[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DH9T64RXTPZXAYVKWKST9R":3,"skill-same:01M6DH9T64RXTPZXAYVKWKST9R":83},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":13,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":42,"install":43,"resources":56},"01M6DH9T64RXTPZXAYVKWKST9R","capture",null,"Turn signals surfaced during work into tracked issues. Park discoveries and keep moving; convert audit\u002Fsession findings to issues; block, triage, and roll up into epics — the human side of the self-improvement loop.","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\u002Fcapture\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"to issues","triage","issues","audit","loop","convert","work","session","up","park","self-improvement","self","human","signals","2026-11-10 10:12:30",false,"---\nname: capture\ndescription: \"Turn signals surfaced during work into tracked issues. Park discoveries and keep moving; convert audit\u002Fsession findings to issues; block, triage, and roll up into epics — the human side of the self-improvement loop.\"\n---\n\n# Capture\n\nSignals in, issues out. During work you surface things outside the current task — a blocker, a defect, an adjacent idea, or system friction. Emit a signal and keep moving; the stop actions log it; `capture` is the deliberate pass that turns those logs into tracked issues (and framework fixes). This closes the feedback loop `docs\u002FSELF_IMPROVEMENT.md` describes.\n\n> Park it and keep moving. A discovery you chase mid-task is two tasks half-done. Capture fast, label correctly, continue — then process the parking lot on purpose.\n\n## Commands\n\n| Command | Purpose | Workflow |\n|-|-|-|\n| `\u002Fcapture:block` | File a `status:blocked` issue for an external blocker | `block.md` |\n| `\u002Fcapture:audit` | Convert `\u002Fverify:audit` findings into issues | `audit.md` |\n| `\u002Fcapture:findings` | Convert session discoveries (`DISCOVERIES.md`) into issues | `findings.md` |\n| `\u002Fcapture:triage` | Classify parked `captured` issues; label, prioritize, route | `triage.md` |\n| `\u002Fcapture:epic` | Group related captured issues into a new epic | `epic.md` |\n\n## The feedback loop (what feeds this skill)\n\nTwo append-only logs collect signals automatically — never edit them by hand as a workaround; process them here.\n\n| Log | Written by (stop action) | From signal | Capture processes it via |\n|-|-|-|-|\n| `context\u002FDISCOVERIES.md` | `stop\u002Factions\u002Fdiscovery-extraction.sh` | `[DISCOVERY:*]` | `findings` → issues |\n| `context\u002FFRICTION_LOG.md` | `stop\u002Factions\u002Ffriction-extraction.sh` | `[FRICTION:*]` | classify PROJECT\u002FFRAMEWORK (below) |\n\nThe signal vocabulary lives in the `patterns` skill (§ Discovery Signals, § Friction Signals). Stop actions never block — they only append; acting on the logs is this skill's job.\n\n**Discovery signals** (outside current scope):\n\n| Signal | Meaning | Typical action |\n|-|-|-|\n| `[DISCOVERY:BLOCKER]` | Blocks current work | `\u002Fcapture:block`, then keep moving |\n| `[DISCOVERY:DEFECT]` | Bug found during work | Issue, continue |\n| `[DISCOVERY:ADJACENT]` | Related, not blocking | Issue, continue |\n| `[DISCOVERY:DISTANT]` | Unrelated finding | Issue, continue |\n\n## Processing friction (PROJECT vs FRAMEWORK)\n\n`FRICTION_LOG.md` entries land tagged `Classification: TODO`. Resolve each per `docs\u002FSELF_IMPROVEMENT.md` § Classification Guide:\n\n- **PROJECT** — a local skill\u002Fhook\u002Frule was wrong for this codebase. Fix the artifact in-repo (see the `workflow` skill), then set `Resolution:` on the log entry.\n- **FRAMEWORK** — an orchestration\u002Fhook\u002Fstate-format problem shared by every project. File it upstream, then let `copier update` pull the fix back:\n\n```bash\ngh issue create --repo JAuto-Corp\u002Fjustinventit \\\n  --title \"FRICTION: \u003Cone line>\" --body \"\u003Clog entry + why it's framework-level>\"\n```\n\n## Label taxonomy (generic — projects extend)\n\nEvery captured issue carries the base `captured` label plus a type and priority. Keep it lean; the project defines its own domain labels.