[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7189GR3MKC7QQYZXCFM73G8":3,"skill-same:01M7189GR3MKC7QQYZXCFM73G8":82},{"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":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M7189GR3MKC7QQYZXCFM73G8","claude-md-improver",null,"Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions \"CLAUDE.md maintenance\" or \"project memory optimization\".","anthropics\u002Fclaude-plugins-official","anthropics","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4","01M697XGDPXJAVQ8391V2BCYTE","Anthropic","01M7188MR49TZ9N2ZKPXJ7M7HY",46906,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-md-management\u002Fskills\u002Fclaude-md-improver\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"claude md improver","claude md","project","repositories","when","outputs","quality report","project memory","for","updates","Memory Optimization","memory","files","maintenance","use","fix","check","improve","Bash","Optimization","2026-11-10 10:12:30",false,"---\nname: claude-md-improver\ndescription: Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions \"CLAUDE.md maintenance\" or \"project memory optimization\".\ntools: Read, Glob, Grep, Bash, Edit\n---\n\n# CLAUDE.md Improver\n\nAudit, evaluate, and improve CLAUDE.md files across a codebase to ensure Claude Code has optimal project context.\n\n**This skill can write to CLAUDE.md files.** After presenting a quality report and getting user approval, it updates CLAUDE.md files with targeted improvements.\n\n## Workflow\n\n### Phase 1: Discovery\n\nFind all CLAUDE.md files in the repository:\n\n```bash\nfind . -name \"CLAUDE.md\" -o -name \".claude.md\" -o -name \".claude.local.md\" 2>\u002Fdev\u002Fnull | head -50\n```\n\n**File Types & Locations:**\n\n| Type | Location | Purpose |\n|------|----------|---------|\n| Project root | `.\u002FCLAUDE.md` | Primary project context (checked into git, shared with team) |\n| Local overrides | `.\u002F.claude.local.md` | Personal\u002Flocal settings (gitignored, not shared) |\n| Global defaults | `~\u002F.claude\u002FCLAUDE.md` | User-wide defaults across all projects |\n| Package-specific | `.\u002Fpackages\u002F*\u002FCLAUDE.md` | Module-level context in monorepos |\n| Subdirectory | Any nested location | Feature\u002Fdomain-specific context |\n\n**Note:** Claude auto-discovers CLAUDE.md files in parent directories, making monorepo setups work automatically.\n\n### Phase 2: Quality Assessment\n\nFor each CLAUDE.md file, evaluate against quality criteria. See [references\u002Fquality-criteria.md](references\u002Fquality-criteria.md) for detailed rubrics.\n\n**Quick Assessment Checklist:**\n\n| Criterion | Weight | Check |\n|-----------|--------|-------|\n| Commands\u002Fworkflows documented | High | Are build\u002Ftest\u002Fdeploy commands present? |\n| Architecture clarity | High | Can Claude understand the codebase structure? |\n| Non-obvious patterns | Medium | Are gotchas and quirks documented? |\n| Conciseness | Medium | No verbose explanations or obvious info? |\n| Currency | High | Does it reflect current codebase state? |\n| Actionability | High | Are instructions executable, not vague? |\n\n**Quality Scores:**\n- **A (90-100)**: Comprehensive, current, actionable\n- **B (70-89)**: Good coverage, minor gaps\n- **C (50-69)**: Basic info, missing key sections\n- **D (30-49)**: Sparse or outdated\n- **F (0-29)**: Missing or severely outdated\n\n### Phase 3: Quality Report Output\n\n**ALWAYS output the quality report BEFORE making any updates.**\n\nFormat:\n\n```\n## CLAUDE.md Quality Report\n\n### Summary\n- Files found: X\n- Average score: X\u002F100\n- Files needing update: X\n\n### File-by-File Assessment\n\n#### 1. .\u002FCLAUDE.md (Project Root)\n**Score: XX\u002F100 (Grade: X)**\n\n| Criterion | Score | Notes |\n|-----------|-------|-------|\n| Commands\u002Fworkflows | X\u002F20 | ... |\n| Architecture clarity | X\u002F20 | ... |\n| Non-obvious patterns | X\u002F15 | ... |\n| Conciseness | X\u002F15 | ... |\n| Currency | X\u002F15 | ... |\n| Actionability | X\u002F15 | ... |\n\n**Issues:**\n- [List specific problems]\n\n**Recommended additions:**\n- [List what should be added]\n\n#### 2. .