[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BXWGV66SSKYFMCHTRKEDKK":3,"skill-same:01M6BXWGV66SSKYFMCHTRKEDKK":54},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":14,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M6BXWGV66SSKYFMCHTRKEDKK","skill-writer",null,"Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.","vjrasane\u002Fdotfiles","vjrasane","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3148501?v=4","01M6BXVXZN07KKKXF9Q8JNN90K","Ville Räsänen","01M6BXVY3R8G19AN5BRA73H85R",0,"GPL-2.0","https:\u002F\u002Fgithub.com\u002Fvjrasane\u002Fdotfiles\u002Fblob\u002Fmain\u002Fllms\u002Fclaude\u002Fskills\u002Fskill-writer\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],"skill writer","design","create","code","help","2026-11-10 10:12:30",false,"---\nname: skill-writer\ndescription: Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.\n---\n\n# Skill Writer\n\nThis Skill helps you create well-structured Agent Skills for Claude Code that follow best practices and validation requirements.\n\n## When to use this Skill\n\nUse this Skill when:\n- Creating a new Agent Skill\n- Writing or updating SKILL.md files\n- Designing skill structure and frontmatter\n- Troubleshooting skill discovery issues\n- Converting existing prompts or workflows into Skills\n\n## Instructions\n\n### Step 1: Determine Skill scope\n\nFirst, understand what the Skill should do:\n\n1. **Ask clarifying questions**:\n   - What specific capability should this Skill provide?\n   - When should Claude use this Skill?\n   - What tools or resources does it need?\n   - Is this for personal use or team sharing?\n\n2. **Keep it focused**: One Skill = one capability\n   - Good: \"PDF form filling\", \"Excel data analysis\"\n   - Too broad: \"Document processing\", \"Data tools\"\n\n### Step 2: Choose Skill location\n\nDetermine where to create the Skill:\n\n**Global Skills** (`~\u002Fdotfiles\u002Fclaude\u002Fskills\u002F`):\n- Home Manager symlinks this directory to `~\u002F.claude\u002Fskills\u002F`\n- Always create global\u002Fpersonal skills here so they are version-controlled and properly symlinked\n- Individual workflows, preferences, and personal productivity tools\n- **Important**: After creating the skill directory, you must also register it in `modules\u002Fagents.nix` under `programs.claude-code.skills` (e.g. `skill-name = \"${dotfiles}\u002Fclaude\u002Fskills\u002Fskill-name\";`). The skill won't be discovered until this entry exists and Home Manager is rebuilt.\n\n**Project Skills** (`.claude\u002Fskills\u002F` relative to a project root):\n- Team workflows and conventions\n- Project-specific expertise\n- Shared utilities (committed to the project's git repo)\n\n### Step 3: Create Skill structure\n\nCreate the directory and files:\n\n```bash\n# Global (managed by Home Manager, symlinked to ~\u002F.claude\u002Fskills\u002F)\nmkdir -p ~\u002Fdotfiles\u002Fclaude\u002Fskills\u002Fskill-name\n\n# Project-specific\nmkdir -p .claude\u002Fskills\u002Fskill-name\n```\n\nFor multi-file Skills:\n```\nskill-name\u002F\n├── SKILL.md (required)\n├── reference.md (optional)\n├── examples.md (optional)\n├── scripts\u002F\n│   └── helper.py (optional)\n└── templates\u002F\n    └── template.txt (optional)\n```\n\n### Step 4: Write SKILL.md frontmatter\n\nCreate YAML frontmatter with required fields:\n\n```yaml\n---\nname: skill-name\ndescription: Brief description of what this does and when to use it\n---\n```\n\n**Field requirements**:\n\n- **name**:\n  - Lowercase letters, numbers, hyphens only\n  - Max 64 characters\n  - Must match directory name\n  - Good: `pdf-processor`, `git-commit-helper`\n  - Bad: `PDF_Processor`, `Git Commits!