[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71T12EE3XNE2G3B7HZPCB34":3,"skill-same:01M71T12EE3XNE2G3B7HZPCB34":80},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":6,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":79},"01M71T12EE3XNE2G3B7HZPCB34","skill-scaffold",null,"Use when you want to scaffold a new clauDNA skill directory with correct structure, valid frontmatter, and a starter body that passes validation.","Claudfather\u002FclauDNA","Claudfather","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F281278891?v=4","01M71SX82K0TBGQ394AB2G1T5Z","01M71SX83CE1S8YC06K9P3P962",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FClaudfather\u002FclauDNA\u002Fblob\u002Fmain\u002Fskills\u002Fskill-scaffold\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"scaffold","skill scaffold","scripts","directory","name","structure","starter","with","valid","Bash","you","when","use","new","true","mkdir","correct","repo","python3","ls","2026-11-10 13:02:02",false,"---\nname: skill-scaffold\nuser-invocable: true\ndisable-model-invocation: true\ndescription: \"Use when you want to scaffold a new clauDNA skill directory with correct structure, valid frontmatter, and a starter body that passes validation.\"\nrequires-context: repo-clone\nargument-hint: \"[skill-name]\"\nallowed-tools:\n  - Bash(python3 scripts\u002Fvalidate-skills.py)\n  - Bash(ls *)\n  - Bash(mkdir *)\n  - Read\n  - Write\n  - Glob\n---\n\n# Skill Scaffold — Interactive Skill Wizard\n\nScaffold a new skill directory with valid SKILL.md frontmatter and body skeleton. Generates boilerplate that passes `validate-skills.py` out of the box so contributors can focus on writing the procedure.\n\n## Procedure\n\n### Step 1: Gather Inputs\n\nIf the user provided a skill name as an argument, use it. Otherwise prompt for the following:\n\n1. **Skill name** — must be `kebab-case` (lowercase letters, digits, hyphens only). This becomes both the directory name and the `name:` frontmatter field.\n2. **One-line description** — must start with \"Use when\" and be 20-500 characters. This becomes the `description:` frontmatter field.\n3. **Tool requirements** — which tools does the skill need? Common patterns:\n   - Read-only analysis: `Read, Grep, Glob`\n   - Code modification: `Read, Write, Edit, Grep, Glob, Bash(git status *), Bash(git diff *), Bash(git add *), Bash(git commit *)`\n   - GitHub interaction: `Bash(gh pr view *), Bash(gh issue view *), Bash(git status *), Bash(git diff *), Read, Grep, Glob`\n   - Full orchestration: `Read, Write, Edit, Grep, Glob, Bash(git status *), Bash(git diff *), Bash(gh pr view *), Agent`\n   - Grant the exact commands or read-only subcommands the skill runs; a whole-family wildcard (`Bash(git *)`, `Bash(python3 *)`) or a build\u002Ftest tool is rejected by validation\n   - None (uses only defaults): omit the field\n4. **Argument hint** — does the skill accept arguments? If yes, what format? (e.g. `[--flag] [positional]`)\n5. **Uses subagents?** — will the skill delegate to Agent\u002Fsubagents for parallel work?\n6. **External CLI dependencies** — does it need tools beyond git\u002Fcurl\u002Fjq? (e.g. `gh>=2.0`, `vercel`, `neon`)\n\n### Step 2: Validate Inputs\n\nBefore creating anything:\n\n- Confirm `skills\u002F\u003Cname>\u002F` does **not** already exist. If it does, stop and tell the user:\n  ```\n  Error: skills\u002F\u003Cname>\u002F already exists. Choose a different name or edit the existing skill.\n  ```\n- Confirm the name matches `^[a-z][a-z0-9-]*$` (starts with letter, kebab-case).\n- Confirm description starts with \"Use when\" and is 20-500 characters.\n\n### Step 3: Create Skill Directory and SKILL.md\n\nCreate `skills\u002F\u003Cname>\u002FSKILL.md` with the following structure:\n\n```markdown\n---\nname: \u003Cname>\nuser-invocable: true\ndescription: \"\u003Cdescription>\"\n[argument-hint: \"\u003Chint>\"]       # only if provided\n[allowed-tools:]                # only if tools were specified\n[  - \u003Ctool>]\n[requires:]                     # only if external CLI deps declared\n[  - cli: \"\u003Ctool>\"]\n[    reason: \"\u003Cwhy>\"]\n---\n\n# \u003CTitle Case Name>\n\n\u003COne-line restatement of what the skill does.