\u002Fpackages\u002Fapi\u002FCLAUDE.md (Package-specific)\n...\n```\n\n### Phase 4: Targeted Updates\n\nAfter outputting the quality report, ask user for confirmation before updating.\n\n**Update Guidelines (Critical):**\n\n1. **Propose targeted additions only** - Focus on genuinely useful info:\n   - Commands or workflows discovered during analysis\n   - Gotchas or non-obvious patterns found in code\n   - Package relationships that weren't clear\n   - Testing approaches that work\n   - Configuration quirks\n\n2. **Keep it minimal** - Avoid:\n   - Restating what's obvious from the code\n   - Generic best practices already covered\n   - One-off fixes unlikely to recur\n   - Verbose explanations when a one-liner suffices\n\n3. **Show diffs** - For each change, show:\n   - Which CLAUDE.md file to update\n   - The specific addition (as a diff or quoted block)\n   - Brief explanation of why this helps future sessions\n\n**Diff Format:**\n\n```markdown\n### Update: .\u002FCLAUDE.md\n\n**Why:** Build command was missing, causing confusion about how to run the project.\n\n```diff\n+ ## Quick Start\n+\n+ ```bash\n+ npm install\n+ npm run dev  # Start development server on port 3000\n+ ```\n```\n```\n\n### Phase 5: Apply Updates\n\nAfter user approval, apply changes using the Edit tool. Preserve existing content structure.\n\n## Templates\n\nSee [references\u002Ftemplates.md](references\u002Ftemplates.md) for CLAUDE.md templates by project type.\n\n## Common Issues to Flag\n\n1. **Stale commands**: Build commands that no longer work\n2. **Missing dependencies**: Required tools not mentioned\n3. **Outdated architecture**: File structure that's changed\n4. **Missing environment setup**: Required env vars or config\n5. **Broken test commands**: Test scripts that have changed\n6. **Undocumented gotchas**: Non-obvious patterns not captured\n\n## User Tips to Share\n\nWhen presenting recommendations, remind users:\n\n- **`#` key shortcut**: During a Claude session, press `#` to have Claude auto-incorporate learnings into CLAUDE.md\n- **Keep it concise**: CLAUDE.md should be human-readable; dense is better than verbose\n- **Actionable commands**: All documented commands should be copy-paste ready\n- **Use `.claude.local.md`**: For personal preferences not shared with team (add to `.gitignore`)\n- **Global defaults**: Put user-wide preferences in `~\u002F.claude\u002FCLAUDE.md`\n\n## What Makes a Great CLAUDE.md\n\n**Key principles:**\n- Concise and human-readable\n- Actionable commands that can be copy-pasted\n- Project-specific patterns, not generic advice\n- Non-obvious gotchas and warnings\n\n**Recommended sections** (use only what's relevant):\n- Commands (build, test, dev, lint)\n- Architecture (directory structure)\n- Key Files (entry points, config)\n- Code Style (project conventions)\n- Environment (required vars, setup)\n- Testing (commands, patterns)\n- Gotchas (quirks, common mistakes)\n- Workflow (when to do what)\n","# CLAUDE.md Improver\n\nAudit, evaluate, and improve CLAUDE.md files across a codebase to ensure Claude Code has optimal project context.\n\n**This skill can write to CLAUDE.md files.** After presenting a quality report and getting user approval, it updates CLAUDE.md files with targeted improvements.\n\n## Workflow\n\n### Phase 1: Discovery\n\nFind all CLAUDE.md files in the repository:\n\n```bash\nfind . -name \"CLAUDE.md\" -o -name \".claude.md\" -o -name \".claude.local.md\" 2>\u002Fdev\u002Fnull | head -50\n```\n\n**File Types & Locations:**\n\n| Type | Location | Purpose |\n|------|----------|---------|\n| Project root | `.\u002FCLAUDE.md` | Primary project context (checked into git, shared with team) |\n| Local overrides | `.\u002F.claude.local.md` | Personal\u002Flocal settings (gitignored, not shared) |\n| Global defaults | `~\u002F.claude\u002FCLAUDE.md` | User-wide defaults across all projects |\n| Package-specific | `.