[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DHAX1NCV3HXK4M1RMBWGAV":3,"skill-same:01M6DHAX1NCV3HXK4M1RMBWGAV":86},{"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":17,"publishedAt":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":13,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":41,"install":42,"resources":55},"01M6DHAX1NCV3HXK4M1RMBWGAV","work",null,"Work lifecycle orchestration: start, continue, pause, handoff, done, plus epic\u002Fsprint planning. Context gathering + goal-focused state-chain transitions.","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\u002Fwork\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25,26,27,28,29,30],"handoff","orchestration","planning","state","start","lifecycle","continue","context","goal","done","transitions","sprint planning","chain","2026-11-10 10:12:30",false,"---\nname: work\ndescription: \"Work lifecycle orchestration: start, continue, pause, handoff, done, plus epic\u002Fsprint planning. Context gathering + goal-focused state-chain transitions.\"\n---\n\n# Work Lifecycle\n\nOrchestrates the full lifecycle of an issue: START → (WORK) → PAUSE\u002FHANDOFF → CONTINUE → DONE, with EPIC-PLAN \u002F SPRINT for multi-phase planning. Every transition updates the state chain and preserves goal-focused context for the next session.\n\n> Don't guess — a 30-second Explore saves 30 minutes. Handoffs are goal-focused, not context dumps. Code is the oracle: when trackers and code disagree, trust the code.\n\n## Commands\n\n| Command | Purpose | Workflow |\n|-|-|-|\n| `\u002Fwork:start #N` | Begin work on issue #N (scope, branch, entry gate) | `start.md` |\n| `\u002Fwork:continue` | Resume from state files | `continue.md` |\n| `\u002Fwork:pause` | Checkpoint + commit WIP | `pause.md` |\n| `\u002Fwork:handoff` | Full context handoff to another session | `handoff.md` |\n| `\u002Fwork:done` | Verify, close issue, clear state | `done.md` |\n| `\u002Fwork:epic-plan #N` | Plan ALL sprints\u002Fphases for epic #N | `epic-plan.md` |\n| `\u002Fwork:sprint` | Transition to the next sprint | `sprint.md` |\n\n## State Chain\n\nRead in this order every session (see `docs\u002FARCHITECTURE.md` § Layer 2):\n\n1. `docs\u002FCURRENT_WORK.md` — active epic\u002Fsprint\u002Fphase pointer (+ SPEC path)\n2. `context\u002FWORKING.md` — immediate next action (append-only observation blocks)\n3. Phase `SPEC.md` — acceptance criteria + exit landmarks\n4. Phase `SCENARIOS.md` — acceptance scenarios (ATDD ENTRY GATE)\n5. Phase `PROGRESS.md` — implementation checklist (checkbox truth)\n\n**WORKING.md observation block** (append-only — stable prefix hits the cache):\n\n```markdown\n## [timestamp]\nPhase: [epic\u002Fsprint\u002Fphase pointer]\nGoal: [one sentence — what the next session should accomplish]\nCompleted: [PROGRESS #n-m or bullets]\nNext: [specific next action]\nUncommitted: [modified-but-uncommitted files, or none]\nBlockers: [none or description]\n```\n\n## Scope Classification (objective — do not self-classify)\n\nClasses and triggers are defined once in `AGENTS.md` § Scope classification (Quick, Quick (tooling), Standard+); apply that table, never a restatement.\n\n| Scope | Ceremony |\n|-|-|\n| Quick | Issue body = spec; unit tests = acceptance. No SCENARIOS. |\n| Standard+ | SPEC → SCENARIOS → RED → GREEN → VALIDATE. Plan doc if 10+ files. |\n\n## ATDD Gate\n\nThe cycle is **Plan → RED → GREEN → VALIDATE** (see `docs\u002FARCHITECTURE.md` § Layer 3).\n\n- **Entry** (`start`\u002F`continue`, Standard+): `SCENARIOS.md` must exist before any code — distill it from `SPEC.md` if missing. The stop hook `checks\u002F01-tdd-gate.sh` blocks session exit if Standard+ scope has no scenarios.\n- **Exit** (`done`\u002Fphase completion): before signaling `[PHASE_COMPLETE]`, every scenario must have a recorded RED-then-GREEN run and `PROGRESS.md` must be fully checked. Enforced by stop hooks `checks\u002F03-scenario-evidence.sh` (passing run), `checks\u002F04-tdd-cycle.sh` (RED before GREEN), `checks\u002F05-progress-evidence.sh` (no unchecked items + commit evidence). Run `\u002Fverify:complete` as the exit gate.\n\n## PROGRESS Protocol\n\nFor each item: implement → check off → commit (descriptive message). Never batch checkoffs — check off immediately after implementing. Commit trailers referencing a landmark are auto-checked off by the stop hook `actions\u002Flandmark-checkoff.sh`. When exit landmarks are met → signal `[PHASE_COMPLETE]`.