[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71K55F63FQ0Q6WTCWVBQBBR":3,"skill-same:01M71K55F63FQ0Q6WTCWVBQBBR":77},{"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":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M71K55F63FQ0Q6WTCWVBQBBR","craft-skill",null,"Create new bigpowers skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill for the bigpowers lifecycle.","danielvm-git\u002Fbigpowers","danielvm-git","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1020864?v=4","01M71H1N1CTQ529S0KN7KETVG6","Daniel V M","01M71H1N218Y3S8WHCJ58NPRSW",292,"MIT","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fskills\u002Fcraft-skill\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"craft","craft skill","user","build","with","progressive disclosure","standard","use","progressive","lifecycle","for","sonnet","new skill","write","structure","create","when","new","resources","2026-11-10 10:12:30",false,"---\n# story: e45s02\n# story: e45s12\n# story: e79s02\nname: craft-skill\nmodel: sonnet\neffort: standard\ndescription: Create new bigpowers skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill for the bigpowers lifecycle.\n---\n\n# Craft Skill\n\n> **HARD GATE** — Do NOT name a skill without a two-word verb-noun pair. Do NOT merge a new skill without running `sync-skills.sh`. Generated `.cursor\u002Frules\u002F` and `.gemini\u002F` artifacts MUST match the source SKILL.md.\n\n## CSO Description Discipline (e45s02)\n\nThe YAML `description` is the **Catalog Selection Object** — the only field agents see when picking a skill.\n\n| Rule | Limit |\n|------|-------|\n| Max length | 1024 characters |\n| Voice | Third person |\n| Content | Capability + `Use when …` triggers only |\n| Forbidden | Workflow steps, phase chains, numbered lists, `→ verify:`, HARD GATE prose |\n\nMove process detail into the SKILL.md body or REFERENCE.md — never into `description`.\n\n## Agentic STE body discipline (e79s02)\n\nSkill-body instructional prose MUST follow [AGENTIC-STE.md](..\u002F..\u002Fdocs\u002FAGENTIC-STE.md).\n\n| Rule | Limit |\n|------|-------|\n| Sentence length | ≤20 words per instruction sentence |\n| Voice | Imperative, active |\n| Directive terms | MUST, MUST NOT, NEVER, ALWAYS, DO, DO NOT |\n| Banned modals | should, might, could, may, consider, try, generally, typically |\n| Scope | SKILL.md body only — not YAML `description`, not `terse-mode` output |\n\n> **HARD GATE** — Do NOT merge a new or edited skill until `bash scripts\u002Fvalidate-agentic-ste.sh --strict skills\u002F\u003Cname>\u002FSKILL.md` exits 0. Fix violations before `sync-skills.sh`.\n\n## Process\n\n1. **Gather requirements** — ask user about:\n   - What task\u002Fdomain does the skill cover?\n   - Which use cases must the skill handle?\n   - Does it need executable scripts or just instructions?\n   - Any reference materials to include?\n   - What specs\u002F output does it produce (if any)?\n\n2. **Verify Principles** — Ensure the skill aligns with [PRINCIPLES.md](..\u002F..\u002Fdocs\u002FPRINCIPLES.md):\n   - Is it atomic (verb-noun)?\n   - Is it \"deep\" (simple interface, complex internal logic)?\n   - Does it include Hard Gates?\n   - Is it verifiable with a `.feature` file?\n\n3. **Draft the skill** — create:\n   - SKILL.md with concise instructions (see [REFERENCE.md](REFERENCE.md) for template)\n   - Additional reference files if content exceeds 100 lines\n   - Utility scripts if deterministic operations needed\n\n   **Auto-skill from library README:** When user provides a library README or API docs URL, extract triggers and HARD GATEs.\n   Draft verify commands and specs\u002F output into SKILL.md. Do NOT invent APIs not in the source.\n\n4. Add `model:` frontmatter (`haiku` | `sonnet` | `opus`) per [model-profiles.md](..\u002F..\u002Fdocs\u002Freferences\u002Fmodel-profiles.md).\n\n> **STREAM CONTINUITY** — When writing file content, output in continuous chunks of ~200 lines. Do not pause. Continue immediately until complete. If you need time, emit a placeholder comment rather than going silent.\n\n5. **Review with user** — present draft and ask:\n   - Does this cover your use cases?\n   - Anything missing or unclear?\n   - Does any section need more or less detail?\n\n6. **Completion-honesty gate (HARD GATE — e45s02)** — Before declaring done:\n   - Run `bash scripts\u002Fvalidate-skill-description.sh skills\u002F\u003Cname>\u002FSKILL.md` — must exit 0\n   - Run `bash scripts\u002Fvalidate-agentic-ste.sh --strict skills\u002F\u003Cname>\u002FSKILL.md` — must exit 0 (e79s02)\n   - Run `bash scripts\u002Fsync-skills.sh` — must complete without error\n   - Run `bash scripts\u002Frun-skill-verify.sh \u003Cname>` if the skill defines a verify command\n   - Show terminal output for each — narration without evidence is rejected\n\n## Naming Rules\n\nEvery skill name must be a **two-word verb-noun pair**. See [REFERENCE.md](REFERENCE.md) for full rules, examples, and documented exceptions.