\u002Fpackages\u002F*\u002FCLAUDE.md` | Module-level context in monorepos |\n| Subdirectory | Any nested location | Feature\u002Fdomain-specific context |\n\n**Note:** Claude auto-discovers CLAUDE.md files in parent directories, making monorepo setups work automatically.\n\n### Phase 2: Quality Assessment\n\nFor each CLAUDE.md file, evaluate against quality criteria. See [references\u002Fquality-criteria.md](references\u002Fquality-criteria.md) for detailed rubrics.\n\n**Quick Assessment Checklist:**\n\n| Criterion | Weight | Check |\n|-----------|--------|-------|\n| Commands\u002Fworkflows documented | High | Are build\u002Ftest\u002Fdeploy commands present? |\n| Architecture clarity | High | Can Claude understand the codebase structure? |\n| Non-obvious patterns | Medium | Are gotchas and quirks documented? |\n| Conciseness | Medium | No verbose explanations or obvious info? |\n| Currency | High | Does it reflect current codebase state? |\n| Actionability | High | Are instructions executable, not vague? |\n\n**Quality Scores:**\n- **A (90-100)**: Comprehensive, current, actionable\n- **B (70-89)**: Good coverage, minor gaps\n- **C (50-69)**: Basic info, missing key sections\n- **D (30-49)**: Sparse or outdated\n- **F (0-29)**: Missing or severely outdated\n\n### Phase 3: Quality Report Output\n\n**ALWAYS output the quality report BEFORE making any updates.**\n\nFormat:\n\n```\n## CLAUDE.md Quality Report\n\n### Summary\n- Files found: X\n- Average score: X\u002F100\n- Files needing update: X\n\n### File-by-File Assessment\n\n#### 1. .\u002FCLAUDE.md (Project Root)\n**Score: XX\u002F100 (Grade: X)**\n\n| Criterion | Score | Notes |\n|-----------|-------|-------|\n| Commands\u002Fworkflows | X\u002F20 | ... |\n| Architecture clarity | X\u002F20 | ... |\n| Non-obvious patterns | X\u002F15 | ... |\n| Conciseness | X\u002F15 | ... |\n| Currency | X\u002F15 | ... |\n| Actionability | X\u002F15 | ... |\n\n**Issues:**\n- [List specific problems]\n\n**Recommended additions:**\n- [List what should be added]\n\n#### 2. .\u002Fpackages\u002Fapi\u002FCLAUDE.md (Package-specific)\n...\n```\n\n### Phase 4: Targeted Updates\n\nAfter outputting the quality report, ask user for confirmation before updating.\n\n**Update Guidelines (Critical):**\n\n1. **Propose targeted additions only** - Focus on genuinely useful info:\n   - Commands or workflows discovered during analysis\n   - Gotchas or non-obvious patterns found in code\n   - Package relationships that weren't clear\n   - Testing approaches that work\n   - Configuration quirks\n\n2. **Keep it minimal** - Avoid:\n   - Restating what's obvious from the code\n   - Generic best practices already covered\n   - One-off fixes unlikely to recur\n   - Verbose explanations when a one-liner suffices\n\n3. **Show diffs** - For each change, show:\n   - Which CLAUDE.md file to update\n   - The specific addition (as a diff or quoted block)\n   - Brief explanation of why this helps future sessions\n\n**Diff Format:**\n\n```markdown\n### Update: .\u002FCLAUDE.md\n\n**Why:** Build command was missing, causing confusion about how to run the project.\n\n```diff\n+ ## Quick Start\n+\n+ ```bash\n+ npm install\n+ npm run dev  # Start development server on port 3000\n+ ```\n```\n```\n\n### Phase 5: Apply Updates\n\nAfter user approval, apply changes using the Edit tool. Preserve existing content structure.\n\n## Templates\n\nSee [references\u002Ftemplates.md](references\u002Ftemplates.md) for CLAUDE.md templates by project type.