`\n\n- **description**:\n  - Max 1024 characters\n  - Include BOTH what it does AND when to use it\n  - Use specific trigger words users would say\n  - Mention file types, operations, and context\n\n**Optional frontmatter fields**:\n\n- **allowed-tools**: Restrict tool access (comma-separated list)\n  ```yaml\n  allowed-tools: Read, Grep, Glob\n  ```\n  Use for:\n  - Read-only Skills\n  - Security-sensitive workflows\n  - Limited-scope operations\n\n### Step 5: Write effective descriptions\n\nThe description is critical for Claude to discover your Skill.\n\n**Formula**: `[What it does] + [When to use it] + [Key triggers]`\n\n**Examples**:\n\n✅ **Good**:\n```yaml\ndescription: Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.\n```\n\n✅ **Good**:\n```yaml\ndescription: Analyze Excel spreadsheets, create pivot tables, and generate charts. Use when working with Excel files, spreadsheets, or analyzing tabular data in .xlsx format.\n```\n\n❌ **Too vague**:\n```yaml\ndescription: Helps with documents\ndescription: For data analysis\n```\n\n**Tips**:\n- Include specific file extensions (.pdf, .xlsx, .json)\n- Mention common user phrases (\"analyze\", \"extract\", \"generate\")\n- List concrete operations (not generic verbs)\n- Add context clues (\"Use when...\", \"For...\")\n\n### Step 6: Structure the Skill content\n\nUse clear Markdown sections:\n\n```markdown\n# Skill Name\n\nBrief overview of what this Skill does.\n\n## Quick start\n\nProvide a simple example to get started immediately.\n\n## Instructions\n\nStep-by-step guidance for Claude:\n1. First step with clear action\n2. Second step with expected outcome\n3. Handle edge cases\n\n## Examples\n\nShow concrete usage examples with code or commands.\n\n## Best practices\n\n- Key conventions to follow\n- Common pitfalls to avoid\n- When to use vs. not use\n\n## Requirements\n\nList any dependencies or prerequisites:\n```bash\npip install package-name\n```\n\n## Advanced usage\n\nFor complex scenarios, see [reference.md](reference.md).\n```\n\n### Step 7: Add supporting files (optional)\n\nCreate additional files for progressive disclosure:\n\n**reference.md**: Detailed API docs, advanced options\n**examples.md**: Extended examples and use cases\n**scripts\u002F**: Helper scripts and utilities\n**templates\u002F**: File templates or boilerplate\n\nReference them from SKILL.md:\n```markdown\nFor advanced usage, see [reference.md](reference.md).\n\nRun the helper script:\n\\`\\`\\`bash\npython scripts\u002Fhelper.py input.txt\n\\`\\`\\`\n```\n\n### Step 8: Validate the Skill\n\nCheck these requirements:\n\n✅ **File structure**:\n- [ ] SKILL.md exists in correct location\n- [ ] Directory name matches frontmatter `name`\n\n✅ **YAML frontmatter**:\n- [ ] Opening `---` on line 1\n- [ ] Closing `---` before content\n- [ ] Valid YAML (no tabs, correct indentation)\n- [ ] `name` follows naming rules\n- [ ] `description` is specific and \u003C 1024 chars\n\n✅ **Content quality**:\n- [ ] Clear instructions for Claude\n- [ ] Concrete examples provided\n- [ ] Edge cases handled\n- [ ] Dependencies listed (if any)\n\n✅ **Testing**:\n- [ ] Description matches user questions\n- [ ] Skill activates on relevant queries\n- [ ] Instructions are clear and actionable\n\n### Step 9: Test the Skill\n\n1. **Restart Claude Code** (if running) to load the Skill\n\n2. **Ask relevant questions** that match the description:\n   ```\n   Can you help me extract text from this PDF?