\n\n## specs\u002F Output\n\nIf the skill produces written output, it goes in `specs\u002F` at the project root. Document the output file path in the skill body and in CONVENTIONS.md's output files table.\n\n## Review Checklist\n\nAfter drafting, verify:\n\n- [ ] Name is a two-word verb-noun pair (or follows grill-me exception)\n- [ ] Description \u003C 1024 chars, triggers only, no workflow-summary leakage\n- [ ] Description includes triggers (\"Use when...\")\n- [ ] SKILL.md under 100 lines\n- [ ] No time-sensitive info\n- [ ] Consistent terminology with CONVENTIONS.md\n- [ ] specs\u002F output documented if applicable\n- [ ] `validate-skill-description.sh` exits 0\n- [ ] `validate-agentic-ste.sh --strict` exits 0 (e79s02)\n- [ ] `sync-skills.sh` run to propagate to Cursor\u002FGemini\n- [ ] `bash scripts\u002Fvalidate-skill-catalog.sh` passes for the new skill (HARD GATE — completion honesty)\n\n> **HARD GATE** — Do NOT declare the skill done until `bash scripts\u002Fvalidate-skill-catalog.sh --strict --skill \u003Cname>` exits 0. Validator enforces verb-noun name, HARD GATE block, description ≤1024 chars, and `→ verify:` command.\n\n## Verify\n\n→ verify: `bash scripts\u002Fvalidate-skill-catalog.sh --strict --skill craft-skill && bash scripts\u002Fvalidate-skill-description.sh skills\u002Fcraft-skill\u002FSKILL.md`\n","# Craft Skill\n\n> **HARD GATE** — Do NOT name a skill without a two-word verb-noun pair. Do NOT merge a new skill without running `sync-skills.sh`. Generated `.cursor\u002Frules\u002F` and `.gemini\u002F` artifacts MUST match the source SKILL.md.\n\n## CSO Description Discipline (e45s02)\n\nThe YAML `description` is the **Catalog Selection Object** — the only field agents see when picking a skill.\n\n| Rule | Limit |\n|------|-------|\n| Max length | 1024 characters |\n| Voice | Third person |\n| Content | Capability + `Use when …` triggers only |\n| Forbidden | Workflow steps, phase chains, numbered lists, `→ verify:`, HARD GATE prose |\n\nMove process detail into the SKILL.md body or REFERENCE.md — never into `description`.\n\n## Agentic STE body discipline (e79s02)\n\nSkill-body instructional prose MUST follow [AGENTIC-STE.md](..\u002F..\u002Fdocs\u002FAGENTIC-STE.md).\n\n| Rule | Limit |\n|------|-------|\n| Sentence length | ≤20 words per instruction sentence |\n| Voice | Imperative, active |\n| Directive terms | MUST, MUST NOT, NEVER, ALWAYS, DO, DO NOT |\n| Banned modals | should, might, could, may, consider, try, generally, typically |\n| Scope | SKILL.md body only — not YAML `description`, not `terse-mode` output |\n\n> **HARD GATE** — Do NOT merge a new or edited skill until `bash scripts\u002Fvalidate-agentic-ste.sh --strict skills\u002F\u003Cname>\u002FSKILL.md` exits 0. Fix violations before `sync-skills.sh`.\n\n## Process\n\n1. **Gather requirements** — ask user about:\n   - What task\u002Fdomain does the skill cover?\n   - Which use cases must the skill handle?\n   - Does it need executable scripts or just instructions?\n   - Any reference materials to include?\n   - What specs\u002F output does it produce (if any)?\n\n2. **Verify Principles** — Ensure the skill aligns with [PRINCIPLES.md](..\u002F..\u002Fdocs\u002FPRINCIPLES.md):\n   - Is it atomic (verb-noun)?\n   - Is it \"deep\" (simple interface, complex internal logic)?\n   - Does it include Hard Gates?\n   - Is it verifiable with a `.feature` file?\n\n3. **Draft the skill** — create:\n   - SKILL.md with concise instructions (see [REFERENCE.md](REFERENCE.md) for template)\n   - Additional reference files if content exceeds 100 lines\n   - Utility scripts if deterministic operations needed\n\n   **Auto-skill from library README:** When user provides a library README or API docs URL, extract triggers and HARD GATEs.\n   Draft verify commands and specs\u002F output into SKILL.md. Do NOT invent APIs not in the source.\n\n4. Add `model:` frontmatter (`haiku` | `sonnet` | `opus`) per [model-profiles.md](..\u002F..\u002Fdocs\u002Freferences\u002Fmodel-profiles.md).\n\n> **STREAM CONTINUITY** — When writing file content, output in continuous chunks of ~200 lines. Do not pause. Continue immediately until complete. If you need time, emit a placeholder comment rather than going silent.\n\n5. **Review with user** — present draft and ask:\n   - Does this cover your use cases?\n   - Anything missing or unclear?\n   - Does any section need more or less detail?\n\n6. **Completion-honesty gate (HARD GATE — e45s02)** — Before declaring done:\n   - Run `bash scripts\u002Fvalidate-skill-description.sh skills\u002F\u003Cname>\u002FSKILL.md` — must exit 0\n   - Run `bash scripts\u002Fvalidate-agentic-ste.sh --strict skills\u002F\u003Cname>\u002FSKILL.md` — must exit 0 (e79s02)\n   - Run `bash scripts\u002Fsync-skills.sh` — must complete without error\n   - Run `bash scripts\u002Frun-skill-verify.sh \u003Cname>` if the skill defines a verify command\n   - Show terminal output for each — narration without evidence is rejected\n\n## Naming Rules\n\nEvery skill name must be a **two-word verb-noun pair**. See [REFERENCE.md](REFERENCE.md) for full rules, examples, and documented exceptions.