\n\n---\n\n## \u002Fwork:start\n\nBegin work on an issue. Fetch the item, **anchor it in the greater plan** (read `CURRENT_WORK.md` + the epic plan for cross-sprint context), classify scope, sync remote and cut a branch, clear the ATDD entry gate for Standard+, deploy an Explore for context, then point the state chain at the new work. Full workflow: `start.md`.\n\n## \u002Fwork:continue\n\nResume from the state chain. If waking from compaction, treat as a fresh session and re-orient. Read the chain in order, detect phase\u002Fsprint transitions, verify actual state against git (drift check), clear the ATDD gate before any code, load the matching best-practices skill, deploy an Explore, and log a verification entry before resuming the immediate next task. Full workflow: `continue.md`.\n\n## \u002Fwork:pause\n\nBriefly stepping away — minimal ceremony. Timestamp, commit WIP if the tree is dirty, append a PAUSED observation block to `WORKING.md` recording the exact next task, and report what was saved. Full workflow: `pause.md`.\n\n## \u002Fwork:handoff\n\nComprehensive handoff to another session. Bring the state chain fully current, summarize done \u002F in-flight \u002F exact-next, confirm the tree is committed-and-pushed (or note uncommitted state explicitly), and emit a goal-focused handoff prompt with scope boundaries and a verification checklist. Full workflow: `handoff.md`.\n\n## \u002Fwork:done\n\nClose out verified work. Confirm the exit gate passed (`\u002Fverify:complete`, stop-hook evidence), run a code review on changed files for Standard+, make the final commit, close the issue with a summary, align docs\u002Flabels and file any deferred-work issues, clear the active pointer, then push and open a PR per the project's git workflow. Full workflow: `done.md`.\n\n## \u002Fwork:epic-plan\n\nPlan an entire epic coherently in one pass — sequential per-sprint planning loses cross-sprint coherence. Read the epic scope, deploy comprehensive explorers (architecture \u002F dependencies \u002F integration \u002F risk), optionally interview for observable outcomes, break into sprints and phases, scaffold the epic\u002Fsprint\u002Fphase folder tree with per-phase SPEC\u002FSCENARIOS\u002FPROGRESS, and point `CURRENT_WORK.md` at the first phase. Full workflow: `epic-plan.md`.\n\n## \u002Fwork:sprint\n\nAdvance to the next sprint within an epic (stays on the epic branch). Confirm the current sprint's phases passed their exit gates, read the transition context, identify the next sprint's issues, explore its scope, scaffold its plan structure if needed, advance the `CURRENT_WORK.md` pointer to the next Phase 1, and open a fresh `WORKING.md` block. Full workflow: `sprint.md`.\n","# Work Lifecycle\n\nOrchestrates the full lifecycle of an issue: START → (WORK) → PAUSE\u002FHANDOFF → CONTINUE → DONE, with EPIC-PLAN \u002F SPRINT for multi-phase planning. Every transition updates the state chain and preserves goal-focused context for the next session.\n\n> Don't guess — a 30-second Explore saves 30 minutes. Handoffs are goal-focused, not context dumps. Code is the oracle: when trackers and code disagree, trust the code.\n\n## Commands\n\n| Command | Purpose | Workflow |\n|-|-|-|\n| `\u002Fwork:start #N` | Begin work on issue #N (scope, branch, entry gate) | `start.md` |\n| `\u002Fwork:continue` | Resume from state files | `continue.md` |\n| `\u002Fwork:pause` | Checkpoint + commit WIP | `pause.md` |\n| `\u002Fwork:handoff` | Full context handoff to another session | `handoff.md` |\n| `\u002Fwork:done` | Verify, close issue, clear state | `done.md` |\n| `\u002Fwork:epic-plan #N` | Plan ALL sprints\u002Fphases for epic #N | `epic-plan.md` |\n| `\u002Fwork:sprint` | Transition to the next sprint | `sprint.md` |\n\n## State Chain\n\nRead in this order every session (see `docs\u002FARCHITECTURE.md` § Layer 2):\n\n1. `docs\u002FCURRENT_WORK.md` — active epic\u002Fsprint\u002Fphase pointer (+ SPEC path)\n2. `context\u002FWORKING.md` — immediate next action (append-only observation blocks)\n3. Phase `SPEC.md` — acceptance criteria + exit landmarks\n4. Phase `SCENARIOS.md` — acceptance scenarios (ATDD ENTRY GATE)\n5. Phase `PROGRESS.md` — implementation checklist (checkbox truth)\n\n**WORKING.md observation block** (append-only — stable prefix hits the cache):\n\n```markdown\n## [timestamp]\nPhase: [epic\u002Fsprint\u002Fphase pointer]\nGoal: [one sentence — what the next session should accomplish]\nCompleted: [PROGRESS #n-m or bullets]\nNext: [specific next action]\nUncommitted: [modified-but-uncommitted files, or none]\nBlockers: [none or description]\n```\n\n## Scope Classification (objective — do not self-classify)\n\nClasses and triggers are defined once in `AGENTS.md` § Scope classification (Quick, Quick (tooling), Standard+); apply that table, never a restatement.