\n\n## Common Issues to Flag\n\n1. **Stale commands**: Build commands that no longer work\n2. **Missing dependencies**: Required tools not mentioned\n3. **Outdated architecture**: File structure that's changed\n4. **Missing environment setup**: Required env vars or config\n5. **Broken test commands**: Test scripts that have changed\n6. **Undocumented gotchas**: Non-obvious patterns not captured\n\n## User Tips to Share\n\nWhen presenting recommendations, remind users:\n\n- **`#` key shortcut**: During a Claude session, press `#` to have Claude auto-incorporate learnings into CLAUDE.md\n- **Keep it concise**: CLAUDE.md should be human-readable; dense is better than verbose\n- **Actionable commands**: All documented commands should be copy-paste ready\n- **Use `.claude.local.md`**: For personal preferences not shared with team (add to `.gitignore`)\n- **Global defaults**: Put user-wide preferences in `~\u002F.claude\u002FCLAUDE.md`\n\n## What Makes a Great CLAUDE.md\n\n**Key principles:**\n- Concise and human-readable\n- Actionable commands that can be copy-pasted\n- Project-specific patterns, not generic advice\n- Non-obvious gotchas and warnings\n\n**Recommended sections** (use only what's relevant):\n- Commands (build, test, dev, lint)\n- Architecture (directory structure)\n- Key Files (entry points, config)\n- Code Style (project conventions)\n- Environment (required vars, setup)\n- Testing (commands, patterns)\n- Gotchas (quirks, common mistakes)\n- Workflow (when to do what)\n",{"name":5,"tools":44,"description":7},"Read, Glob, Grep, Bash, Edit","main","dceb15d50832e6adf380bedc26dde03d251324b9","plugins\u002Fclaude-md-management\u002Fskills\u002Fclaude-md-improver",4875,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official","https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins","https:\u002F\u002Fgithub.com\u002Fanthropics","https:\u002F\u002Fanthropic.com","2026-11-12 03:40:35",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add anthropics\u002Fclaude-plugins-official --skill claude-md-improver",{"tool":60,"command":61},"bunx","bunx skills add anthropics\u002Fclaude-plugins-official --skill claude-md-improver",{"tool":63,"command":64},"pnpm","pnpm dlx skills add anthropics\u002Fclaude-plugins-official --skill claude-md-improver","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-md-management\u002Fskills\u002Fclaude-md-improver\u002FSKILL.md",true,[68,74,78],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fquality-criteria.md","REFERENCE","参考文档",2617,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-md-management\u002Fskills\u002Fclaude-md-improver\u002Freferences\u002Fquality-criteria.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Ftemplates.md",3687,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-md-management\u002Fskills\u002Fclaude-md-improver\u002Freferences\u002Ftemplates.md",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fupdate-guidelines.md",3197,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-md-management\u002Fskills\u002Fclaude-md-improver\u002Freferences\u002Fupdate-guidelines.md",[83,112,138,163,187,208],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":95,"publishedAt":39},"01M718BVSPNAK6S5NZCYFDBG6E","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-creator\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-creator\u002Fskills\u002Fskill-creator\u002FSKILL.md",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[96,97,98,36,99,100,23,101,102,103,104,105,106,107,108,109,27,110,111,33],"skill creator","creator","performance","run evals","new","analysis","create","optimize","variance analysis","run","edit","benchmark","existing skill","evals","accuracy","scratch",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":123,"publishedAt":39},"01M718BSVAWJRFN6MRCZZ0QX4X","session-report","Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~\u002F.claude\u002Fprojects transcripts.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fsession-report\u002Fskills\u002Fsession-report\u002FSKILL.md",[118],{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[124,125,126,127,128,129,130,131,132,133,134,135,136,137],"session","report","session report","projects","usage","generate","tokens","html report","transcripts","prompts","cache","code","html","subagents",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":147,"publishedAt":39},"01M718BPKHVD214FAS1T4E5XCE","receipts","Generate a personal Claude Code usage & impact report (\"receipts\") from this machine's local session transcripts — for justifying Claude Code usage\u002Fspend to a manager, self-review, or \"what have I been using this for\" check-ins. Mines ~\u002F.claude\u002Fprojects locally (no extra API calls beyond one final write-up), cross-references local git history, and writes a markdown report plus a self-contained HTML receipt to your home directory. Use when the user asks for \"receipts\", an \"impact report\", \"usage report\", wants to \"show my Claude Code activity\", \"prove the value of Claude Code\", or runs `\u002Freceipts`.