[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DHAJTF40984VZYBZHFD52D":3,"skill-same:01M6DHAJTF40984VZYBZHFD52D":72},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":13,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":51,"install":52,"resources":65},"01M6DHAJTF40984VZYBZHFD52D","scope",null,"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.","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\u002Fscope\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"plan","progress","orient","domain","structure","gate","scoping","before building","work","design","loop","equip","feeds","audit","produce","planning","change","spec","2026-11-10 10:12:30",false,"---\nname: scope\ndescription: \"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.\"\n---\n\n# Scope — Plan and Design Work\n\n**Intent**: understand what needs building, then produce plan artifacts solid enough to hand to `\u002Fwork`.\n\n**Flow**: Orient → Equip → Act. Finish each phase before the next.\n\n`\u002Fscope` is the *planning* front of the plan → build → verify chain. It doesn't reimplement planning — it orchestrates the existing pieces (`work:epic-plan`, the ATDD gate, the `patterns` interview) and, for Standard+ work, converges the plan through an audit loop before any code is written.\n\n---\n\n## Phase 1: Orient\n\n**STEP 0 — chain state.** Read the `chain` skill (`schema.md` § Reading state) and `context\u002FCHAIN.json`. If `chain.ready_for == \"scope\"` you're RESUMING a plan-convergence loop → jump to Phase 3's loop with the saved iteration\u002Ftier. Terminal \u002F stale \u002F branch-mismatch handling: per `schema.md`.\n\nThen read, to know what exists and where this fits:\n\n| Read | Learn |\n|-|-|\n| `docs\u002FCURRENT_WORK.md` · `context\u002FWORKING.md` | What's already in flight — don't plan over active work |\n| `docs\u002FROADMAP.md` | Where this work sits in the bigger picture |\n| The issue\u002Fepic (`gh issue view N`) | Scope, constraints, acceptance criteria |\n| Existing plans under `docs\u002F` | Patterns to follow for structure |\n| `AGENTS.md` § Scope classification | **Scope classification** — decides how much planning is needed |\n\n**Scope classification is objective — do not self-classify.** Apply `AGENTS.md` § Scope classification (Quick, Quick (tooling), Standard+); the `work` skill points there too.\n\n**Refactor awareness**: note messiness in the code this work will touch — competing abstractions, dead code, pattern drift. These are refactor targets to *bundle into the plan*, not separate debt. A plan is the cheapest place to decide what to clean up.\n\n---\n\n## Phase 2: Equip\n\n| Load | When | Why |\n|-|-|-|\n| `Skill(skill: \"work:epic-plan\")` | Epic (3+ sprints) | The full planning procedure — explorer waves, folder tree, state-chain updates |\n| `work` skill § scope + PROGRESS | Single sprint\u002Fphase | Sprint-level planning shape |\n| Matching skill(s) in `.claude\u002Fskills\u002Fdomain\u002F` | The work touches that domain | SPECs written without domain conventions drift — wrong names, missing constraints |\n| `patterns` skill § Interview | Outcomes the code can't answer | Structured Q&A before writing the SPEC |\n| `team-lead` | Parallel explorer\u002Faudit waves | Spawn templates, file ownership |\n\n**Quick scope** (as classified by `AGENTS.md` § Scope classification): skip Phase 2 — domain skills load too much context for a small fix.\n\n---\n\n## Phase 3: Act\n\nPick the approach for the scope, then execute:\n\n| Situation | Approach |\n|-|-|\n| New epic | Run the `work:epic-plan` workflow you loaded |\n| Single phase in a planned epic | Author its `SPEC.md` \u002F `SCENARIOS.md` \u002F `PROGRESS.md` |\n| Quick scope | No formal plan — assess and start |\n| Investigation \u002F research | Deploy explorers (`patterns` § Multi-Explorer), report findings |\n\n**Output shape** (Standard+): each phase gets `SPEC.md` (acceptance criteria + exit landmarks), `SCENARIOS.md` (the ATDD contract — must exist before any code; the stop check `checks\u002F01-tdd-gate` blocks Standard+ scope with no scenarios), and `PROGRESS.md` (implementation checklist). This is the entry gate `\u002Fwork` inherits.\n\n**If scope isn't clear**: ask one focusing question. Ten seconds saves thirty minutes of wrong-direction work.\n\n### Grounding self-check (before the audit loop)\n\nCheap pass over every SPEC authored this round, catching the drift an audit would otherwise burn cycles on:\n\n1. **Named things exist.** Every function\u002Froute\u002Ftype\u002Ftable the SPEC cites: grep the codebase. Present → ok. Absent but declared in this SPEC's own scope → ok (new surface). Absent and undeclared → hallucination; remove it or expand scope. Don't write names from memory.