\n\n| Facet | Values |\n|-|-|\n| Base | `captured` (set on creation; removed once triaged\u002Fassigned) |\n| Type | `bug`, `enhancement`, `tech-debt` |\n| Priority | `p0` (now), `p1` (this sprint), `p2` (planned) |\n| Status | `status:blocked` |\n| Lineage | `epic:N`, `discovered:from-#N` |\n\n## Coherence\n\nCapture writes issues + logs; it does not merge PRs or move work state. Blockers promoted here land in `context\u002FWORKING.md` (Blockers) and, when they gate a phase, `docs\u002FCURRENT_WORK.md`. Epics created here are planned later by `\u002Fwork:epic-plan`. Verify code state before recording — trust the code over the tracker.\n\n---\n\n## \u002Fcapture:block\n\nFile a blocked issue when an external dependency stops progress. Create the issue with `status:blocked`, record the blocker in `context\u002FWORKING.md` (and `docs\u002FCURRENT_WORK.md` if it gates a phase), append a `[DISCOVERY:BLOCKER]` line to `context\u002FDISCOVERIES.md`, then keep moving on unblocked work. Full workflow: `block.md`.\n\n## \u002Fcapture:audit\n\nConvert the findings from a prior `\u002Fverify:audit` run into tracked issues. Confirm each finding is still valid and not a duplicate, create one `captured` issue per actionable finding (grouping duplicates, mapping severity → priority), and append `[DISCOVERY:*]` lines to `context\u002FDISCOVERIES.md` linking the created issues. Full workflow: `audit.md`.\n\n## \u002Fcapture:findings\n\nProcess the session's discoveries — the `[DISCOVERY:*]` entries the stop action collected in `context\u002FDISCOVERIES.md`, plus any surfaced live — into issues. Read the log, skip already-tracked items, create one `captured` issue per open discovery, and annotate the log entry with the issue number. Full workflow: `findings.md`.\n\n## \u002Fcapture:triage\n\nGive the parking lot a pass. List open `captured` issues, classify each by discovery type (blocker \u002F defect \u002F adjacent \u002F distant), set type + priority labels, promote blockers into the active state chain, and leave the rest parked with the `captured` label removed. Full workflow: `triage.md`.\n\n## \u002Fcapture:epic\n\nWhen several captured issues share a theme, group them into a new epic issue that links them as its scope, and note the epic in the state chain for a later `\u002Fwork:epic-plan`. This creates a NEW epic — routing issues into EXISTING epics is `\u002Fcapture:triage`. Full workflow: `epic.md`.\n","# Capture\n\nSignals in, issues out. During work you surface things outside the current task — a blocker, a defect, an adjacent idea, or system friction. Emit a signal and keep moving; the stop actions log it; `capture` is the deliberate pass that turns those logs into tracked issues (and framework fixes). This closes the feedback loop `docs\u002FSELF_IMPROVEMENT.md` describes.\n\n> Park it and keep moving. A discovery you chase mid-task is two tasks half-done. Capture fast, label correctly, continue — then process the parking lot on purpose.\n\n## Commands\n\n| Command | Purpose | Workflow |\n|-|-|-|\n| `\u002Fcapture:block` | File a `status:blocked` issue for an external blocker | `block.md` |\n| `\u002Fcapture:audit` | Convert `\u002Fverify:audit` findings into issues | `audit.md` |\n| `\u002Fcapture:findings` | Convert session discoveries (`DISCOVERIES.md`) into issues | `findings.md` |\n| `\u002Fcapture:triage` | Classify parked `captured` issues; label, prioritize, route | `triage.md` |\n| `\u002Fcapture:epic` | Group related captured issues into a new epic | `epic.md` |\n\n## The feedback loop (what feeds this skill)\n\nTwo append-only logs collect signals automatically — never edit them by hand as a workaround; process them here.