[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JS28D19EP428BECVQFB0M":3,"skill-same:01M71JS28D19EP428BECVQFB0M":67},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":6,"updatedAt":52,"install":53,"resources":66},"01M71JS28D19EP428BECVQFB0M","orchestrate-project",null,"Meta-skill that enforces the 6-phase core loop (discover → elaborate → plan → build → verify → release) with hard gates. Use to coordinate multi-phase projects with guaranteed quality checkpoints. One-time command for the entire project lifecycle.","danielvm-git\u002Fbigpowers","danielvm-git","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1020864?v=4","01M71H1N1CTQ529S0KN7KETVG6","Daniel V M","01M71H1N218Y3S8WHCJ58NPRSW",290,"MIT","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Forchestrate-project\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"project","orchestrate project","orchestrate","use","lifecycle","for","core","checkpoints","sonnet","release","command","plan","phase","loop","Meta","meta-skill","time","discover","projects","coordinate","2026-11-10 10:12:30",false,"---\nname: orchestrate-project\nmodel: sonnet\ndescription: \"Meta-skill that enforces the 6-phase core loop (discover → elaborate → plan → build → verify → release) with hard gates. Use to coordinate multi-phase projects with guaranteed quality checkpoints. One-time command for the entire project lifecycle.\"\n---\n\n# Orchestrate\n> **HARD GATE** — **HARD GATE** — Do NOT invoke orchestrate-project unless you have a clear multi-phase workflow. Single-skill tasks should use dedicated skills instead. Orchestrate is for complex, multi-stage work that requires coordination across phases.\n\n\nThe orchestrate skill coordinates projects through a prescriptive 6-phase core loop with hard gates, ensuring consistent quality and preventing scope creep.\n\n## Quick Start\n\n```bash\n# Start a new project (initializes specs\u002F YAML cockpit and begins discover phase)\nclaude \u002Forchestrate --mode standard\n\n# Or resume an existing project at the current phase\nclaude \u002Forchestrate --mode standard --resume\n\n# For low-risk scenarios (hotfixes, refactors on well-tested code)\nclaude \u002Forchestrate --mode fast-track\n```\n\n## The 6-Phase Core Loop\n\n1. **DISCOVER** (3-6 hours): Understand problem. Deliverables: `requirements\u002FVISION_LATEST.yaml`, `requirements\u002FSCOPE_LATEST.yaml`, `plans\u002FTECH_STACK_LATEST.md`.\n2. **ELABORATE** (3-6 hours): Research solutions. Deliverables: Prior art in scope YAML, ADRs in `specs\u002Fadr\u002F`.\n3. **PLAN** (2-4 hours): Write verifiable plan. Deliverables: `release-plan.yaml`, `epics\u002FeNN-*.yaml` with `verify:` per task.\n4. **BUILD** (1-8 hours): Execute plan. Runs build-epic once per story in WSJF order. Deliverables: Code; update `execution-status.yaml`.\n5. **VERIFY** (1-3 hours): Validate success criteria. Deliverables: UAT evidence, `specs\u002FEVALS-*.md` if used.\n6. **RELEASE** (30 min - 2 hours): Ship to production. Deliverables: Release tag (vX.Y.Z), `state.yaml` `release.last_tag`.\n\n### Checkpoint \u002F resume\n\nTrack progress via `specs\u002Fstate.yaml` `project_cycle`:\n- `project_cycle.current_phase`: current phase (1–6)\n- `project_cycle.completed_phases`: completed phase numbers\n- `handoff.next_skill`: skill for the current phase\n- On resume, read `project_cycle.current_phase` and continue from there\n\nSee [REFERENCE.md](REFERENCE.md) for detailed phase specifications and gate types.\n\n## How Orchestrate Works\n\n1. **Maintains state.yaml** — Tracks current phase, `active_epic`, `active_flow`, decisions, risks.\n2. **Spawns appropriate skills** — Routes by `model:` frontmatter. Decisions pass only via `specs\u002Fstate.yaml` `handoff` between spawns.\n3. **Methodology lenses** — If `specs\u002Ftech-architecture\u002Fe*-TEST_PLAN_LATEST.md` or ADRs exist, apply at phase gates.\n4. **Enforces gates** — Hard stops if success criteria not met.