\n2. **Numbers are sourced.** Every numeric fact (cutoffs, thresholds, counts) cites its source inline, or the SPEC is rewritten range-tolerant \u002F to read the value dynamically. Unsourced literals are the highest-risk drift.\n3. **Consumer claims are concrete.** Every \"consumed by X \u002F downstream reads Y\" names the consumer file, or is rewritten as forward-compat. Don't claim a reader that doesn't exist yet.\n\nClean → enter the audit loop. Issues → fix the SPEC, re-check, then enter.\n\n### Plan-convergence loop (Standard+)\n\nAfter the plan docs are written, converge them through escalating audit rounds — revise the plan between rounds, don't just re-run the audit. Tier ladder, exit rules, and chain I\u002FO: **`converge.md`**. Skip only if the user says \"just plan this, skip the audit\" — record the skip in `context\u002FWORKING.md` so the next agent knows.\n\n---\n\n## Related\n\n- Plan-convergence loop: `converge.md`\n- Convergence machinery: `chain` skill\n- Executing the plan: `work` skill (`\u002Fwork:continue`)\n- Verifying the built result: `check` skill\n","# Scope — Plan and Design Work\n\n**Intent**: understand what needs building, then produce plan artifacts solid enough to hand to `\u002Fwork`.\n\n**Flow**: Orient → Equip → Act. Finish each phase before the next.\n\n`\u002Fscope` is the *planning* front of the plan → build → verify chain. It doesn't reimplement planning — it orchestrates the existing pieces (`work:epic-plan`, the ATDD gate, the `patterns` interview) and, for Standard+ work, converges the plan through an audit loop before any code is written.\n\n---\n\n## Phase 1: Orient\n\n**STEP 0 — chain state.** Read the `chain` skill (`schema.md` § Reading state) and `context\u002FCHAIN.json`. If `chain.ready_for == \"scope\"` you're RESUMING a plan-convergence loop → jump to Phase 3's loop with the saved iteration\u002Ftier. Terminal \u002F stale \u002F branch-mismatch handling: per `schema.md`.\n\nThen read, to know what exists and where this fits:\n\n| Read | Learn |\n|-|-|\n| `docs\u002FCURRENT_WORK.md` · `context\u002FWORKING.md` | What's already in flight — don't plan over active work |\n| `docs\u002FROADMAP.md` | Where this work sits in the bigger picture |\n| The issue\u002Fepic (`gh issue view N`) | Scope, constraints, acceptance criteria |\n| Existing plans under `docs\u002F` | Patterns to follow for structure |\n| `AGENTS.md` § Scope classification | **Scope classification** — decides how much planning is needed |\n\n**Scope classification is objective — do not self-classify.** Apply `AGENTS.md` § Scope classification (Quick, Quick (tooling), Standard+); the `work` skill points there too.\n\n**Refactor awareness**: note messiness in the code this work will touch — competing abstractions, dead code, pattern drift. These are refactor targets to *bundle into the plan*, not separate debt. A plan is the cheapest place to decide what to clean up.\n\n---\n\n## Phase 2: Equip\n\n| Load | When | Why |\n|-|-|-|\n| `Skill(skill: \"work:epic-plan\")` | Epic (3+ sprints) | The full planning procedure — explorer waves, folder tree, state-chain updates |\n| `work` skill § scope + PROGRESS | Single sprint\u002Fphase | Sprint-level planning shape |\n| Matching skill(s) in `.claude\u002Fskills\u002Fdomain\u002F` | The work touches that domain | SPECs written without domain conventions drift — wrong names, missing constraints |\n| `patterns` skill § Interview | Outcomes the code can't answer | Structured Q&A before writing the SPEC |\n| `team-lead` | Parallel explorer\u002Faudit waves | Spawn templates, file ownership |\n\n**Quick scope** (as classified by `AGENTS.md` § Scope classification): skip Phase 2 — domain skills load too much context for a small fix.\n\n---\n\n## Phase 3: Act\n\nPick the approach for the scope, then execute:\n\n| Situation | Approach |\n|-|-|\n| New epic | Run the `work:epic-plan` workflow you loaded |\n| Single phase in a planned epic | Author its `SPEC.md` \u002F `SCENARIOS.md` \u002F `PROGRESS.md` |\n| Quick scope | No formal plan — assess and start |\n| Investigation \u002F research | Deploy explorers (`patterns` § Multi-Explorer), report findings |\n\n**Output shape** (Standard+): each phase gets `SPEC.md` (acceptance criteria + exit landmarks), `SCENARIOS.md` (the ATDD contract — must exist before any code; the stop check `checks\u002F01-tdd-gate` blocks Standard+ scope with no scenarios), and `PROGRESS.md` (implementation checklist). This is the entry gate `\u002Fwork` inherits.\n\n**If scope isn't clear**: ask one focusing question. Ten seconds saves thirty minutes of wrong-direction work.