[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DHB1GD89RW71ZYZJZJH4ZG":3,"skill-same:01M6DHB1GD89RW71ZYZJZJH4ZG":91},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":13,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M6DHB1GD89RW71ZYZJZJH4ZG","workflow",null,"Meta-skill for editing the framework itself — skills, hooks, commands, rules, CLAUDE.md. Use before changing anything under .claude\u002F or the routing docs, so the change keeps the system's shape (lazy-load, forge markers, hook auto-discovery, harness).","JAuto-Corp\u002Fjustinventit","JAuto-Corp","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F254009312?v=4","01M6DH85D43FJAXD8RPBY6A91C","01M6DH85M60CDJBZ9W2CAFCPXE",0,"MIT","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"commands","docs","meta-skill","shape","hooks","auto","use","editing","Rules","system","discovery","Meta","forge","harness","framework","routing","change","2026-11-10 10:12:30",false,"---\nname: workflow\ndescription: \"Meta-skill for editing the framework itself — skills, hooks, commands, rules, CLAUDE.md. Use before changing anything under .claude\u002F or the routing docs, so the change keeps the system's shape (lazy-load, forge markers, hook auto-discovery, harness).\"\n---\n\n# Workflow (Self-Edit Meta-Skill)\n\nThis is how the framework safely edits ITSELF. Every artifact under `.claude\u002F` (skills, hooks, commands, rules) and the `CLAUDE.md` router follows a shape the runtime depends on. Editing one blindly breaks discovery, enforcement, or `copier update`. Read the matching operation before you touch it.\n\n> Route, don't dump. Load on demand. Enforce, don't suggest. A system artifact earns its tokens — keep every layer lean and let the layer below hold the detail. (`docs\u002FARCHITECTURE.md` § Design Principles.)\n\n## Operations\n\nOnly `edit-skill` has a command wrapper; the rest are sub-operations you reach by reading this skill. Do NOT add new wrappers.\n\n| Operation | When | Sub-file |\n|-|-|-|\n| Add \u002F edit a skill | New capability or changed workflow knowledge | `skill.md` |\n| Add \u002F edit a command | New or changed slash-command entry point | `command.md` |\n| Add \u002F edit a hook | New\u002Fchanged guard, stop check, or action | `hook.md` |\n| Edit a rule | Path-scoped domain guidance | `rule.md` |\n| Edit CLAUDE.md | The session router | `claude-md.md` |\n| Validate a change | Before committing any of the above | `validate.md` |\n\n## System map (what the runtime depends on)\n\n| Layer | Location | Contract |\n|-|-|-|\n| Router | `CLAUDE.md` (\u003C 200 lines) | Copier-managed content lives between `\u003C!-- forge:start -->` \u002F `\u003C!-- forge:end -->`; edits OUTSIDE the markers survive `copier update`. Source: `CLAUDE.md.jinja`. |\n| Skills | `.claude\u002Fskills\u002F**\u002FSKILL.md` | Lazy-loaded: only frontmatter (`name`, `description`) enters context at session start; the full body loads on invocation. Router SKILL.md + lean sub-files. |\n| Commands | `.claude\u002Fcommands\u002F\u003Cdomain>\u002F\u003Cname>.md` | Auto-discovered by path → slash command. Thin pointer into a skill. |\n| Rules | `.claude\u002Frules\u002F*.md` | Frontmatter `paths: [...]` globs; load only when Claude touches a matching file. Project-owned. |\n| Hooks | `.claude\u002Fhooks\u002F` | Stop `stop\u002Fchecks\u002F[0-9]*.sh` + `stop\u002Factions\u002F*.sh` are auto-discovered by `stop\u002Frunner.sh` (checks run in order, exit ≠0 blocks; actions never block). PreToolUse `guards\u002F*.sh` are NOT auto-discovered — register them in `settings.json`. |\n| Tests | `.claude\u002Fhooks\u002Ftests\u002F` | `harness.sh` drives a hook with no live session; suites are `test-*.sh`; `run-all.sh` aggregates them. |\n\n**Copier suffix**: a template file rendered with answer variables ends in `.jinja` (stripped on generation); a generic file is copied verbatim. Match the neighbor you are editing.