\n5. **The Gatekeeper** — Between stories in BUILD: read `specs\u002Fexecution-status.yaml`; previous story must be `done` before starting the next; use `build-epic` for the 8-step epic cycle.\n6. **Pauses for confirmation** — After each phase, asks \"Ready to proceed?\".\n7. **Snapshots** — `bash scripts\u002Fbp-yaml-snapshot.sh` before major release cuts.\n\n## Orchestration Modes\n\n- **Standard**: Enforce all gates. Use for new features and major refactors.\n- **Fast-Track**: Skip negotiable gates. Use for hotfixes and minor improvements.\n- **Ad-Hoc**: Warnings only. Use for prototyping and spikes (non-production).\n\nSee [REFERENCE.md](REFERENCE.md) for full mode behaviors.\n\n## Verification\n\nAll phases complete with artifacts:\n```bash\nverify: test -f specs\u002Fstate.yaml && test -f specs\u002Frelease-plan.yaml && test -f specs\u002Fproduct\u002FSCOPE_LATEST.yaml && ls specs\u002Fepics\u002F*.yaml 1>\u002Fdev\u002Fnull && echo \"✅ All phases complete\"\n```\n\n\n\n\u003C!-- story: e05s03 -->\n\n---\n\n# Orchestrate Reference: Phases, Modes, and Workflows\n\nDetailed documentation for the `orchestrate-project` meta-skill.\n\n## The 6-Phase Core Loop\n\n### PHASE 1: DISCOVER\n- **Goal**: Understand the problem completely and map existing context.\n- **Deliverables**: `requirements\u002FVISION_LATEST.yaml`, `requirements\u002FSCOPE_LATEST.yaml`, `plans\u002FTECH_STACK_LATEST.md`.\n- **Skills**: `survey-context`, `elaborate-spec`, `grill-me`.\n- **Gate**: Confirm (\"Is the problem clear?\").\n\n### PHASE 2: ELABORATE\n- **Goal**: Research solutions and lock architectural design.\n- **Deliverables**: Prior art in scope YAML, ADRs in `specs\u002Fadr\u002F`.\n- **Skills**: `grill-me`, `model-domain`, `define-language`, `deepen-architecture`, `design-interface`.\n- **Gate**: Quality ≥94% (via `request-review`) + Confirm (\"Are decisions locked?\").\n\n### PHASE 3: PLAN\n- **Goal**: Write a verifiable implementation plan with success criteria.\n- **Deliverables**: `release-plan.yaml`, `epics\u002FeNN-*.yaml` with `verify:` per task.\n- **Skills**: `scope-work`, `slice-tasks`, `plan-work`.\n- **Gate**: Quality (request-review ≥94%) + slopcheck [SUS]\u002F[SLOP].\n\n### PHASE 4: BUILD\n- **Goal**: Execute the plan story-by-story using the 8-step `build-epic` cycle with TDD and vertical slices.\n- **Deliverables**: Code; `execution-status.yaml` updated per story; `specs\u002Fmetrics\u002Fcycle-times.yaml` row per story.\n- **Skills**: `build-epic` (conductor) → per-story: `survey-context`, `plan-work`, `kickoff-branch`, `develop-tdd`, `verify-work`, `audit-code`, `commit-message`, `release-branch`.\n- **BCP tracking**: `plan-release` sizes each story in Business Complexity Points (BCP) before the build queue; `plan-work` confirms and writes the size to `state.yaml` as `epic_cycle.story_bcps`. See `docs\u002Freferences\u002Fbcp.md` for the canonical sizing method.\n- **Timestamps**: `survey-context` stamps `metrics.story_start`; `release-branch` stamps `metrics.story_end` and writes BCP\u002Fhr to `specs\u002Fmetrics\u002Fcycle-times.yaml`.\n- **next_skill**: Each critical-path skill writes `handoff.next_skill` to `state.yaml`. Agents resume by reading `state.yaml` — no guessing.\n- **Dashboard**: `npm run dashboard` (TUI) or `npm run dashboard:web` (browser, port 7742) shows live pipeline, epic queue, BCP metrics, and cycle-time ledger.\n- **Gate**: Integration tests PASS; all 8 build-epic steps completed per story.\n\n### PHASE 5: VERIFY\n- **Goal**: Validate success criteria and ensure production readiness.\n- **Deliverables**: UAT evidence, eval results.\n- **Skills**: `run-evals`, `verify-work`, `audit-code`, `request-review` (optional).\n- **Gate**: Verification Script confirmed; `verify-work` not on `main`\u002F`master`.\n\n### PHASE 6: RELEASE (Integrate)\n- **Goal**: Ship to `main` with full traceability.\n- **Deliverables**: Release tag (vX.Y.Z), release notes via semantic-release.\n- **Skills**: `commit-message`, `release-branch`.