>\n\n## Procedure\n\n### Step 1: \u003CFirst Action>\n\n1. \u003CPlaceholder — describe what to do>\n2. \u003CPlaceholder — describe what to check>\n\n### Step 2: \u003CSecond Action>\n\n1. \u003CPlaceholder — describe what to do>\n2. \u003CPlaceholder — describe what to check>\n\n### Step 3: Verify & Report\n\n1. Confirm the output is correct\n2. Present results to the user\n```\n\n**If subagents indicated**, also create `skills\u002F\u003Cname>\u002Fsubagent-prompts.md`:\n\n```markdown\n# Subagent Prompts — \u003Cname>\n\nReference material for subagent prompts used by this skill.\n\n## Scout Agent\n\n```\n\u003CPrompt template for scout\u002Fresearch subagent>\n```\n\n## Worker Agent\n\n```\n\u003CPrompt template for implementation subagent>\n```\n```\n\n### Step 4: Run Validator\n\nRun:\n\n```bash\npython3 scripts\u002Fvalidate-skills.py\n```\n\nIf the new skill fails validation, read the error, fix the generated file, and re-run until it passes.\n\n### Step 5: Present Result\n\nPrint a summary:\n\n```\nSkill Scaffolded\n═══════════════════════════════════════════════════════\n  Created:\n    skills\u002F\u003Cname>\u002FSKILL.md          (frontmatter + skeleton)\n    [skills\u002F\u003Cname>\u002Fsubagent-prompts.md]  (if subagents)\n\n  Next steps:\n    1. Edit the procedure steps in skills\u002F\u003Cname>\u002FSKILL.md\n    2. Test locally: claude --plugin-dir \u002Fpath\u002Fto\u002FclauDNA\n    3. Run validator: python3 scripts\u002Fvalidate-skills.py\n    4. Submit PR referencing any tracking issue\n═══════════════════════════════════════════════════════\n```\n\n## Rules\n\n- **Never overwrite an existing skill directory.** If `skills\u002F\u003Cname>\u002F` exists, refuse and explain.\n- **Generated output must pass validation on first run.** If it doesn't, that's a bug in the scaffold — fix it before presenting to the user.\n- **Follow SKILL_CONTRACT.md exactly.** The scaffold is the happy path for contributors — if it produces invalid output, trust erodes.\n- **Kebab-case only.** Reject camelCase, PascalCase, snake_case, or names with spaces.\n- **Description must start with \"Use when\".** This is a SKILL_CONTRACT convention. Enforce it at input time, not after generation.\n","# Skill Scaffold — Interactive Skill Wizard\n\nScaffold a new skill directory with valid SKILL.md frontmatter and body skeleton. Generates boilerplate that passes `validate-skills.py` out of the box so contributors can focus on writing the procedure.\n\n## Procedure\n\n### Step 1: Gather Inputs\n\nIf the user provided a skill name as an argument, use it. Otherwise prompt for the following:\n\n1. **Skill name** — must be `kebab-case` (lowercase letters, digits, hyphens only). This becomes both the directory name and the `name:` frontmatter field.\n2. **One-line description** — must start with \"Use when\" and be 20-500 characters. This becomes the `description:` frontmatter field.\n3. **Tool requirements** — which tools does the skill need? Common patterns:\n   - Read-only analysis: `Read, Grep, Glob`\n   - Code modification: `Read, Write, Edit, Grep, Glob, Bash(git status *), Bash(git diff *), Bash(git add *), Bash(git commit *)`\n   - GitHub interaction: `Bash(gh pr view *), Bash(gh issue view *), Bash(git status *), Bash(git diff *), Read, Grep, Glob`\n   - Full orchestration: `Read, Write, Edit, Grep, Glob, Bash(git status *), Bash(git diff *), Bash(gh pr view *), Agent`\n   - Grant the exact commands or read-only subcommands the skill runs; a whole-family wildcard (`Bash(git *)`, `Bash(python3 *)`) or a build\u002Ftest tool is rejected by validation\n   - None (uses only defaults): omit the field\n4. **Argument hint** — does the skill accept arguments? If yes, what format? (e.g. `[--flag] [positional]`)\n5. **Uses subagents?** — will the skill delegate to Agent\u002Fsubagents for parallel work?