\n   ```\n\n3. **Verify activation**: Claude should use the Skill automatically\n\n4. **Check behavior**: Confirm Claude follows the instructions correctly\n\n### Step 10: Debug if needed\n\nIf Claude doesn't use the Skill:\n\n1. **Make description more specific**:\n   - Add trigger words\n   - Include file types\n   - Mention common user phrases\n\n2. **Check file location**:\n   ```bash\n   # Global skills (source managed by Home Manager)\n   ls ~\u002Fdotfiles\u002Fclaude\u002Fskills\u002Fskill-name\u002FSKILL.md\n   # Verify symlink is active\n   ls ~\u002F.claude\u002Fskills\u002Fskill-name\u002FSKILL.md\n   # Project skills\n   ls .claude\u002Fskills\u002Fskill-name\u002FSKILL.md\n   ```\n\n3. **Validate YAML**:\n   ```bash\n   cat SKILL.md | head -n 10\n   ```\n\n4. **Run debug mode**:\n   ```bash\n   claude --debug\n   ```\n\n## Common patterns\n\n### Read-only Skill\n\n```yaml\n---\nname: code-reader\ndescription: Read and analyze code without making changes. Use for code review, understanding codebases, or documentation.\nallowed-tools: Read, Grep, Glob\n---\n```\n\n### Script-based Skill\n\n```yaml\n---\nname: data-processor\ndescription: Process CSV and JSON data files with Python scripts. Use when analyzing data files or transforming datasets.\n---\n\n# Data Processor\n\n## Instructions\n\n1. Use the processing script:\n\\`\\`\\`bash\npython scripts\u002Fprocess.py input.csv --output results.json\n\\`\\`\\`\n\n2. Validate output with:\n\\`\\`\\`bash\npython scripts\u002Fvalidate.py results.json\n\\`\\`\\`\n```\n\n### Multi-file Skill with progressive disclosure\n\n```yaml\n---\nname: api-designer\ndescription: Design REST APIs following best practices. Use when creating API endpoints, designing routes, or planning API architecture.\n---\n\n# API Designer\n\nQuick start: See [examples.md](examples.md)\n\nDetailed reference: See [reference.md](reference.md)\n\n## Instructions\n\n1. Gather requirements\n2. Design endpoints (see examples.md)\n3. Document with OpenAPI spec\n4. Review against best practices (see reference.md)\n```\n\n## Best practices for Skill authors\n\n1. **One Skill, one purpose**: Don't create mega-Skills\n2. **Specific descriptions**: Include trigger words users will say\n3. **Clear instructions**: Write for Claude, not humans\n4. **Concrete examples**: Show real code, not pseudocode\n5. **List dependencies**: Mention required packages in description\n6. **Test with teammates**: Verify activation and clarity\n7. **Version your Skills**: Document changes in content\n8. **Use progressive disclosure**: Put advanced details in separate files\n\n## Validation checklist\n\nBefore finalizing a Skill, verify:\n\n- [ ] Name is lowercase, hyphens only, max 64 chars\n- [ ] Description is specific and \u003C 1024 chars\n- [ ] Description includes \"what\" and \"when\"\n- [ ] YAML frontmatter is valid\n- [ ] Instructions are step-by-step\n- [ ] Examples are concrete and realistic\n- [ ] Dependencies are documented\n- [ ] File paths use forward slashes\n- [ ] Skill activates on relevant queries\n- [ ] Claude follows instructions correctly\n\n## Troubleshooting\n\n**Skill doesn't activate**:\n- Make description more specific with trigger words\n- Include file types and operations in description\n- Add \"Use when...\" clause with user phrases\n\n**Multiple Skills conflict**:\n- Make descriptions more distinct\n- Use different trigger words\n- Narrow the scope of each Skill\n\n**Skill has errors**:\n- Check YAML syntax (no tabs, proper indentation)\n- Verify file paths (use forward slashes)\n- Ensure scripts have execute permissions\n- List all dependencies\n\n## Examples\n\nSee the documentation for complete examples:\n- Simple single-file Skill (commit-helper)\n- Skill with tool permissions (code-reviewer)\n- Multi-file Skill (pdf-processing)\n\n## Output format\n\nWhen creating a Skill, I will:\n\n1. Ask clarifying questions about scope and requirements\n2. Suggest a Skill name and location\n3. Create the SKILL.md file with proper frontmatter\n4. Include clear instructions and examples\n5. Add supporting files if needed\n6. Provide testing instructions\n7. Validate against all requirements\n\nThe result will be a complete, working Skill that follows all best practices and validation rules.