\n- **Git arc**:\n  1. Plan on `main` (Discover \u002F Plan)\n  2. `kickoff-branch` → worktree + feature branch + clean baseline\n  3. Build \u002F Verify \u002F Review on feature branch\n  4. Integrate: **solo-local** (`scripts\u002Fland-branch.sh`) or **team-pr** (`gh pr create` → squash merge)\n  5. Cleanup worktree; **end on `main`** in primary repo root\n- **Gate**: Safety (\"About to land on main. Confirm?\").\n\n---\n\n## Orchestration Modes\n\n### Mode 1: Standard (Enforce All Gates)\n**Use Case**: New features, major refactors, architectural changes.\n**Behavior**:\n- All Confirm gates require explicit user approval.\n- All Quality gates are hard stops if threshold is not met.\n- No shortcuts or phase skipping.\n\n### Mode 2: Fast-Track (Skip Negotiable Gates)\n**Use Case**: Hotfixes, minor improvements, refactors on well-tested code.\n**Behavior**:\n- Skip Discover if `requirements\u002FSCOPE_LATEST.yaml` exists.\n- Skip Elaborate if design decisions are already locked.\n- Skip Verify if coverage ≥95% + all tests PASS.\n- Soft gates auto-approve if baseline conditions are met.\n\n### Mode 3: Ad-Hoc (Legacy, Warnings Only)\n**Use Case**: Exploration, prototyping, spikes (NOT for production).\n**Behavior**:\n- Gates emit warnings but do not block execution.\n- User can manually skip any phase.\n- No enforced quality thresholds.\n\n---\n\n## Gate & Checkpoint Types\n*See `docs\u002Freferences\u002Fgates.md` and `docs\u002Freferences\u002Fcheckpoints.md` for full specs.*\n\n- **Confirm**: Requires human \"yes\u002Fno\" decision.\n- **Quality**: Automated threshold check (e.g., coverage, audit score).\n- **Safety**: Destructive actions require risk acknowledgment.\n- **Transition**: Mandatory artifact presence check.\n- **slopcheck**: Identification of [SUS] (Suspicious) or [SLOP] (High-risk) packages.\n\n---\n\n## Error Recovery & State\nOrchestrate maintains `specs\u002Fstate.yaml` to track:\n- **Current flow \u002F epic**: `active_flow`, `active_epic_id`, `epic_cycle`.\n- **Handoff**: `last_step_completed`, `open_decisions`, `required_reading`, `next_skill`.\n- **Git**: `branch`, `hash` for session continuity.\n- **Progress**: Story status lives in `execution-status.yaml` only.\n\nIn the event of a crash or exit, run `claude \u002Forchestrate --resume` to pick up exactly where the session left off.\n","# Orchestrate\n> **HARD GATE** — **HARD GATE** — Do NOT invoke orchestrate-project unless you have a clear multi-phase workflow. Single-skill tasks should use dedicated skills instead. Orchestrate is for complex, multi-stage work that requires coordination across phases.\n\n\nThe orchestrate skill coordinates projects through a prescriptive 6-phase core loop with hard gates, ensuring consistent quality and preventing scope creep.\n\n## Quick Start\n\n```bash\n# Start a new project (initializes specs\u002F YAML cockpit and begins discover phase)\nclaude \u002Forchestrate --mode standard\n\n# Or resume an existing project at the current phase\nclaude \u002Forchestrate --mode standard --resume\n\n# For low-risk scenarios (hotfixes, refactors on well-tested code)\nclaude \u002Forchestrate --mode fast-track\n```\n\n## The 6-Phase Core Loop\n\n1. **DISCOVER** (3-6 hours): Understand problem. Deliverables: `requirements\u002FVISION_LATEST.yaml`, `requirements\u002FSCOPE_LATEST.yaml`, `plans\u002FTECH_STACK_LATEST.md`.\n2. **ELABORATE** (3-6 hours): Research solutions. Deliverables: Prior art in scope YAML, ADRs in `specs\u002Fadr\u002F`.\n3. **PLAN** (2-4 hours): Write verifiable plan. Deliverables: `release-plan.yaml`, `epics\u002FeNN-*.yaml` with `verify:` per task.\n4. **BUILD** (1-8 hours): Execute plan. Runs build-epic once per story in WSJF order. Deliverables: Code; update `execution-status.yaml`.\n5. **VERIFY** (1-3 hours): Validate success criteria. Deliverables: UAT evidence, `specs\u002FEVALS-*.md` if used.\n6. **RELEASE** (30 min - 2 hours): Ship to production. Deliverables: Release tag (vX.Y.Z), `state.yaml` `release.last_tag`.