\n\n| Log | Written by (stop action) | From signal | Capture processes it via |\n|-|-|-|-|\n| `context\u002FDISCOVERIES.md` | `stop\u002Factions\u002Fdiscovery-extraction.sh` | `[DISCOVERY:*]` | `findings` → issues |\n| `context\u002FFRICTION_LOG.md` | `stop\u002Factions\u002Ffriction-extraction.sh` | `[FRICTION:*]` | classify PROJECT\u002FFRAMEWORK (below) |\n\nThe signal vocabulary lives in the `patterns` skill (§ Discovery Signals, § Friction Signals). Stop actions never block — they only append; acting on the logs is this skill's job.\n\n**Discovery signals** (outside current scope):\n\n| Signal | Meaning | Typical action |\n|-|-|-|\n| `[DISCOVERY:BLOCKER]` | Blocks current work | `\u002Fcapture:block`, then keep moving |\n| `[DISCOVERY:DEFECT]` | Bug found during work | Issue, continue |\n| `[DISCOVERY:ADJACENT]` | Related, not blocking | Issue, continue |\n| `[DISCOVERY:DISTANT]` | Unrelated finding | Issue, continue |\n\n## Processing friction (PROJECT vs FRAMEWORK)\n\n`FRICTION_LOG.md` entries land tagged `Classification: TODO`. Resolve each per `docs\u002FSELF_IMPROVEMENT.md` § Classification Guide:\n\n- **PROJECT** — a local skill\u002Fhook\u002Frule was wrong for this codebase. Fix the artifact in-repo (see the `workflow` skill), then set `Resolution:` on the log entry.\n- **FRAMEWORK** — an orchestration\u002Fhook\u002Fstate-format problem shared by every project. File it upstream, then let `copier update` pull the fix back:\n\n```bash\ngh issue create --repo JAuto-Corp\u002Fjustinventit \\\n  --title \"FRICTION: \u003Cone line>\" --body \"\u003Clog entry + why it's framework-level>\"\n```\n\n## Label taxonomy (generic — projects extend)\n\nEvery captured issue carries the base `captured` label plus a type and priority. Keep it lean; the project defines its own domain labels.\n\n| Facet | Values |\n|-|-|\n| Base | `captured` (set on creation; removed once triaged\u002Fassigned) |\n| Type | `bug`, `enhancement`, `tech-debt` |\n| Priority | `p0` (now), `p1` (this sprint), `p2` (planned) |\n| Status | `status:blocked` |\n| Lineage | `epic:N`, `discovered:from-#N` |\n\n## Coherence\n\nCapture writes issues + logs; it does not merge PRs or move work state. Blockers promoted here land in `context\u002FWORKING.md` (Blockers) and, when they gate a phase, `docs\u002FCURRENT_WORK.md`. Epics created here are planned later by `\u002Fwork:epic-plan`. Verify code state before recording — trust the code over the tracker.\n\n---\n\n## \u002Fcapture:block\n\nFile a blocked issue when an external dependency stops progress. Create the issue with `status:blocked`, record the blocker in `context\u002FWORKING.md` (and `docs\u002FCURRENT_WORK.md` if it gates a phase), append a `[DISCOVERY:BLOCKER]` line to `context\u002FDISCOVERIES.md`, then keep moving on unblocked work. Full workflow: `block.md`.\n\n## \u002Fcapture:audit\n\nConvert the findings from a prior `\u002Fverify:audit` run into tracked issues. Confirm each finding is still valid and not a duplicate, create one `captured` issue per actionable finding (grouping duplicates, mapping severity → priority), and append `[DISCOVERY:*]` lines to `context\u002FDISCOVERIES.md` linking the created issues. Full workflow: `audit.md`.\n\n## \u002Fcapture:findings\n\nProcess the session's discoveries — the `[DISCOVERY:*]` entries the stop action collected in `context\u002FDISCOVERIES.md`, plus any surfaced live — into issues. Read the log, skip already-tracked items, create one `captured` issue per open discovery, and annotate the log entry with the issue number. Full workflow: `findings.md`.\n\n## \u002Fcapture:triage\n\nGive the parking lot a pass. List open `captured` issues, classify each by discovery type (blocker \u002F defect \u002F adjacent \u002F distant), set type + priority labels, promote blockers into the active state chain, and leave the rest parked with the `captured` label removed. Full workflow: `triage.md`.\n\n## \u002Fcapture:epic\n\nWhen several captured issues share a theme, group them into a new epic issue that links them as its scope, and note the epic in the state chain for a later `\u002Fwork:epic-plan`. This creates a NEW epic — routing issues into EXISTING epics is `\u002Fcapture:triage`. Full workflow: `epic.md`.