\n","# Skill Writer\n\nThis Skill helps you create well-structured Agent Skills for Claude Code that follow best practices and validation requirements.\n\n## When to use this Skill\n\nUse this Skill when:\n- Creating a new Agent Skill\n- Writing or updating SKILL.md files\n- Designing skill structure and frontmatter\n- Troubleshooting skill discovery issues\n- Converting existing prompts or workflows into Skills\n\n## Instructions\n\n### Step 1: Determine Skill scope\n\nFirst, understand what the Skill should do:\n\n1. **Ask clarifying questions**:\n   - What specific capability should this Skill provide?\n   - When should Claude use this Skill?\n   - What tools or resources does it need?\n   - Is this for personal use or team sharing?\n\n2. **Keep it focused**: One Skill = one capability\n   - Good: \"PDF form filling\", \"Excel data analysis\"\n   - Too broad: \"Document processing\", \"Data tools\"\n\n### Step 2: Choose Skill location\n\nDetermine where to create the Skill:\n\n**Global Skills** (`~\u002Fdotfiles\u002Fclaude\u002Fskills\u002F`):\n- Home Manager symlinks this directory to `~\u002F.claude\u002Fskills\u002F`\n- Always create global\u002Fpersonal skills here so they are version-controlled and properly symlinked\n- Individual workflows, preferences, and personal productivity tools\n- **Important**: After creating the skill directory, you must also register it in `modules\u002Fagents.nix` under `programs.claude-code.skills` (e.g. `skill-name = \"${dotfiles}\u002Fclaude\u002Fskills\u002Fskill-name\";`). The skill won't be discovered until this entry exists and Home Manager is rebuilt.\n\n**Project Skills** (`.claude\u002Fskills\u002F` relative to a project root):\n- Team workflows and conventions\n- Project-specific expertise\n- Shared utilities (committed to the project's git repo)\n\n### Step 3: Create Skill structure\n\nCreate the directory and files:\n\n```bash\n# Global (managed by Home Manager, symlinked to ~\u002F.claude\u002Fskills\u002F)\nmkdir -p ~\u002Fdotfiles\u002Fclaude\u002Fskills\u002Fskill-name\n\n# Project-specific\nmkdir -p .claude\u002Fskills\u002Fskill-name\n```\n\nFor multi-file Skills:\n```\nskill-name\u002F\n├── SKILL.md (required)\n├── reference.md (optional)\n├── examples.md (optional)\n├── scripts\u002F\n│   └── helper.py (optional)\n└── templates\u002F\n    └── template.txt (optional)\n```\n\n### Step 4: Write SKILL.md frontmatter\n\nCreate YAML frontmatter with required fields:\n\n```yaml\n---\nname: skill-name\ndescription: Brief description of what this does and when to use it\n---\n```\n\n**Field requirements**:\n\n- **name**:\n  - Lowercase letters, numbers, hyphens only\n  - Max 64 characters\n  - Must match directory name\n  - Good: `pdf-processor`, `git-commit-helper`\n  - Bad: `PDF_Processor`, `Git Commits!`\n\n- **description**:\n  - Max 1024 characters\n  - Include BOTH what it does AND when to use it\n  - Use specific trigger words users would say\n  - Mention file types, operations, and context\n\n**Optional frontmatter fields**:\n\n- **allowed-tools**: Restrict tool access (comma-separated list)\n  ```yaml\n  allowed-tools: Read, Grep, Glob\n  ```\n  Use for:\n  - Read-only Skills\n  - Security-sensitive workflows\n  - Limited-scope operations\n\n### Step 5: Write effective descriptions\n\nThe description is critical for Claude to discover your Skill.\n\n**Formula**: `[What it does] + [When to use it] + [Key triggers]`\n\n**Examples**:\n\n✅ **Good**:\n```yaml\ndescription: Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.\n```\n\n✅ **Good**:\n```yaml\ndescription: Analyze Excel spreadsheets, create pivot tables, and generate charts. Use when working with Excel files, spreadsheets, or analyzing tabular data in .xlsx format.