[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74X95CDNEC3F3WHWVP5QMM2":3,"skill-same:01M74X95CDNEC3F3WHWVP5QMM2":45},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M74X95CDNEC3F3WHWVP5QMM2","write-a-skill",null,"Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.","DS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend","DS-PROYECTO-ARROW-MAZE","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F284100063?v=4","01M74X8A9F5638W98PBEJ2BY4C","ARROW-MAZE-EQ01","01M74X8AA6RGDRE1TMHBH95A7M",0,"MIT","https:\u002F\u002Fgithub.com\u002FDS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: write-a-skill\ndescription: Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.\n---\n\n# Writing Skills\n\n## Source of truth: `.agents\u002Fskills\u002F`\n\nThis repo keeps **all real skill content in `.agents\u002Fskills\u002F`**. The `.claude\u002Fskills\u002F`\nfolder holds only lightweight pointers back to it, so there is a single source of truth.\n\nWhen creating or updating a skill, you **always** do two things:\n\n1. Write \u002F edit the actual files under `.agents\u002Fskills\u002F\u003Cskill-name>\u002F`.\n2. Generate the corresponding pointer file(s) under `.claude\u002Fskills\u002F\u003Cskill-name>\u002F`.\n\nNever put real instructions in `.claude\u002Fskills\u002F` — edit `.agents\u002Fskills\u002F` and the\npointer picks it up.\n\n### Pointer rules\n\n- **`SKILL.md`** — keep only the YAML frontmatter (`name`, `description`, and any\n  other frontmatter fields from the source), then a single pointer line in the body.\n  The frontmatter is required so Claude Code can discover the skill and auto-trigger it.\n\n  ```md\n  ---\n  name: zoom-out\n  description: \u003Ccopied verbatim from the source SKILL.md frontmatter>\n  ---\n\n  See @.agents\u002Fskills\u002Fzoom-out\u002FSKILL.md\n  ```\n\n- **Every other file** (REFERENCE.md, EXAMPLES.md, *-FORMAT.md, TEMPLATE.md, scripts, …)\n  — a single pointer line, no frontmatter:\n\n  ```\n  See @.agents\u002Fskills\u002Fzoom-out\u002FREFERENCE.md\n  ```\n\nThe pointer path mirrors the file's relative path under `.agents\u002Fskills\u002F`.\n\n## Process\n\n1. **Gather requirements** - ask user about:\n   - What task\u002Fdomain does the skill cover?\n   - What specific use cases should it handle?\n   - Does it need executable scripts or just instructions?\n   - Any reference materials to include?\n\n2. **Draft the skill in `.agents\u002Fskills\u002F`** - create:\n   - SKILL.md with concise instructions\n   - Additional reference files if content exceeds 500 lines\n   - Utility scripts if deterministic operations needed\n\n3. **Generate pointers in `.claude\u002Fskills\u002F`** - create the pointer file(s) by hand\n   following the rules above, mirroring each source file's relative path.\n\n4. **Review with user** - present draft and ask:\n   - Does this cover your use cases?\n   - Anything missing or unclear?\n   - Should any section be more\u002Fless detailed?\n\n## Skill Structure\n\n`.agents\u002Fskills\u002F` holds the real content:\n\n```\n.agents\u002Fskills\u002Fskill-name\u002F\n├── SKILL.md           # Main instructions (required)\n├── REFERENCE.md       # Detailed docs (if needed)\n├── EXAMPLES.md        # Usage examples (if needed)\n└── scripts\u002F           # Utility scripts (if needed)\n    └── helper.js\n```\n\n`.claude\u002Fskills\u002F` mirrors the same paths, but every file is a one-line pointer\n(SKILL.md additionally keeps its frontmatter):\n\n```\n.claude\u002Fskills\u002Fskill-name\u002F\n├── SKILL.md           # frontmatter + \"See @.agents\u002Fskills\u002Fskill-name\u002FSKILL.md\"\n├── REFERENCE.md       # \"See @.agents\u002Fskills\u002Fskill-name\u002FREFERENCE.md\"\n├── EXAMPLES.md        # \"See @.agents\u002Fskills\u002Fskill-name\u002FEXAMPLES.md\"\n└── scripts\u002F\n    └── helper.js      # \"See @.agents\u002Fskills\u002Fskill-name\u002Fscripts\u002Fhelper.js\"\n```\n\n## SKILL.md Template\n\n```md\n---\nname: skill-name\ndescription: Brief description of capability. Use when [specific triggers].\n---\n\n# Skill Name\n\n## Quick start\n\n[Minimal working example]\n\n## Workflows\n\n[Step-by-step processes with checklists for complex tasks]\n\n## Advanced features\n\n[Link to separate files: See [REFERENCE.md](REFERENCE.md)]\n```\n\n## Description Requirements\n\nThe description is **the only thing your agent sees** when deciding which skill to load. It's surfaced in the system prompt alongside all other installed skills. Your agent reads these descriptions and picks the relevant skill based on the user's request.