\n\n## \u002Fworkflow:edit-skill\n\nThe general self-edit workflow. The `\u002Fworkflow:edit-skill` command routes here; despite the name it covers ANY system artifact — skill, hook, command, rule, or `CLAUDE.md`.\n\n1. **Identify the artifact** and read it *in full*, plus one sibling as a shape reference. Meta-work rewards full context — read before editing.\n2. **Pick the operation** from the table above and read its sub-file.\n3. **Edit, preserving shape** — keep the frontmatter contract, the router-then-sub-file split, and the line budgets. Content lives in the lowest layer that can hold it; higher layers only point.\n4. **Validate** — run the `validate.md` checklist. A hook change also needs a harness test (`hook.md`).\n5. **Record it** in the state chain (`context\u002FWORKING.md`) like any other change.\n\nFor skill-specific structure and line budgets, read `skill.md`.\n\n## Add or edit a command\n\nThin pointers only — a command reads its skill; it does not embed the workflow. Commands are auto-discovered by path, so a new file IS a new slash command; don't add one unless a genuinely new entry point is needed. Full patterns: `command.md`.\n\n## Add or edit a hook\n\nA guard (PreToolUse), a stop check, or a stop action. Stop checks\u002Factions are auto-discovered by `stop\u002Frunner.sh`; guards must be registered in `settings.json`. EVERY hook change ships with a harness test (`test-*.sh`) and a green `run-all.sh`. Full workflow: `hook.md`.\n\n## Edit a rule\n\nPath-scoped guidance that loads only for files matching its `paths:` globs — cheaper than CLAUDE.md for anything not universal. Full patterns: `rule.md`.\n\n## Edit CLAUDE.md\n\nThe router every session reads. Stay under 200 lines; framework content goes between the forge markers (in `CLAUDE.md.jinja`), project content outside them. Full guidance: `claude-md.md`.\n\n## Validate a change\n\nBefore committing any system edit: frontmatter intact, line budgets met, pointers resolve, hooks have passing harness tests, `CLAUDE.md` under budget. Full checklist: `validate.md`.\n","# Workflow (Self-Edit Meta-Skill)\n\nThis is how the framework safely edits ITSELF. Every artifact under `.claude\u002F` (skills, hooks, commands, rules) and the `CLAUDE.md` router follows a shape the runtime depends on. Editing one blindly breaks discovery, enforcement, or `copier update`. Read the matching operation before you touch it.\n\n> Route, don't dump. Load on demand. Enforce, don't suggest. A system artifact earns its tokens — keep every layer lean and let the layer below hold the detail. (`docs\u002FARCHITECTURE.md` § Design Principles.)\n\n## Operations\n\nOnly `edit-skill` has a command wrapper; the rest are sub-operations you reach by reading this skill. Do NOT add new wrappers.\n\n| Operation | When | Sub-file |\n|-|-|-|\n| Add \u002F edit a skill | New capability or changed workflow knowledge | `skill.md` |\n| Add \u002F edit a command | New or changed slash-command entry point | `command.md` |\n| Add \u002F edit a hook | New\u002Fchanged guard, stop check, or action | `hook.md` |\n| Edit a rule | Path-scoped domain guidance | `rule.md` |\n| Edit CLAUDE.md | The session router | `claude-md.md` |\n| Validate a change | Before committing any of the above | `validate.md` |\n\n## System map (what the runtime depends on)\n\n| Layer | Location | Contract |\n|-|-|-|\n| Router | `CLAUDE.md` (\u003C 200 lines) | Copier-managed content lives between `\u003C!-- forge:start -->` \u002F `\u003C!-- forge:end -->`; edits OUTSIDE the markers survive `copier update`. Source: `CLAUDE.md.jinja`. |\n| Skills | `.claude\u002Fskills\u002F**\u002FSKILL.md` | Lazy-loaded: only frontmatter (`name`, `description`) enters context at session start; the full body loads on invocation. Router SKILL.md + lean sub-files. |\n| Commands | `.claude\u002Fcommands\u002F\u003Cdomain>\u002F\u003Cname>.md` | Auto-discovered by path → slash command. Thin pointer into a skill. |\n| Rules | `.claude\u002Frules\u002F*.md` | Frontmatter `paths: [...]