\n```\n\n❌ **Too vague**:\n```yaml\ndescription: Helps with documents\ndescription: For data analysis\n```\n\n**Tips**:\n- Include specific file extensions (.pdf, .xlsx, .json)\n- Mention common user phrases (\"analyze\", \"extract\", \"generate\")\n- List concrete operations (not generic verbs)\n- Add context clues (\"Use when...\", \"For...\")\n\n### Step 6: Structure the Skill content\n\nUse clear Markdown sections:\n\n```markdown\n# Skill Name\n\nBrief overview of what this Skill does.\n\n## Quick start\n\nProvide a simple example to get started immediately.\n\n## Instructions\n\nStep-by-step guidance for Claude:\n1. First step with clear action\n2. Second step with expected outcome\n3. Handle edge cases\n\n## Examples\n\nShow concrete usage examples with code or commands.\n\n## Best practices\n\n- Key conventions to follow\n- Common pitfalls to avoid\n- When to use vs. not use\n\n## Requirements\n\nList any dependencies or prerequisites:\n```bash\npip install package-name\n```\n\n## Advanced usage\n\nFor complex scenarios, see [reference.md](reference.md).\n```\n\n### Step 7: Add supporting files (optional)\n\nCreate additional files for progressive disclosure:\n\n**reference.md**: Detailed API docs, advanced options\n**examples.md**: Extended examples and use cases\n**scripts\u002F**: Helper scripts and utilities\n**templates\u002F**: File templates or boilerplate\n\nReference them from SKILL.md:\n```markdown\nFor advanced usage, see [reference.md](reference.md).\n\nRun the helper script:\n\\`\\`\\`bash\npython scripts\u002Fhelper.py input.txt\n\\`\\`\\`\n```\n\n### Step 8: Validate the Skill\n\nCheck these requirements:\n\n✅ **File structure**:\n- [ ] SKILL.md exists in correct location\n- [ ] Directory name matches frontmatter `name`\n\n✅ **YAML frontmatter**:\n- [ ] Opening `---` on line 1\n- [ ] Closing `---` before content\n- [ ] Valid YAML (no tabs, correct indentation)\n- [ ] `name` follows naming rules\n- [ ] `description` is specific and \u003C 1024 chars\n\n✅ **Content quality**:\n- [ ] Clear instructions for Claude\n- [ ] Concrete examples provided\n- [ ] Edge cases handled\n- [ ] Dependencies listed (if any)\n\n✅ **Testing**:\n- [ ] Description matches user questions\n- [ ] Skill activates on relevant queries\n- [ ] Instructions are clear and actionable\n\n### Step 9: Test the Skill\n\n1. **Restart Claude Code** (if running) to load the Skill\n\n2. **Ask relevant questions** that match the description:\n   ```\n   Can you help me extract text from this PDF?\n   ```\n\n3. **Verify activation**: Claude should use the Skill automatically\n\n4. **Check behavior**: Confirm Claude follows the instructions correctly\n\n### Step 10: Debug if needed\n\nIf Claude doesn't use the Skill:\n\n1. **Make description more specific**:\n   - Add trigger words\n   - Include file types\n   - Mention common user phrases\n\n2. **Check file location**:\n   ```bash\n   # Global skills (source managed by Home Manager)\n   ls ~\u002Fdotfiles\u002Fclaude\u002Fskills\u002Fskill-name\u002FSKILL.md\n   # Verify symlink is active\n   ls ~\u002F.claude\u002Fskills\u002Fskill-name\u002FSKILL.md\n   # Project skills\n   ls .claude\u002Fskills\u002Fskill-name\u002FSKILL.md\n   ```\n\n3. **Validate YAML**:\n   ```bash\n   cat SKILL.md | head -n 10\n   ```\n\n4. **Run debug mode**:\n   ```bash\n   claude --debug\n   ```\n\n## Common patterns\n\n### Read-only Skill\n\n```yaml\n---\nname: code-reader\ndescription: Read and analyze code without making changes. Use for code review, understanding codebases, or documentation.\nallowed-tools: Read, Grep, Glob\n---\n```\n\n### Script-based Skill\n\n```yaml\n---\nname: data-processor\ndescription: Process CSV and JSON data files with Python scripts. Use when analyzing data files or transforming datasets.