\n\n**Goal**: Give your agent just enough info to know:\n\n1. What capability this skill provides\n2. When\u002Fwhy to trigger it (specific keywords, contexts, file types)\n\n**Format**:\n\n- Max 1024 chars\n- Write in third person\n- First sentence: what it does\n- Second sentence: \"Use when [specific triggers]\"\n\n**Good example**:\n\n```\nExtract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when user mentions PDFs, forms, or document extraction.\n```\n\n**Bad example**:\n\n```\nHelps with documents.\n```\n\nThe bad example gives your agent no way to distinguish this from other document skills.\n\n## When to Add Scripts\n\nAdd utility scripts when:\n\n- Operation is deterministic (validation, formatting)\n- Same code would be generated repeatedly\n- Errors need explicit handling\n\nScripts save tokens and improve reliability vs generated code.\n\n## When to Split Files\n\nSplit into separate files when:\n\n- SKILL.md exceeds 100 lines\n- Content has distinct domains (finance vs sales schemas)\n- Advanced features are rarely needed\n\n## Review Checklist\n\nAfter drafting, verify:\n\n- [ ] Real content lives in `.agents\u002Fskills\u002F\u003Cskill-name>\u002F`\n- [ ] A matching pointer exists in `.claude\u002Fskills\u002F\u003Cskill-name>\u002F` for every source file\n- [ ] Pointer `SKILL.md` keeps the source frontmatter; other pointers are a single line\n- [ ] Description includes triggers (\"Use when...\")\n- [ ] SKILL.md under 100 lines\n- [ ] No time-sensitive info\n- [ ] Consistent terminology\n- [ ] Concrete examples included\n- [ ] References one level deep\n","# Writing Skills\n\n## Source of truth: `.agents\u002Fskills\u002F`\n\nThis repo keeps **all real skill content in `.agents\u002Fskills\u002F`**. The `.claude\u002Fskills\u002F`\nfolder holds only lightweight pointers back to it, so there is a single source of truth.\n\nWhen creating or updating a skill, you **always** do two things:\n\n1. Write \u002F edit the actual files under `.agents\u002Fskills\u002F\u003Cskill-name>\u002F`.\n2. Generate the corresponding pointer file(s) under `.claude\u002Fskills\u002F\u003Cskill-name>\u002F`.\n\nNever put real instructions in `.claude\u002Fskills\u002F` — edit `.agents\u002Fskills\u002F` and the\npointer picks it up.\n\n### Pointer rules\n\n- **`SKILL.md`** — keep only the YAML frontmatter (`name`, `description`, and any\n  other frontmatter fields from the source), then a single pointer line in the body.\n  The frontmatter is required so Claude Code can discover the skill and auto-trigger it.\n\n  ```md\n  ---\n  name: zoom-out\n  description: \u003Ccopied verbatim from the source SKILL.md frontmatter>\n  ---\n\n  See @.agents\u002Fskills\u002Fzoom-out\u002FSKILL.md\n  ```\n\n- **Every other file** (REFERENCE.md, EXAMPLES.md, *-FORMAT.md, TEMPLATE.md, scripts, …)\n  — a single pointer line, no frontmatter:\n\n  ```\n  See @.agents\u002Fskills\u002Fzoom-out\u002FREFERENCE.md\n  ```\n\nThe pointer path mirrors the file's relative path under `.agents\u002Fskills\u002F`.\n\n## Process\n\n1. **Gather requirements** - ask user about:\n   - What task\u002Fdomain does the skill cover?\n   - What specific use cases should it handle?\n   - Does it need executable scripts or just instructions?\n   - Any reference materials to include?\n\n2. **Draft the skill in `.agents\u002Fskills\u002F`** - create:\n   - SKILL.md with concise instructions\n   - Additional reference files if content exceeds 500 lines\n   - Utility scripts if deterministic operations needed\n\n3. **Generate pointers in `.claude\u002Fskills\u002F`** - create the pointer file(s) by hand\n   following the rules above, mirroring each source file's relative path.\n\n4. **Review with user** - present draft and ask:\n   - Does this cover your use cases?\n   - Anything missing or unclear?\n   - Should any section be more\u002Fless detailed?\n\n## Skill Structure\n\n`.agents\u002Fskills\u002F` holds the real content:\n\n```\n.agents\u002Fskills\u002Fskill-name\u002F\n├── SKILL.md           # Main instructions (required)\n├── REFERENCE.md       # Detailed docs (if needed)\n├── EXAMPLES.md        # Usage examples (if needed)\n└── scripts\u002F           # Utility scripts (if needed)\n    └── helper.js\n```\n\n`.claude\u002Fskills\u002F` mirrors the same paths, but every file is a one-line pointer\n(SKILL.md additionally keeps its frontmatter):\n\n```\n.claude\u002Fskills\u002Fskill-name\u002F\n├── SKILL.md           # frontmatter + \"See @.agents\u002Fskills\u002Fskill-name\u002FSKILL.md\"\n├── REFERENCE.md       # \"See @.agents\u002Fskills\u002Fskill-name\u002FREFERENCE.md\"\n├── EXAMPLES.md        # \"See @.agents\u002Fskills\u002Fskill-name\u002FEXAMPLES.md\"\n└── scripts\u002F\n    └── helper.js      # \"See @.agents\u002Fskills\u002Fskill-name\u002Fscripts\u002Fhelper.js\"\n```\n\n## SKILL.md Template\n\n```md\n---\nname: skill-name\ndescription: Brief description of capability. Use when [specific triggers].