\n\n### Checkpoint \u002F resume\n\nTrack progress via `specs\u002Fstate.yaml` `project_cycle`:\n- `project_cycle.current_phase`: current phase (1–6)\n- `project_cycle.completed_phases`: completed phase numbers\n- `handoff.next_skill`: skill for the current phase\n- On resume, read `project_cycle.current_phase` and continue from there\n\nSee [REFERENCE.md](REFERENCE.md) for detailed phase specifications and gate types.\n\n## How Orchestrate Works\n\n1. **Maintains state.yaml** — Tracks current phase, `active_epic`, `active_flow`, decisions, risks.\n2. **Spawns appropriate skills** — Routes by `model:` frontmatter. Decisions pass only via `specs\u002Fstate.yaml` `handoff` between spawns.\n3. **Methodology lenses** — If `specs\u002Ftech-architecture\u002Fe*-TEST_PLAN_LATEST.md` or ADRs exist, apply at phase gates.\n4. **Enforces gates** — Hard stops if success criteria not met.\n5. **The Gatekeeper** — Between stories in BUILD: read `specs\u002Fexecution-status.yaml`; previous story must be `done` before starting the next; use `build-epic` for the 8-step epic cycle.\n6. **Pauses for confirmation** — After each phase, asks \"Ready to proceed?\".\n7. **Snapshots** — `bash scripts\u002Fbp-yaml-snapshot.sh` before major release cuts.\n\n## Orchestration Modes\n\n- **Standard**: Enforce all gates. Use for new features and major refactors.\n- **Fast-Track**: Skip negotiable gates. Use for hotfixes and minor improvements.\n- **Ad-Hoc**: Warnings only. Use for prototyping and spikes (non-production).\n\nSee [REFERENCE.md](REFERENCE.md) for full mode behaviors.\n\n## Verification\n\nAll phases complete with artifacts:\n```bash\nverify: test -f specs\u002Fstate.yaml && test -f specs\u002Frelease-plan.yaml && test -f specs\u002Fproduct\u002FSCOPE_LATEST.yaml && ls specs\u002Fepics\u002F*.yaml 1>\u002Fdev\u002Fnull && echo \"✅ All phases complete\"\n```\n\n\n\n\u003C!-- story: e05s03 -->\n\n---\n\n# Orchestrate Reference: Phases, Modes, and Workflows\n\nDetailed documentation for the `orchestrate-project` meta-skill.\n\n## The 6-Phase Core Loop\n\n### PHASE 1: DISCOVER\n- **Goal**: Understand the problem completely and map existing context.\n- **Deliverables**: `requirements\u002FVISION_LATEST.yaml`, `requirements\u002FSCOPE_LATEST.yaml`, `plans\u002FTECH_STACK_LATEST.md`.\n- **Skills**: `survey-context`, `elaborate-spec`, `grill-me`.\n- **Gate**: Confirm (\"Is the problem clear?\").\n\n### PHASE 2: ELABORATE\n- **Goal**: Research solutions and lock architectural design.\n- **Deliverables**: Prior art in scope YAML, ADRs in `specs\u002Fadr\u002F`.\n- **Skills**: `grill-me`, `model-domain`, `define-language`, `deepen-architecture`, `design-interface`.\n- **Gate**: Quality ≥94% (via `request-review`) + Confirm (\"Are decisions locked?\").\n\n### PHASE 3: PLAN\n- **Goal**: Write a verifiable implementation plan with success criteria.\n- **Deliverables**: `release-plan.yaml`, `epics\u002FeNN-*.yaml` with `verify:` per task.\n- **Skills**: `scope-work`, `slice-tasks`, `plan-work`.\n- **Gate**: Quality (request-review ≥94%) + slopcheck [SUS]\u002F[SLOP].\n\n### PHASE 4: BUILD\n- **Goal**: Execute the plan story-by-story using the 8-step `build-epic` cycle with TDD and vertical slices.\n- **Deliverables**: Code; `execution-status.yaml` updated per story; `specs\u002Fmetrics\u002Fcycle-times.yaml` row per story.\n- **Skills**: `build-epic` (conductor) → per-story: `survey-context`, `plan-work`, `kickoff-branch`, `develop-tdd`, `verify-work`, `audit-code`, `commit-message`, `release-branch`.\n- **BCP tracking**: `plan-release` sizes each story in Business Complexity Points (BCP) before the build queue; `plan-work` confirms and writes the size to `state.yaml` as `epic_cycle.story_bcps`. See `docs\u002Freferences\u002Fbcp.md` for the canonical sizing method.\n- **Timestamps**: `survey-context` stamps `metrics.story_start`; `release-branch` stamps `metrics.story_end` and writes BCP\u002Fhr to `specs\u002Fmetrics\u002Fcycle-times.yaml`.\n- **next_skill**: Each critical-path skill writes `handoff.next_skill` to `state.yaml`. Agents resume by reading `state.yaml` — no guessing.