\n---\n\n# Data Processor\n\n## Instructions\n\n1. Use the processing script:\n\\`\\`\\`bash\npython scripts\u002Fprocess.py input.csv --output results.json\n\\`\\`\\`\n\n2. Validate output with:\n\\`\\`\\`bash\npython scripts\u002Fvalidate.py results.json\n\\`\\`\\`\n```\n\n### Multi-file Skill with progressive disclosure\n\n```yaml\n---\nname: api-designer\ndescription: Design REST APIs following best practices. Use when creating API endpoints, designing routes, or planning API architecture.\n---\n\n# API Designer\n\nQuick start: See [examples.md](examples.md)\n\nDetailed reference: See [reference.md](reference.md)\n\n## Instructions\n\n1. Gather requirements\n2. Design endpoints (see examples.md)\n3. Document with OpenAPI spec\n4. Review against best practices (see reference.md)\n```\n\n## Best practices for Skill authors\n\n1. **One Skill, one purpose**: Don't create mega-Skills\n2. **Specific descriptions**: Include trigger words users will say\n3. **Clear instructions**: Write for Claude, not humans\n4. **Concrete examples**: Show real code, not pseudocode\n5. **List dependencies**: Mention required packages in description\n6. **Test with teammates**: Verify activation and clarity\n7. **Version your Skills**: Document changes in content\n8. **Use progressive disclosure**: Put advanced details in separate files\n\n## Validation checklist\n\nBefore finalizing a Skill, verify:\n\n- [ ] Name is lowercase, hyphens only, max 64 chars\n- [ ] Description is specific and \u003C 1024 chars\n- [ ] Description includes \"what\" and \"when\"\n- [ ] YAML frontmatter is valid\n- [ ] Instructions are step-by-step\n- [ ] Examples are concrete and realistic\n- [ ] Dependencies are documented\n- [ ] File paths use forward slashes\n- [ ] Skill activates on relevant queries\n- [ ] Claude follows instructions correctly\n\n## Troubleshooting\n\n**Skill doesn't activate**:\n- Make description more specific with trigger words\n- Include file types and operations in description\n- Add \"Use when...\" clause with user phrases\n\n**Multiple Skills conflict**:\n- Make descriptions more distinct\n- Use different trigger words\n- Narrow the scope of each Skill\n\n**Skill has errors**:\n- Check YAML syntax (no tabs, proper indentation)\n- Verify file paths (use forward slashes)\n- Ensure scripts have execute permissions\n- List all dependencies\n\n## Examples\n\nSee the documentation for complete examples:\n- Simple single-file Skill (commit-helper)\n- Skill with tool permissions (code-reviewer)\n- Multi-file Skill (pdf-processing)\n\n## Output format\n\nWhen creating a Skill, I will:\n\n1. Ask clarifying questions about scope and requirements\n2. Suggest a Skill name and location\n3. Create the SKILL.md file with proper frontmatter\n4. Include clear instructions and examples\n5. Add supporting files if needed\n6. Provide testing instructions\n7. Validate against all requirements\n\nThe result will be a complete, working Skill that follows all best practices and validation rules.\n",{"name":5,"description":7},"main","56fc291d843c7fcb046d00e4f557d565516019bb","llms\u002Fclaude\u002Fskills\u002Fskill-writer","https:\u002F\u002Fgithub.com\u002Fvjrasane\u002Fdotfiles","https:\u002F\u002Fgithub.com\u002Fvjrasane","2026-11-05 23:04:06",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add vjrasane\u002Fdotfiles --skill skill-writer",{"tool":46,"command":47},"bunx","bunx skills add vjrasane\u002Fdotfiles --skill skill-writer",{"tool":49,"command":50},"pnpm","pnpm dlx skills add vjrasane\u002Fdotfiles --skill