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Freceipts\u002Fskills\u002Freceipts\u002FSKILL.md",[144],{"categoryNo":145,"categoryName":146,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000030","开发工程师",[140,127,148,149,150,151,23,135,152,153,154,155,129,156,157,158,159,160,161,162],"show","up","local","impact","api","review","self","references","markdown","directory","write","git","activity","my","manager",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":39},"01M718BJMX0T4691FJQ62GYY5C","project-artifact","Generate and publish a project status artifact — an opinionated, tabbed status page for a project too big for one update (overview & success criteria, the workstream sequence, next steps, plus background, plan, risks & open questions, and decisions\u002FFAQ when they earn a tab) — published with the built-in Artifact tool to a default-private claude.ai page the user can share with teammates. Use when a piece of work spans several workstreams and you want a shareable overview kept current. Each artifact is backed by a small per-project config in the plugin data dir, so refreshing it re-gathers live state, redeploys the same URL, and reports only the delta. For software projects whose workstreams are PRs, also read swe.md (the X.Y PR-numbering convention; pulling PR state with gh\u002Fgit; a per-PR detail block). Needs the built-in Artifact tool (claude.ai login). Not for single-PR changes or public docs.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fproject-artifact\u002Fskills\u002Fproject-artifact\u002FSKILL.md",[],[21,170,171,172,127,173,174,175,176,177,178,23,179,180,181,182,183,184,185,186],"artifact","project artifact","project status","re","default","next steps","open","only","SWE","URL","you","reports","publish","work","plan","status page","next",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":194,"publishedAt":39},"01M718BF1TTFP5CM0S5HBW64FJ","skill-development","This skill should be used when the user wants to \"create a skill\", \"add a skill to plugin\", \"write a new skill\", \"improve skill description\", \"organize skill content\", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fplugin-dev\u002Fskills\u002Fskill-development\u002FSKILL.md",[193],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[195,196,197,36,100,198,23,135,102,199,158,200,201,202,203,27,204,205,206,207],"development","skill development","skill to plugin","improve skill","structure","organize","new skill","claude code plugins","add","progressive","best practices","progressive disclosure","plugin",{"skillNo":209,"name":210,"nameZh":6,"description":211,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":212,"categories":213,"keywords":215,"publishedAt":39},"01M718BCARZ2J4PW0X3AJCZ8MZ","plugin-structure","This skill should be used when the user asks to \"create a plugin\", \"scaffold a plugin\", \"understand plugin structure\", \"organize plugin components\", \"set up plugin.json\", \"use ${CLAUDE_PLUGIN_ROOT}\", \"add commands\u002Fagents\u002Fskills\u002Fhooks\", \"configure auto-discovery\", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fplugin-dev\u002Fskills\u002Fplugin-structure\u002FSKILL.md",[214],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[199,216,207,217,218,219,149,220,221,23,222,135,223,224,102,225,226,227,157,228],"Plugin Structure","SET","plugin architecture","hooks","auto-discovery","auto","configure","components","architecture","component","layout","organization","commands"]