\n- **Dashboard**: `npm run dashboard` (TUI) or `npm run dashboard:web` (browser, port 7742) shows live pipeline, epic queue, BCP metrics, and cycle-time ledger.\n- **Gate**: Integration tests PASS; all 8 build-epic steps completed per story.\n\n### PHASE 5: VERIFY\n- **Goal**: Validate success criteria and ensure production readiness.\n- **Deliverables**: UAT evidence, eval results.\n- **Skills**: `run-evals`, `verify-work`, `audit-code`, `request-review` (optional).\n- **Gate**: Verification Script confirmed; `verify-work` not on `main`\u002F`master`.\n\n### PHASE 6: RELEASE (Integrate)\n- **Goal**: Ship to `main` with full traceability.\n- **Deliverables**: Release tag (vX.Y.Z), release notes via semantic-release.\n- **Skills**: `commit-message`, `release-branch`.\n- **Git arc**:\n  1. Plan on `main` (Discover \u002F Plan)\n  2. `kickoff-branch` → worktree + feature branch + clean baseline\n  3. Build \u002F Verify \u002F Review on feature branch\n  4. Integrate: **solo-local** (`scripts\u002Fland-branch.sh`) or **team-pr** (`gh pr create` → squash merge)\n  5. Cleanup worktree; **end on `main`** in primary repo root\n- **Gate**: Safety (\"About to land on main. Confirm?\").\n\n---\n\n## Orchestration Modes\n\n### Mode 1: Standard (Enforce All Gates)\n**Use Case**: New features, major refactors, architectural changes.\n**Behavior**:\n- All Confirm gates require explicit user approval.\n- All Quality gates are hard stops if threshold is not met.\n- No shortcuts or phase skipping.\n\n### Mode 2: Fast-Track (Skip Negotiable Gates)\n**Use Case**: Hotfixes, minor improvements, refactors on well-tested code.\n**Behavior**:\n- Skip Discover if `requirements\u002FSCOPE_LATEST.yaml` exists.\n- Skip Elaborate if design decisions are already locked.\n- Skip Verify if coverage ≥95% + all tests PASS.\n- Soft gates auto-approve if baseline conditions are met.\n\n### Mode 3: Ad-Hoc (Legacy, Warnings Only)\n**Use Case**: Exploration, prototyping, spikes (NOT for production).\n**Behavior**:\n- Gates emit warnings but do not block execution.\n- User can manually skip any phase.\n- No enforced quality thresholds.\n\n---\n\n## Gate & Checkpoint Types\n*See `docs\u002Freferences\u002Fgates.md` and `docs\u002Freferences\u002Fcheckpoints.md` for full specs.*\n\n- **Confirm**: Requires human \"yes\u002Fno\" decision.\n- **Quality**: Automated threshold check (e.g., coverage, audit score).\n- **Safety**: Destructive actions require risk acknowledgment.\n- **Transition**: Mandatory artifact presence check.\n- **slopcheck**: Identification of [SUS] (Suspicious) or [SLOP] (High-risk) packages.\n\n---\n\n## Error Recovery & State\nOrchestrate maintains `specs\u002Fstate.yaml` to track:\n- **Current flow \u002F epic**: `active_flow`, `active_epic_id`, `epic_cycle`.\n- **Handoff**: `last_step_completed`, `open_decisions`, `required_reading`, `next_skill`.\n- **Git**: `branch`, `hash` for session continuity.\n- **Progress**: Story status lives in `execution-status.yaml` only.\n\nIn the event of a crash or exit, run `claude \u002Forchestrate --resume` to pick up exactly where the session left off.\n",{"name":5,"model":27,"description":7},"main","72f5e4c8b43f60cf86b37078ad8cd7e22daf67aa",".qwen\u002Fskills\u002Forchestrate-project",24,"https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers","https:\u002F\u002Fdanielvm-git.github.io\u002Fbigpowers\u002F","https:\u002F\u002Fgithub.com\u002Fdanielvm-git","danielvm.net","2026-11-10 01:18:54",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add danielvm-git\u002Fbigpowers --skill orchestrate-project",{"tool":59,"command":60},"bunx","bunx skills add danielvm-git\u002Fbigpowers --skill orchestrate-project",{"tool":62,"command":63},"pnpm","pnpm dlx skills add danielvm-git\u002Fbigpowers --skill orchestrate-project","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Forchestrate-project\u002FSKILL.md",true,[],[68,88,95,123,144,165],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":79,"publishedAt":39},"01M71KBG9F8X644MJB16H4V8M7","skill-verify-fail-open-fixture","Negative-path