\n\n## specs\u002F Output\n\nIf the skill produces written output, it goes in `specs\u002F` at the project root. Document the output file path in the skill body and in CONVENTIONS.md's output files table.\n\n## Review Checklist\n\nAfter drafting, verify:\n\n- [ ] Name is a two-word verb-noun pair (or follows grill-me exception)\n- [ ] Description \u003C 1024 chars, triggers only, no workflow-summary leakage\n- [ ] Description includes triggers (\"Use when...\")\n- [ ] SKILL.md under 100 lines\n- [ ] No time-sensitive info\n- [ ] Consistent terminology with CONVENTIONS.md\n- [ ] specs\u002F output documented if applicable\n- [ ] `validate-skill-description.sh` exits 0\n- [ ] `validate-agentic-ste.sh --strict` exits 0 (e79s02)\n- [ ] `sync-skills.sh` run to propagate to Cursor\u002FGemini\n- [ ] `bash scripts\u002Fvalidate-skill-catalog.sh` passes for the new skill (HARD GATE — completion honesty)\n\n> **HARD GATE** — Do NOT declare the skill done until `bash scripts\u002Fvalidate-skill-catalog.sh --strict --skill \u003Cname>` exits 0. Validator enforces verb-noun name, HARD GATE block, description ≤1024 chars, and `→ verify:` command.\n\n## Verify\n\n→ verify: `bash scripts\u002Fvalidate-skill-catalog.sh --strict --skill craft-skill && bash scripts\u002Fvalidate-skill-description.sh skills\u002Fcraft-skill\u002FSKILL.md`\n",{"name":5,"model":35,"effort":30,"description":7},"main","72f5e4c8b43f60cf86b37078ad8cd7e22daf67aa","skills\u002Fcraft-skill",23,"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":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add danielvm-git\u002Fbigpowers --skill craft-skill",{"tool":63,"command":64},"bunx","bunx skills add danielvm-git\u002Fbigpowers --skill craft-skill",{"tool":66,"command":67},"pnpm","pnpm dlx skills add danielvm-git\u002Fbigpowers --skill craft-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fskills\u002Fcraft-skill\u002FSKILL.md",true,[71],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"REFERENCE.md","REFERENCE","参考文档",2620,"https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fskills\u002Fcraft-skill\u002FREFERENCE.md",[78,94,101,126,149,169],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":85,"publishedAt":43},"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",[84],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[86,87,88,89,90,91,92,34,93],"fixture","open","verify","skill verify fail open fixture","skill verify","path","run","never",{"skillNo":95,"name":96,"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":97,"categories":98,"keywords":99,"publishedAt":43},"01M71KBE3BKEMKNE0C5DGVDWZH","negative-path","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fspecs\u002Fverifications\u002Ffixtures\u002Fnegative-path\u002FSKILL.md",[],[100,91],"negative path",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":110,"publishedAt":43},"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",[107],{"categoryNo":108,"categoryName":109,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",[37,111,112,113,114,115,116,117,118,30,31,40,119,120,35,121,122,123,124,125],"write document","document","documents","actionable","technical","methodology","high","bmad","minimal","bold","integrity","organize","sync","directory","guides",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":43},"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",[],[133,134,135,30,136,31,137,138,139,140,35,141,142,143,144,145,146,40,147,148],"observability","wire observability","readiness","commands","development","as","logging","add","instrumentation","at","structured logging","production-readiness","idempotent","phase","project","scripts",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":43},"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",[],[156,157,158,159,160,161,162,163,164,165,28,30,166,34,133,35,167,168],"wire ci","ci","remote","local","pipeline","forge","validation","setup","templates","REST","ci pipeline setup","git","workflows",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":186,"publishedAt":43},"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",[175,178,183],{"categoryNo":176,"categoryName":177,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":179,"categoryName":180,"taxonomyType":181,"taxonomyTypeDesc":182},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":184,"categoryName":185,"taxonomyType":181,"taxonomyTypeDesc":182},"01JBSEEDCAT000000000000033","数据分析师",[187,188,189,190,191,192,193,194,195,35,196,197,198,199,200,201,202,147,203,204],"dashboard","visual","visual dashboard","status","artifacts","http","plans","planning","panel","start","release","opencode","plan","browser","api","architecture","project status","http api"]