\n---\n\n# Skill Name\n\n## Quick start\n\n[Minimal working example]\n\n## Workflows\n\n[Step-by-step processes with checklists for complex tasks]\n\n## Advanced features\n\n[Link to separate files: See [REFERENCE.md](REFERENCE.md)]\n```\n\n## Description Requirements\n\nThe description is **the only thing your agent sees** when deciding which skill to load. It's surfaced in the system prompt alongside all other installed skills. Your agent reads these descriptions and picks the relevant skill based on the user's request.\n\n**Goal**: Give your agent just enough info to know:\n\n1. What capability this skill provides\n2. When\u002Fwhy to trigger it (specific keywords, contexts, file types)\n\n**Format**:\n\n- Max 1024 chars\n- Write in third person\n- First sentence: what it does\n- Second sentence: \"Use when [specific triggers]\"\n\n**Good example**:\n\n```\nExtract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when user mentions PDFs, forms, or document extraction.\n```\n\n**Bad example**:\n\n```\nHelps with documents.\n```\n\nThe bad example gives your agent no way to distinguish this from other document skills.\n\n## When to Add Scripts\n\nAdd utility scripts when:\n\n- Operation is deterministic (validation, formatting)\n- Same code would be generated repeatedly\n- Errors need explicit handling\n\nScripts save tokens and improve reliability vs generated code.\n\n## When to Split Files\n\nSplit into separate files when:\n\n- SKILL.md exceeds 100 lines\n- Content has distinct domains (finance vs sales schemas)\n- Advanced features are rarely needed\n\n## Review Checklist\n\nAfter drafting, verify:\n\n- [ ] Real content lives in `.agents\u002Fskills\u002F\u003Cskill-name>\u002F`\n- [ ] A matching pointer exists in `.claude\u002Fskills\u002F\u003Cskill-name>\u002F` for every source file\n- [ ] Pointer `SKILL.md` keeps the source frontmatter; other pointers are a single line\n- [ ] Description includes triggers (\"Use when...\")\n- [ ] SKILL.md under 100 lines\n- [ ] No time-sensitive info\n- [ ] Consistent terminology\n- [ ] Concrete examples included\n- [ ] References one level deep\n",{"name":5,"description":7},"main","efd18d74b40a4e07b83c264b9dd4784b0f2f0546",".agents\u002Fskills\u002Fwrite-a-skill","https:\u002F\u002Fgithub.com\u002FDS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend","https:\u002F\u002Fgithub.com\u002FDS-PROYECTO-ARROW-MAZE","Contiene el desarrollo de un clon funcional del juego casual \"Arrow Maze — Escape Puzzle\",  como proyecto semestral para la asignatura Desarrollo de Software.","2026-07-19 11:55:07",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add DS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend --skill write-a-skill",{"tool":37,"command":38},"bunx","bunx skills add DS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend --skill write-a-skill",{"tool":40,"command":41},"pnpm","pnpm dlx skills add DS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend --skill write-a-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",true,[],[46,53,58,65,72,79],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M74X9ZAFBWMXQJRPHW7D5D8V","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","https:\u002F\u002Fgithub.com\u002FDS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fzoom-out\u002FSKILL.md",[],[],{"skillNo":54,"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":55,"categories":56,"keywords":57,"publishedAt":19},"01M74X9XSNYXAYY6WHX0GZWXM8","https:\u002F\u002Fgithub.com\u002FDS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M74X9WHQZNCASPRM3FWJKD1J","teach","Teach the user a new skill or concept, within this workspace.","https:\u002F\u002Fgithub.com\u002FDS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fteach\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M74X9T1XWW6GQ9XSRGS3PK11","tdd-strict","Enforce strict Test-Driven Development (TDD) cycle. Use whenever writing new features, fixing bugs, or implementing use cases.","https:\u002F\u002Fgithub.com\u002FDS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftdd-strict\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M74X9QHRX6V1DMM1YSNTRE3S","nestjs-patterns","NestJS architecture patterns for modules, controllers, providers, DTO validation, guards, interceptors, config, and production-grade TypeScript backends.","https:\u002F\u002Fgithub.com\u002FDS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fnestjs-patterns\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M74X9NZJXQ59GAP70V87S6W5","handoff","Compact the current conversation into a handoff document for another agent to pick up.","https:\u002F\u002Fgithub.com\u002FDS-PROYECTO-ARROW-MAZE\u002Farrowmaze-frontend\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhandoff\u002FSKILL.md",[],[]]