\n6. **External CLI dependencies** — does it need tools beyond git\u002Fcurl\u002Fjq? (e.g. `gh>=2.0`, `vercel`, `neon`)\n\n### Step 2: Validate Inputs\n\nBefore creating anything:\n\n- Confirm `skills\u002F\u003Cname>\u002F` does **not** already exist. If it does, stop and tell the user:\n  ```\n  Error: skills\u002F\u003Cname>\u002F already exists. Choose a different name or edit the existing skill.\n  ```\n- Confirm the name matches `^[a-z][a-z0-9-]*$` (starts with letter, kebab-case).\n- Confirm description starts with \"Use when\" and is 20-500 characters.\n\n### Step 3: Create Skill Directory and SKILL.md\n\nCreate `skills\u002F\u003Cname>\u002FSKILL.md` with the following structure:\n\n```markdown\n---\nname: \u003Cname>\nuser-invocable: true\ndescription: \"\u003Cdescription>\"\n[argument-hint: \"\u003Chint>\"]       # only if provided\n[allowed-tools:]                # only if tools were specified\n[  - \u003Ctool>]\n[requires:]                     # only if external CLI deps declared\n[  - cli: \"\u003Ctool>\"]\n[    reason: \"\u003Cwhy>\"]\n---\n\n# \u003CTitle Case Name>\n\n\u003COne-line restatement of what the skill does.>\n\n## Procedure\n\n### Step 1: \u003CFirst Action>\n\n1. \u003CPlaceholder — describe what to do>\n2. \u003CPlaceholder — describe what to check>\n\n### Step 2: \u003CSecond Action>\n\n1. \u003CPlaceholder — describe what to do>\n2. \u003CPlaceholder — describe what to check>\n\n### Step 3: Verify & Report\n\n1. Confirm the output is correct\n2. Present results to the user\n```\n\n**If subagents indicated**, also create `skills\u002F\u003Cname>\u002Fsubagent-prompts.md`:\n\n```markdown\n# Subagent Prompts — \u003Cname>\n\nReference material for subagent prompts used by this skill.\n\n## Scout Agent\n\n```\n\u003CPrompt template for scout\u002Fresearch subagent>\n```\n\n## Worker Agent\n\n```\n\u003CPrompt template for implementation subagent>\n```\n```\n\n### Step 4: Run Validator\n\nRun:\n\n```bash\npython3 scripts\u002Fvalidate-skills.py\n```\n\nIf the new skill fails validation, read the error, fix the generated file, and re-run until it passes.\n\n### Step 5: Present Result\n\nPrint a summary:\n\n```\nSkill Scaffolded\n═══════════════════════════════════════════════════════\n  Created:\n    skills\u002F\u003Cname>\u002FSKILL.md          (frontmatter + skeleton)\n    [skills\u002F\u003Cname>\u002Fsubagent-prompts.md]  (if subagents)\n\n  Next steps:\n    1. Edit the procedure steps in skills\u002F\u003Cname>\u002FSKILL.md\n    2. Test locally: claude --plugin-dir \u002Fpath\u002Fto\u002FclauDNA\n    3. Run validator: python3 scripts\u002Fvalidate-skills.py\n    4. Submit PR referencing any tracking issue\n═══════════════════════════════════════════════════════\n```\n\n## Rules\n\n- **Never overwrite an existing skill directory.** If `skills\u002F\u003Cname>\u002F` exists, refuse and explain.\n- **Generated output must pass validation on first run.** If it doesn't, that's a bug in the scaffold — fix it before presenting to the user.\n- **Follow SKILL_CONTRACT.md exactly.** The scaffold is the happy path for contributors — if it produces invalid output, trust erodes.\n- **Kebab-case only.** Reject camelCase, PascalCase, snake_case, or names with spaces.\n- **Description must start with \"Use when\".** This is a SKILL_CONTRACT convention. Enforce it at input time, not after generation.\n",{"name":5,"description":7,"allowed-tools":48,"argument-hint":55,"user-invocable":56,"requires-context":57,"disable-model-invocation":56},[49,50,51,52,53,54],"Bash(python3 scripts\u002Fvalidate-skills.py)","Bash(ls *)","Bash(mkdir *)","Read","Write","Glob","[skill-name]",true,"repo-clone","main","525fa1341307bedb4500dcb4865351f705f470dd","skills\u002Fskill-scaffold",1,"https:\u002F\u002Fgithub.com\u002FClaudfather\u002FclauDNA","https:\u002F\u002Fgithub.com\u002FClaudfather","https:\u002F\u002Fcrog.gg","Rise of the machines","2026-11-13 18:50:49",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":56},[69,72,75],{"tool":70,"command":71},"npx","npx skills add Claudfather\u002FclauDNA --skill skill-scaffold",{"tool":73,"command":74},"bunx","bunx skills add Claudfather\u002FclauDNA --skill skill-scaffold",{"tool":76,"command":77},"pnpm","pnpm dlx skills add Claudfather\u002FclauDNA --skill skill-scaffold","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FClaudfather\u002FclauDNA\u002Fblob\u002Fmain\u002Fskills\u002Fskill-scaffold\u002FSKILL.md",[],[81,103,113,137,161,177],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":43},"01M71T1STJ99BE1C0JYHCQW0XN","example-review","Use when you want to review pull requests with detailed, actionable feedback on code quality, correctness, and maintainability.","https:\u002F\u002Fgithub.com\u002FClaudfather\u002FclauDNA\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fvalid-package\u002FSKILL.md",[],[88,89,90,91,92,30,93,94,32,33,34,35,95,96,97,98,99,100,101,102],"review","example","example review","actionable","pull requests","code","correctness","gh","gh pr","diff","view","pr","code quality","feedback","pull",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":43},"01M71T1RMCD30MAJC954JC7580","bad-skill","Too short","https:\u002F\u002Fgithub.com\u002FClaudfather\u002FclauDNA\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Ffailing-package\u002FSKILL.md",[],[110,111,112],"bad","bad skill","short",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":43},"01M71T1NS97NJ2MQ993V7FBES7","worktree","Use when starting feature work that needs isolation from the current workspace, or when running multiple Claude sessions in parallel on different branches — creates and manages git worktrees. For fetching latest main into every existing worktree and branch across your sibling repos, use \u002Fclaudna:sync-branches instead.","https:\u002F\u002Fgithub.com\u002FClaudfather\u002FclauDNA\u002Fblob\u002Fmain\u002Fskills\u002Fworktree\u002FSKILL.md",[],[115,120,121,122,123,124,125,126,127,128,129,130,34,131,58,132,133,134,135,136],"sync","repos","git","isolation","running","sessions","worktrees","work","across","needs","git worktrees","claude sessions","branches","branch","parallel","for","feature",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":43},"01M71T1HNVG1CZY8P904P6RB7P","weigh-development-paths","Use when at a development junction with multiple viable approaches — architecture choices, refactoring strategies, where to put new code, or which pattern to follow. Triggers on 'which approach', 'how should I', 'Option A vs B', or any point where the next step isn't obvious and the wrong choice creates rework.","https:\u002F\u002Fgithub.com\u002FClaudfather\u002FclauDNA\u002Fblob\u002Fmain\u002Fskills\u002Fweigh-development-paths\u002FSKILL.md",[],[144,145,146,147,148,149,150,151,152,153,154,155,156,93,34,157,36,158,159,160],"development","weigh development paths","paths","next step","path","refactoring","choice","pattern","at","how","next","strategies","architecture","auto","junction","option","which",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":43},"01M71T1ECV1T5E168GH70AY5B3","verify-completion","Use when about to claim work is complete, fixed, or passing -- requires running verification commands and confirming output before making any success claims.","https:\u002F\u002Fgithub.com\u002FClaudfather\u002FclauDNA\u002Fblob\u002Fmain\u002Fskills\u002Fverify-completion\u002FSKILL.md",[],[168,169,170,171,124,37,172,173,127,174,175,176,34,35],"verify completion","verify","claim","complete","commands","about","verification","claims","output",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":186,"publishedAt":43},"01M71T1BC1HA7XQH0Q1H574FYS","vercel","Use for Vercel operations — deploy to production or preview (or roll back), view, filter, or debug deployment logs, or check project status (deployments, domains, env vars, config). Replaces \u002Fvercel-deploy, \u002Fvercel-logs, \u002Fvercel-status.","https:\u002F\u002Fgithub.com\u002FClaudfather\u002FclauDNA\u002Fblob\u002Fmain\u002Fskills\u002Fvercel\u002FSKILL.md",[183],{"categoryNo":184,"categoryName":185,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[179,187,188,189,190,191,192,193,194,35,195,37,196,197,198,199,135,98,200,201],"inspection","check","filter","env","logs","preview","debug deployment","debug","deployments","domains","deployment","env vars","project","project status","back"]