fixture for run-skill-verify.sh — must never PASS.","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fspecs\u002Fverifications\u002Ffixtures\u002Fskill-verify-fail-open\u002FSKILL.md",[74],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[80,81,82,83,84,85,86,24,87],"fixture","open","verify","skill verify fail open fixture","skill verify","path","run","never",{"skillNo":89,"name":90,"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":91,"categories":92,"keywords":93,"publishedAt":39},"01M71KBE3BKEMKNE0C5DGVDWZH","negative-path","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fspecs\u002Fverifications\u002Ffixtures\u002Fnegative-path\u002FSKILL.md",[],[94,85],"negative path",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":104,"publishedAt":39},"01M71KBBGF7Y4EB4AMHBZ8CJFC","write-document","Write, organize, and sync high-integrity technical documents using the BMAD methodology. Ensures every document is Bold, Minimal, Actionable, and Durable. Use when creating architectural docs, technical guides, or organizing the specs\u002F directory.","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-document\u002FSKILL.md",[101],{"categoryNo":102,"categoryName":103,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000002","文档处理",[105,106,107,108,109,110,111,112,113,114,22,115,116,117,27,118,119,120,121,122],"write","write document","document","documents","actionable","technical","methodology","high","bmad","standard","when","minimal","bold","integrity","organize","sync","directory","guides",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":39},"01M71KB8TM089JJD5AY5KAFSDM","wire-observability","Add structured JSON logging, observability commands, and idempotent setup scripts to a project. Use when a project needs production-readiness instrumentation, when user wants structured logging, or as a production-readiness gate at any phase of development.","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fskills\u002Fwire-observability\u002FSKILL.md",[],[130,131,132,114,133,22,134,135,136,137,27,138,139,140,141,142,31,115,19,143],"observability","wire observability","readiness","commands","development","as","logging","add","instrumentation","at","structured logging","production-readiness","idempotent","scripts",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":39},"01M71KB6CNRANP449DQA3NJZ96","wire-ci","CI pipeline setup with bundled, forge-neutral templates and local validation. Detects the forge from the git remote, generates workflows for supported forges, and skips honestly for the rest. The CI equivalent of wire-observability.","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fskills\u002Fwire-ci\u002FSKILL.md",[],[151,152,153,154,155,156,157,158,159,160,161,114,162,24,130,27,163,164],"wire ci","ci","remote","local","pipeline","forge","validation","setup","templates","REST","with","ci pipeline setup","git","workflows",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":182,"publishedAt":39},"01M71KB2ZV98P03X88QR8MT9F1","visual-dashboard","Start a browser-based dashboard that visualizes architecture, implementation plans, and project status. Persists artifacts in .bigpowers\u002Fdashboard\u002F. Reads specs\u002Fstate.yaml, release-plan.yaml, epics, and planning-status via HTTP API or opencode panel.","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-dashboard\u002FSKILL.md",[171,174,179],{"categoryNo":172,"categoryName":173,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":175,"categoryName":176,"taxonomyType":177,"taxonomyTypeDesc":178},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":180,"categoryName":181,"taxonomyType":177,"taxonomyTypeDesc":178},"01JBSEEDCAT000000000000033","数据分析师",[183,184,185,186,187,188,189,190,191,27,192,28,193,30,194,195,196,19,197,198],"dashboard","visual","visual dashboard","status","artifacts","http","plans","planning","panel","start","opencode","browser","api","architecture","project status","http api"]