\n",{"name":5,"description":7},"main","07fef474a459f2562dbae35a3baf6470c8ae530d","template\u002F.claude\u002Fskills\u002Forchestrators\u002Fcapture","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit","https:\u002F\u002Fgithub.com\u002FJAuto-Corp","2026-11-10 13:45:22",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add JAuto-Corp\u002Fjustinventit --skill capture",{"tool":49,"command":50},"bunx","bunx skills add JAuto-Corp\u002Fjustinventit --skill capture",{"tool":52,"command":53},"pnpm","pnpm dlx skills add JAuto-Corp\u002Fjustinventit --skill capture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fcapture\u002FSKILL.md",true,[57,63,67,71,75,79],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"audit.md","REFERENCE","参考文档",1783,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fcapture\u002Faudit.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"block.md",1678,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fcapture\u002Fblock.md",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"epic.md",1778,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fcapture\u002Fepic.md",{"path":72,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":73,"sourceHtmlUrl":74},"findings.md",1908,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fcapture\u002Ffindings.md",{"path":76,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":77,"sourceHtmlUrl":78},"index.json",516,"https:\u002F\u002Fgithub.com\u002FDCx7C5\u002Fai-marketplace\u002Fblob\u002Fmain\u002Fskills\u002Fcloud-security-secrets-manage\u002Findex.json",{"path":80,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":81,"sourceHtmlUrl":82},"triage.md",2036,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fcapture\u002Ftriage.md",[84,111,135,157,176,192],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":32},"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",[],[86,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110],"writing","yagni","line","recipes","platform","dependencies","task","do","translation","default","general","minimal","use","question","refactoring","knowledge","dev","code","libraries",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":127,"publishedAt":32},"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",[117,122],{"categoryNo":118,"categoryName":119,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":123,"categoryName":124,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[128,129,130,131,132,133,134,94],"workflow skill","workflow","patterns","router","editing","file","contract",{"skillNo":136,"name":129,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":141,"publishedAt":32},"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",[140],{"categoryNo":118,"categoryName":119,"taxonomyType":120,"taxonomyTypeDesc":121},[129,142,143,144,145,146,104,132,147,148,149,150,151,152,153,154,155,156],"commands","meta-skill","shape","hooks","auto","Rules","system","discovery","Meta","forge","harness","change","routing","docs","framework",{"skillNo":158,"name":24,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":32},"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",[],[24,163,164,165,166,167,168,169,170,171,172,173,174,175],"continue","chain","sprint planning","transitions","done","goal","context","lifecycle","start","state","planning","orchestration","handoff",{"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":32},"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",[],[178,183,184,185,186,187,188,189,190,191],"check","verification","acceptance","run","validate","evidence","type","build","gate",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":198,"publishedAt":32},"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",[],[199,200,201,202,203,204,205,206,24,207,208,209,21,133,174,210,211,212],"team","team lead","implementation","wait","mechanical","pattern","agent team","coordinate","multi-agent","model","constraints","research","design","testing"]