` globs; load only when Claude touches a matching file. Project-owned. |\n| Hooks | `.claude\u002Fhooks\u002F` | Stop `stop\u002Fchecks\u002F[0-9]*.sh` + `stop\u002Factions\u002F*.sh` are auto-discovered by `stop\u002Frunner.sh` (checks run in order, exit ≠0 blocks; actions never block). PreToolUse `guards\u002F*.sh` are NOT auto-discovered — register them in `settings.json`. |\n| Tests | `.claude\u002Fhooks\u002Ftests\u002F` | `harness.sh` drives a hook with no live session; suites are `test-*.sh`; `run-all.sh` aggregates them. |\n\n**Copier suffix**: a template file rendered with answer variables ends in `.jinja` (stripped on generation); a generic file is copied verbatim. Match the neighbor you are editing.\n\n## \u002Fworkflow:edit-skill\n\nThe general self-edit workflow. The `\u002Fworkflow:edit-skill` command routes here; despite the name it covers ANY system artifact — skill, hook, command, rule, or `CLAUDE.md`.\n\n1. **Identify the artifact** and read it *in full*, plus one sibling as a shape reference. Meta-work rewards full context — read before editing.\n2. **Pick the operation** from the table above and read its sub-file.\n3. **Edit, preserving shape** — keep the frontmatter contract, the router-then-sub-file split, and the line budgets. Content lives in the lowest layer that can hold it; higher layers only point.\n4. **Validate** — run the `validate.md` checklist. A hook change also needs a harness test (`hook.md`).\n5. **Record it** in the state chain (`context\u002FWORKING.md`) like any other change.\n\nFor skill-specific structure and line budgets, read `skill.md`.\n\n## Add or edit a command\n\nThin pointers only — a command reads its skill; it does not embed the workflow. Commands are auto-discovered by path, so a new file IS a new slash command; don't add one unless a genuinely new entry point is needed. Full patterns: `command.md`.\n\n## Add or edit a hook\n\nA guard (PreToolUse), a stop check, or a stop action. Stop checks\u002Factions are auto-discovered by `stop\u002Frunner.sh`; guards must be registered in `settings.json`. EVERY hook change ships with a harness test (`test-*.sh`) and a green `run-all.sh`. Full workflow: `hook.md`.\n\n## Edit a rule\n\nPath-scoped guidance that loads only for files matching its `paths:` globs — cheaper than CLAUDE.md for anything not universal. Full patterns: `rule.md`.\n\n## Edit CLAUDE.md\n\nThe router every session reads. Stay under 200 lines; framework content goes between the forge markers (in `CLAUDE.md.jinja`), project content outside them. Full guidance: `claude-md.md`.\n\n## Validate a change\n\nBefore committing any system edit: frontmatter intact, line budgets met, pointers resolve, hooks have passing harness tests, `CLAUDE.md` under budget. Full checklist: `validate.md`.\n",{"name":5,"description":7},"main","07fef474a459f2562dbae35a3baf6470c8ae530d","template\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit","https:\u002F\u002Fgithub.com\u002FJAuto-Corp","2026-11-10 13:45:22",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add JAuto-Corp\u002Fjustinventit --skill workflow",{"tool":57,"command":58},"bunx","bunx skills add JAuto-Corp\u002Fjustinventit --skill workflow",{"tool":60,"command":61},"pnpm","pnpm dlx skills add JAuto-Corp\u002Fjustinventit --skill workflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002FSKILL.md",true,[65,71,75,79,83,87],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"claude-md.md","REFERENCE","参考文档",1655,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002Fclaude-md.md",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"command.md",1669,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002Fcommand.md",{"path":76,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":77,"sourceHtmlUrl":78},"hook.md",2765,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002Fhook.md",{"path":80,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":81,"sourceHtmlUrl":82},"rule.md",1309,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002Frule.md",{"path":84,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":85,"sourceHtmlUrl":86},"skill.md",2059,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002Fskill.md",{"path":88,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":89,"sourceHtmlUrl":90},"validate.md",1664,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002Fvalidate.md",[92,118,135,155,171,193],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":40},"01M6DHBJE2P291DTXAW6DE6ZSR","ponytail","Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says \"ponytail\", \"be lazy\", \"lazy mode\", \"simplest solution\", \"minimal solution\", \"yagni\", \"do less\", or \"shortest path\", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Fponytail\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Fponytail\u002FSKILL.md",[],[94,100,101,102,103,104,105,106,107,108,109,110,29,111,112,113,114,115,116,117],"yagni","line","recipes","platform","dependencies","task","do","translation","default","general","minimal","question","refactoring","knowledge","dev","code","libraries","writing",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":122,"keywords":129,"publishedAt":40},"01M6DHB61PAWVGHF53A89MJ6SM","workflow\u002Fskill","Patterns for adding or editing a skill — frontmatter contract, router + sub-file split, line budgets.",[123,124],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[130,5,131,30,132,101,133,134],"workflow skill","router","file","patterns","contract",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":40},"01M6DHAX1NCV3HXK4M1RMBWGAV","work","Work lifecycle orchestration: start, continue, pause, handoff, done, plus epic\u002Fsprint planning. Context gathering + goal-focused state-chain transitions.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork\u002FSKILL.md",[],[137,142,143,144,145,146,147,148,149,150,151,152,153,154],"goal","chain","sprint planning","transitions","done","context","continue","lifecycle","start","state","planning","orchestration","handoff",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":40},"01M6DHASZYRB1ZZWVNQ6CN8FN3","verify","Verification and auditing. Validate acceptance scenarios, run multi-perspective audits, check type-check\u002Fbuild evidence, and gate phase\u002Fsprint completion.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify\u002FSKILL.md",[],[157,162,163,164,165,166,167,168,169,170],"gate","build","evidence","check","verification","acceptance","run","validate","type",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":40},"01M6DHAP9JN9X7ZSWCWYTWN1KT","team-lead","Coordinate an Agent Team for parallelizable work — implementation, audit, research, or testing. Teaches the mechanical constraints (WAIT pattern, file ownership, model tiers) and lets you design the team. For orchestration_tier=cluster \u002F multi-agent runs.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fteam-lead\u002FSKILL.md",[],[178,179,180,181,182,153,183,184,185,186,187,188,137,189,190,191,192,132],"team","team lead","research","design","testing","pattern","wait","mechanical","agent team","coordinate","implementation","multi-agent","model","constraints","audit",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":202,"publishedAt":40},"01M6DHAJTF40984VZYBZHFD52D","scope","Plan and design work before building. Invoke when starting an epic, scoping a sprint, or planning any Standard+ change: orient on what exists, equip the planning procedure + domain skills, then produce the SPEC\u002FSCENARIOS\u002FPROGRESS structure and converge it through an audit loop. Feeds \u002Fwork:epic-plan and the ATDD entry gate.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fscope\u002FSKILL.md",[199],{"categoryNo":200,"categoryName":201,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",[195,137,203,204,205,206,162,207,208,209,210,211,212,192,213,152,39,214,181],"progress","orient","domain","structure","scoping","before building","plan","loop","equip","feeds","produce","spec"]