skill-writer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvjrasane\u002Fdotfiles\u002Fblob\u002Fmain\u002Fllms\u002Fclaude\u002Fskills\u002Fskill-writer\u002FSKILL.md",true,[],[55,83,108,114,125,144],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":62,"publishedAt":29},"01M6PMCNSAK1GC3P7C5J49R3RE","start-ticket","Kick off work on a Linear ticket end to end — file or look up the ticket, create an isolated jj workspace for it, move into that workspace, pull the ticket, and brief its scope. Use when the user wants to start working on a subject or an existing ticket, \"start a ticket\", \"kick off LIN-123\", or spin up a workspace from a ticket and begin.","https:\u002F\u002Fgithub.com\u002Fvjrasane\u002Fdotfiles\u002Fblob\u002Fmain\u002Fllms\u002Fclaude\u002Fskills\u002Fstart-ticket\u002FSKILL.md",[61],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82],"start ticket","ticket","start","use","MCP","pull","file","brief","Bash","work on","jj","linear ticket","up","end","scope","move","quick","URL","for","Existing",{"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":6,"sourceHtmlUrl":87,"categories":88,"keywords":100,"publishedAt":29},"01M6BXWMYDB847PE9T0JR5J26K","writing-assistant","Help improve and flesh out written text in markdown or plain text files. Use when the user wants writing feedback, style fixes, grammar corrections, or help expanding bullet points into prose. Does not write text from scratch.","https:\u002F\u002Fgithub.com\u002Fvjrasane\u002Fdotfiles\u002Fblob\u002Fmain\u002Fllms\u002Fclaude\u002Fskills\u002Fwriting-assistant\u002FSKILL.md",[89,92,95],{"categoryNo":90,"categoryName":91,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":93,"categoryName":94,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[101,102,103,104,105,28,69,106,107],"assistant","writing assistant","writing","feedback","text","markdown","improve",{"skillNo":109,"name":110,"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":111,"categories":112,"keywords":113,"publishedAt":29},"01M6BXWKJ4182T739T99VZFMHT","workspace","https:\u002F\u002Fgithub.com\u002Fvjrasane\u002Fdotfiles\u002Fblob\u002Fmain\u002Fllms\u002Fclaude\u002Fskills\u002Fworkspace\u002FSKILL.md",[],[110],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":29},"01M6BXWF4JR4RRHJRSMRVS7BKQ","review","Review code changes for quality, security, and best practices","https:\u002F\u002Fgithub.com\u002Fvjrasane\u002Fdotfiles\u002Fblob\u002Fmain\u002Fllms\u002Fclaude\u002Fskills\u002Freview\u002FSKILL.md",[],[116,27,121,122,123,124],"security","best practices","review code","quality",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":135,"publishedAt":29},"01M6BXWCGMN7YPSZ71AG207YSW","review-mr","Find the GitLab merge request for the current jj branch and run a code review on it. Use when the user wants to review the MR, review the merge request, review \"my MR\", or review the current branch's changes on GitLab.","https:\u002F\u002Fgithub.com\u002Fvjrasane\u002Fdotfiles\u002Fblob\u002Fmain\u002Fllms\u002Fclaude\u002Fskills\u002Freview-mr\u002FSKILL.md",[131,134],{"categoryNo":132,"categoryName":133,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[136,116,137,138,26,139,27,140,71,73,141,142,67,143],"review mr","plugin","gitlab","run","linear","diffs","merge","code review",{"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":151,"publishedAt":29},"01M6BXWA9RFTMJQ7R5XP4ETSC8","researcher","Research a topic by gathering information from web sources and local files. Use when the user asks to research, investigate, or deep-dive into a subject. Supports incremental research via a research.md file.","https:\u002F\u002Fgithub.com\u002Fvjrasane\u002Fdotfiles\u002Fblob\u002Fmain\u002Fllms\u002Fclaude\u002Fskills\u002Fresearcher\u002FSKILL.md",[150],{"categoryNo":93,"categoryName":94,"taxonomyType":21,"taxonomyTypeDesc":22},[146,152,69,153,154],"investigate","web","research"]