\n\n| Scope | Ceremony |\n|-|-|\n| Quick | Issue body = spec; unit tests = acceptance. No SCENARIOS. |\n| Standard+ | SPEC → SCENARIOS → RED → GREEN → VALIDATE. Plan doc if 10+ files. |\n\n## ATDD Gate\n\nThe cycle is **Plan → RED → GREEN → VALIDATE** (see `docs\u002FARCHITECTURE.md` § Layer 3).\n\n- **Entry** (`start`\u002F`continue`, Standard+): `SCENARIOS.md` must exist before any code — distill it from `SPEC.md` if missing. The stop hook `checks\u002F01-tdd-gate.sh` blocks session exit if Standard+ scope has no scenarios.\n- **Exit** (`done`\u002Fphase completion): before signaling `[PHASE_COMPLETE]`, every scenario must have a recorded RED-then-GREEN run and `PROGRESS.md` must be fully checked. Enforced by stop hooks `checks\u002F03-scenario-evidence.sh` (passing run), `checks\u002F04-tdd-cycle.sh` (RED before GREEN), `checks\u002F05-progress-evidence.sh` (no unchecked items + commit evidence). Run `\u002Fverify:complete` as the exit gate.\n\n## PROGRESS Protocol\n\nFor each item: implement → check off → commit (descriptive message). Never batch checkoffs — check off immediately after implementing. Commit trailers referencing a landmark are auto-checked off by the stop hook `actions\u002Flandmark-checkoff.sh`. When exit landmarks are met → signal `[PHASE_COMPLETE]`.\n\n---\n\n## \u002Fwork:start\n\nBegin work on an issue. Fetch the item, **anchor it in the greater plan** (read `CURRENT_WORK.md` + the epic plan for cross-sprint context), classify scope, sync remote and cut a branch, clear the ATDD entry gate for Standard+, deploy an Explore for context, then point the state chain at the new work. Full workflow: `start.md`.\n\n## \u002Fwork:continue\n\nResume from the state chain. If waking from compaction, treat as a fresh session and re-orient. Read the chain in order, detect phase\u002Fsprint transitions, verify actual state against git (drift check), clear the ATDD gate before any code, load the matching best-practices skill, deploy an Explore, and log a verification entry before resuming the immediate next task. Full workflow: `continue.md`.\n\n## \u002Fwork:pause\n\nBriefly stepping away — minimal ceremony. Timestamp, commit WIP if the tree is dirty, append a PAUSED observation block to `WORKING.md` recording the exact next task, and report what was saved. Full workflow: `pause.md`.\n\n## \u002Fwork:handoff\n\nComprehensive handoff to another session. Bring the state chain fully current, summarize done \u002F in-flight \u002F exact-next, confirm the tree is committed-and-pushed (or note uncommitted state explicitly), and emit a goal-focused handoff prompt with scope boundaries and a verification checklist. Full workflow: `handoff.md`.\n\n## \u002Fwork:done\n\nClose out verified work. Confirm the exit gate passed (`\u002Fverify:complete`, stop-hook evidence), run a code review on changed files for Standard+, make the final commit, close the issue with a summary, align docs\u002Flabels and file any deferred-work issues, clear the active pointer, then push and open a PR per the project's git workflow. Full workflow: `done.md`.\n\n## \u002Fwork:epic-plan\n\nPlan an entire epic coherently in one pass — sequential per-sprint planning loses cross-sprint coherence. Read the epic scope, deploy comprehensive explorers (architecture \u002F dependencies \u002F integration \u002F risk), optionally interview for observable outcomes, break into sprints and phases, scaffold the epic\u002Fsprint\u002Fphase folder tree with per-phase SPEC\u002FSCENARIOS\u002FPROGRESS, and point `CURRENT_WORK.md` at the first phase. Full workflow: `epic-plan.md`.