\n\n### Grounding self-check (before the audit loop)\n\nCheap pass over every SPEC authored this round, catching the drift an audit would otherwise burn cycles on:\n\n1. **Named things exist.** Every function\u002Froute\u002Ftype\u002Ftable the SPEC cites: grep the codebase. Present → ok. Absent but declared in this SPEC's own scope → ok (new surface). Absent and undeclared → hallucination; remove it or expand scope. Don't write names from memory.\n2. **Numbers are sourced.** Every numeric fact (cutoffs, thresholds, counts) cites its source inline, or the SPEC is rewritten range-tolerant \u002F to read the value dynamically. Unsourced literals are the highest-risk drift.\n3. **Consumer claims are concrete.** Every \"consumed by X \u002F downstream reads Y\" names the consumer file, or is rewritten as forward-compat. Don't claim a reader that doesn't exist yet.\n\nClean → enter the audit loop. Issues → fix the SPEC, re-check, then enter.\n\n### Plan-convergence loop (Standard+)\n\nAfter the plan docs are written, converge them through escalating audit rounds — revise the plan between rounds, don't just re-run the audit. Tier ladder, exit rules, and chain I\u002FO: **`converge.md`**. Skip only if the user says \"just plan this, skip the audit\" — record the skip in `context\u002FWORKING.md` so the next agent knows.\n\n---\n\n## Related\n\n- Plan-convergence loop: `converge.md`\n- Convergence machinery: `chain` skill\n- Executing the plan: `work` skill (`\u002Fwork:continue`)\n- Verifying the built result: `check` skill\n",{"name":5,"description":7},"main","07fef474a459f2562dbae35a3baf6470c8ae530d","template\u002F.claude\u002Fskills\u002Forchestrators\u002Fscope","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit","https:\u002F\u002Fgithub.com\u002FJAuto-Corp","2026-11-10 13:45:22",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add JAuto-Corp\u002Fjustinventit --skill scope",{"tool":58,"command":59},"bunx","bunx skills add JAuto-Corp\u002Fjustinventit --skill scope",{"tool":61,"command":62},"pnpm","pnpm dlx skills add JAuto-Corp\u002Fjustinventit --skill scope","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fscope\u002FSKILL.md",true,[66],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"converge.md","REFERENCE","参考文档",2745,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fscope\u002Fconverge.md",[73,100,122,143,161,176],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":41},"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",[],[75,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99],"writing","yagni","line","recipes","platform","dependencies","task","do","translation","default","general","minimal","use","question","refactoring","knowledge","dev","code","libraries",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":114,"publishedAt":41},"01M6DHB61PAWVGHF53A89MJ6SM","workflow\u002Fskill","Patterns for adding or editing a skill — frontmatter contract, router + sub-file split, line budgets.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002Fskill.md",[106,109],{"categoryNo":107,"categoryName":108,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[115,116,117,118,119,120,121,83],"workflow skill","workflow","patterns","router","editing","file","contract",{"skillNo":123,"name":116,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":128,"publishedAt":41},"01M6DHB1GD89RW71ZYZJZJH4ZG","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).","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002FSKILL.md",[127],{"categoryNo":107,"categoryName":108,"taxonomyType":20,"taxonomyTypeDesc":21},[116,129,130,131,132,133,93,119,134,135,136,137,138,139,39,140,141,142],"commands","meta-skill","shape","hooks","auto","Rules","system","discovery","Meta","forge","harness","routing","docs","framework",{"skillNo":144,"name":31,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":41},"01M6DHAX1NCV3HXK4M1RMBWGAV","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",[],[31,149,150,151,152,153,154,155,156,157,158,38,159,160],"continue","chain","sprint planning","transitions","done","goal","context","lifecycle","start","state","orchestration","handoff",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":41},"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",[],[163,168,169,170,171,172,173,174,175,28],"check","verification","acceptance","run","validate","evidence","type","build",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":41},"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",[],[183,184,185,186,187,188,189,190,31,191,192,193,36,120,159,194,32,195],"team","team lead","implementation","wait","mechanical","pattern","agent team","coordinate","multi-agent","model","constraints","research","testing"]