u002Fnull | head -1\nnode \u002Fpath\u002Fto\u002Fplan-review\u002Freferences\u002Fannotate-server.js specs\n```\n\nIf the `find` prints nothing, plan-review isn't installed — say so and offer\nthe catalog (`specs\u002Findex.md`) instead of silently skipping the browse step.\n\nSame annotation UI as plan\u002Fspec review: notes land in\n`specs\u002Freview.feedback.md`. This is browsing, not a decision gate — no\napprove\u002Fdeny polling needed unless you want it.\n\n## Notes\n\n- The catalog is a generated artifact — the header marks it \"do not edit by\n  hand.\" Editing a spec means editing that spec's own files, then re-running\n  step 1.\n- Pairs with `technical-spec` (which writes individual specs) — this skill is\n  the index over all of them. For a single spec, use plan-review's directory\n  mode (technical-spec's old standalone preview is retired); use spec-browser\n  when you have many.\n- Keep `specs\u002Findex.md` committed so agents in a fresh checkout can reference\n  the catalog without running anything.\n","# \u002Fspec-browser\n\nTurn a growing `specs\u002F` tree into (1) a plain-markdown **catalog** any agent\ncan read or grep, and (2) a **browsable doc site** across every spec, reusing\nplan-review's renderer and folder-grouped navigation. No external services,\nno plugins, no build step.\n\n## Two outputs, two audiences\n\n| Output | Audience | Form |\n|---|---|---|\n| `specs\u002Findex.md` | agents + humans | one markdown table: spec title, purpose, path |\n| plan-review viewer | humans | live doc site over the whole `specs\u002F` tree |\n\nThe catalog is the portable, dependency-free way for an agent to discover and\nreference specs — read or `grep` one file. It is deliberately not tied to any\nsearch MCP, so it works in plain Claude Code, Codex, or any compatible agent.\n\n## Steps\n\n### 1. Build \u002F refresh the catalog\n\nLocate this skill's generator and run it against the specs root (default\n`specs`):\n\n```bash\nnode \u003Cpath-to>\u002Fspec-browser\u002Freferences\u002Fbuild-index.js [specs-root]\n```\n\nIt walks the tree, treats every directory containing an `index.md` as a spec,\nextracts the title (`# heading`) and purpose (first `>` note or first line),\nand writes `\u003Cspecs-root>\u002Findex.md`. Re-run it whenever specs are added or\nrenamed — it overwrites the catalog in place.\n\n### 2. Browse the tree (optional)\n\nTo read\u002Fannotate the whole set in the browser, launch the plan-review server\nin directory mode against the specs root — it now recurses the tree and groups\nthe Contents nav by spec folder, with `index.md` (the catalog) as the landing\npage:\n\nThis step needs the **condux plugin's plan-review skill installed** — the\nserver ships with it, not with spec-browser. Step 1 (the catalog) works\nwithout it.\n\n```bash\n# find the server shipped with the plan-review skill\nfind ~\u002F.claude ~\u002F.codex ~\u002F.agents -name annotate-server.js -path '*plan-review*' 2>\u002Fdev\u002Fnull | head -1\nnode \u002Fpath\u002Fto\u002Fplan-review\u002Freferences\u002Fannotate-server.js specs\n```\n\nIf the `find` prints nothing, plan-review isn't installed — say so and offer\nthe catalog (`specs\u002Findex.md`) instead of silently skipping the browse step.\n\nSame annotation UI as plan\u002Fspec review: notes land in\n`specs\u002Freview.feedback.md`. This is browsing, not a decision gate — no\napprove\u002Fdeny polling needed unless you want it.\n\n## Notes\n\n- The catalog is a generated artifact — the header marks it \"do not edit by\n  hand.\" Editing a spec means editing that spec's own files, then re-running\n  step 1.\n- Pairs with `technical-spec` (which writes individual specs) — this skill is\n  the index over all of them. For a single spec, use plan-review's directory\n  mode (technical-spec's old standalone preview is retired); use spec-browser\n  when you have many.\n- Keep `specs\u002Findex.md` committed so agents in a fresh checkout can reference\n  the catalog without running anything.\n",{"name":5,"effort":24,"description":7,"when_to_use":25,"argument-hint":26},"low","Reach for this once a repo accumulates several specs and a single spec folder view (technical-spec's own preview) is no longer enough — you want the whole specs\u002F tree at once, plus a plain-markdown catalog for agents that have no search plugin. Not for an approve\u002Frevise decision on one plan; use plan-review.","[specs-root]","main","5277649b071c1c0cdf4f15eee861b1608fc1bbcb","skills\u002Fspec-browser",0,"https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit","https:\u002F\u002Fgithub.com\u002Fjabworks","2026-11-03 15:03:51",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add jabworks\u002Fagentic-toolkit --skill spec-browser",{"tool":40,"command":41},"bunx","bunx skills add jabworks\u002Fagentic-toolkit --skill spec-browser",{"tool":43,"command":44},"pnpm","pnpm dlx skills add jabworks\u002Fagentic-toolkit --skill spec-browser","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fspec-browser\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fbuild-index.js","SCRIPT","脚本",5331,"https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fspec-browser\u002Freferences\u002Fbuild-index.js",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fpackage.json","REFERENCE","参考文档",25,"https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fspec-browser\u002Freferences\u002Fpackage.json",[61,67,73,80,87,94],{"skillNo":62,"name":63,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7540BPNTFZH7V41P5E2S692","orphan","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcomposition\u002Fbad\u002Fskills\u002Forphan\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7540AG2KFTQ8DJMNV6806MV","no-blurb","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcomposition\u002Fbad\u002Fskills\u002Fno-blurb\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M75404N306PY1JFPQ0GGNTYB","workflow","Routes any dev task into the right execution tier (Small\u002FMedium\u002FLarge) and carries condux's operating rules — proportional effort, lazy skill loading, soft gates, implement-yourself-by-default.","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M753ZZ6TTA06GRJAG679BQ2H","usage-trace","Checks and manages durable, local usage capture — ingest, health status, and the opt-in limit snapshot — for Claude Code and Codex. Capture itself runs automatically at session start.","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fusage-trace\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M753ZSKJSF8WFS7AXR2N65SE","toolkit-skill-standards","Use when writing or reviewing a SKILL.md for jabworks\u002Fagentic-toolkit — frontmatter budgets, the trigger contract (\"Use when…\" description or when_to_use field), progressive disclosure into references\u002F, and keeping a new description out of existing skills' trigger space. Triggers include \"review this skill description\", \"write the frontmatter\", \"does this collide with an existing skill\", \"where should this content live\". Not for scaffold\u002Fsync mechanics; use toolkit-foundry.","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Ftoolkit-skill-standards\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M753ZKX3KTVYWX15A9A0WZN0","toolkit-research-frontier","Use when planning improvement work on jabworks\u002Fagentic-toolkit itself — open problems (trigger-collision automation, YAML-strict frontmatter checks, docs-catalog enforcement), existing assets, the next three concrete steps, and the four-front library-health campaign with commands and success criteria. Triggers include \"let's improve our toolkit\", \"let's improve this repo\", \"what should we improve next\", \"toolkit roadmap\", \"open problems\", \"run the health campaign\".","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Ftoolkit-research-frontier\u002FSKILL.md",[],[]]