\n\n## \u002Fwork:sprint\n\nAdvance to the next sprint within an epic (stays on the epic branch). Confirm the current sprint's phases passed their exit gates, read the transition context, identify the next sprint's issues, explore its scope, scaffold its plan structure if needed, advance the `CURRENT_WORK.md` pointer to the next Phase 1, and open a fresh `WORKING.md` block. Full workflow: `sprint.md`.\n",{"name":5,"description":7},"main","07fef474a459f2562dbae35a3baf6470c8ae530d","template\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit","https:\u002F\u002Fgithub.com\u002FJAuto-Corp","2026-11-10 13:45:22",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add JAuto-Corp\u002Fjustinventit --skill work",{"tool":48,"command":49},"bunx","bunx skills add JAuto-Corp\u002Fjustinventit --skill work",{"tool":51,"command":52},"pnpm","pnpm dlx skills add JAuto-Corp\u002Fjustinventit --skill work","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork\u002FSKILL.md",true,[56,62,66,70,74,78,82],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"continue.md","REFERENCE","参考文档",3266,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork\u002Fcontinue.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"done.md",2462,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork\u002Fdone.md",{"path":67,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":68,"sourceHtmlUrl":69},"epic-plan.md",2682,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork\u002Fepic-plan.md",{"path":71,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":72,"sourceHtmlUrl":73},"handoff.md",2091,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork\u002Fhandoff.md",{"path":75,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":76,"sourceHtmlUrl":77},"pause.md",1010,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork\u002Fpause.md",{"path":79,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":80,"sourceHtmlUrl":81},"sprint.md",2133,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork\u002Fsprint.md",{"path":83,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":84,"sourceHtmlUrl":85},"start.md",2712,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork\u002Fstart.md",[87,114,138,160,176,198],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":31},"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",[],[89,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113],"yagni","line","recipes","platform","dependencies","task","do","translation","default","general","minimal","use","question","refactoring","knowledge","dev","code","libraries","writing",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":130,"publishedAt":31},"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",[120,125],{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":126,"categoryName":127,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[131,132,133,134,135,136,137,96],"workflow skill","workflow","router","editing","file","contract","patterns",{"skillNo":139,"name":132,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":144,"publishedAt":31},"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",[143],{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},[132,145,146,147,148,149,150,151,152,153,154,106,134,155,156,157,158,159],"meta-skill","routing","framework","harness","commands","forge","discovery","shape","hooks","auto","Rules","system","Meta","docs","change",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":31},"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",[],[162,167,168,169,170,171,172,173,174,175],"type","build","gate","evidence","check","verification","acceptance","run","validate",{"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":31},"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",[],[183,184,19,185,186,187,135,188,189,190,191,192,193,5,194,195,196,197],"team lead","team","research","design","testing","wait","mechanical","pattern","agent team","coordinate","implementation","multi-agent","model","constraints","audit",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":207,"publishedAt":31},"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",[204],{"categoryNo":205,"categoryName":206,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000015","视觉设计",[200,208,209,210,211,212,169,213,5,214,215,216,217,197,218,20,159,219,186],"before building","progress","orient","domain","structure","scoping","plan","loop","equip","feeds","produce","spec"]