{
  "markdown": "# Claude Skills Repository\n\nA curated collection of reusable skills for Claude Code. Pick the skills you need and add them to your project to enhance Claude's capabilities.\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Claude Code Skill](https://img.shields.io/badge/Claude%20Code-Skill-blue)](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/skills)\n## 🎯 What is This?\n\nThis repository provides ready-to-use skills that extend Claude Code's functionality. Each skill is a self-contained module that teaches Claude how to perform specific tasks or follow particular workflows in your projects.\n\n## 📦 Available Skills\n\n| Skill Name                                         | Description                                                                                           | Source | Installation |\n|----------------------------------------------------|-------------------------------------------------------------------------------------------------------|--------|--------------|\n| **[create-skill-file](./create-skill-file)**       | Guides Claude in creating well-structured SKILL.md files with templates, examples, and best practices | - | `cp -r create-skill-file .claude/skills/` |\n| **[prompt-optimize](./prompt-optimize)**           | Optimize your prompt with Claude                                                                      | - | `cp -r prompt-optimize .claude/skills/` |\n| **[deep-reading-analyst](./deep-reading-analyst)** | Comprehensive framework for deep analysis using 10+ thinking models (SCQA, 5W2H, Critical Thinking, Mental Models, First Principles, etc.) | [🔗 GitHub](https://github.com/ginobefun/deep-reading-analyst-skill) | `cp -r deep-reading-analyst .claude/skills/` |\n| **[dry-refactoring](./dry-refactoring)**           | Systematic code refactoring following DRY principle with 4-step workflow to eliminate code duplication | - | `cp -r dry-refactoring .claude/skills/` |\n| **[frontend-design](./frontend-design)**           | Creates unique, production-grade frontend interfaces with exceptional design quality and creative aesthetics | - | `cp -r frontend-design .claude/skills/` |\n| **[mcp-builder](./mcp-builder)**                   | Guide for creating high-quality MCP servers that enable LLMs to interact with external services through tools | - | `cp -r mcp-builder .claude/skills/` |\n| **[daily-ai-news](./daily-ai-news)**               | Aggregates and summarizes the latest AI news from multiple sources with concise briefs and direct links | - | `cp -r daily-ai-news .claude/skills/` |\n| **[fastgpt-workflow-generator](./fastgpt-workflow-generator)** | Generates production-ready FastGPT workflow JSON from natural language requirements with AI-powered template matching and three-layer validation | - | `cp -r fastgpt-workflow-generator .claude/skills/` |\n| **[planning-with-files](./planning-with-files)** | Manus-style workflow using persistent markdown files for planning, progress tracking, and knowledge storage with 3-file pattern | [🔗 GitHub](https://github.com/OthmanAdi/planning-with-files) | `cp -r planning-with-files .claude/skills/` |\n| **[local-diff-review](./local-diff-review)**     | Pre-PR local code review skill based on git diff, applies the same three-dimension standards as pr-review (code quality, style guide, common issues checklist) | - | `cp -r local-diff-review .claude/skills/` |\n| **[software-copyright-writer](./software-copyright-writer)** | Prepares legitimate software copyright registration materials from real repositories, product pages, UI screenshots, source evidence, and module scopes | - | `cp -r software-copyright-writer .claude/skills/` |\n\n**Total:** 11 skills available\n\n---\n\n### Skill Details\n\n#### 🔧 create-skill-file\n**Versions:** [Chinese](./create-skill-file) / [English](./create-skill-file-EN)\n\nA meta-skill that teaches you how to create high-quality SKILL.md files for Claude.\n\n**What's included:**\n- ✅ Comprehensive writing guidelines\n- ✅ Ready-to-use templates (Basic & Workflow)\n- ✅ Real-world examples (Good & Bad practices)\n- ✅ Quality checklist and troubleshooting guide\n\n**Trigger Keywords:** `\"create skill\"`, `\"write skill\"`, `\"SKILL.md\"`, `\"skill guidelines\"`, `\"best practices\"`\n\n**Installation:**\n```bash\n# Chinese version\ncp -r create-skill-file .claude/skills/\n\n# English version\ncp -r create-skill-file-EN .claude/skills/\n```\n\n---\n\n#### 🔧 prompt-optimize\n**Version:** [Chinese](./prompt-optimize)\n\nAn expert prompt engineering skill that transforms Claude into \"Alpha-Prompt\" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue.\n\n**What's included:**\n- ✅ Expert prompt engineering consultation\n- ✅ Advanced cognitive architectures (CoT, ToT, Self-Consistency, ReAct)\n- ✅ Security guardrails and safety considerations\n- ✅ Architecture upgrade suggestions for simple requirements\n- ✅ Collaborative dialogue-based prompt optimization\n\n**Key Features:**\n- **Flexible Communication**: Genuine two-way dialogue, not rigid templated questions\n- **Proactive Architecture Upgrades**: Suggests advanced techniques like Tree of Thought for creative tasks\n- **Security Awareness**: Provides safety recommendations for public-facing AI roles\n- **Quality Standards**: Delivers production-ready prompts with clear role definitions and structured outputs\n\n**Trigger Keywords:** `\"optimize prompt\"`, `\"improve prompt\"`, `\"enhance AI instruction\"`, `\"prompt engineering\"`, `\"system instruction\"`\n\n**Installation:**\n```bash\ncp -r prompt-optimize .claude/skills/\n```\n\n---\n\n#### 🔧 deep-reading-analyst\n\nA professional skill that transforms surface-level reading into deep learning through systematic analysis using 10+ proven thinking frameworks.\n\n**For detailed documentation, see:** [Deep Reading Analyst Introduction](./skill-intro/depp-reading-analyst-intro.md)\n\n**🔗 GitHub Repository:** https://github.com/ginobefun/deep-reading-analyst-skill/tree/main\n\n**Installation:**\n```bash\ncp -r deep-reading-analyst .claude/skills/\n```\n\n---\n\n#### 🔧 dry-refactoring\n**Version:** [Chinese](./dry-refactoring)\n\nA systematic skill that guides code refactoring following the DRY (Don't Repeat Yourself) principle through a proven 4-step workflow.\n\n**What's included:**\n- ✅ Step 1: Identify Repetition (obvious and semantic duplication)\n- ✅ Step 2: Abstract the Logic (functions, classes, constants)\n- ✅ Step 3: Replace Implementation (systematic replacement)\n- ✅ Step 4: Verify and Test (unit tests, integration tests, performance)\n\n**Key Features:**\n- **Comprehensive Coverage**: Handles copy-paste code, magic numbers, structural and logical repetition\n- **Step-by-Step Process**: Clear workflow from identification to verification\n- **Real-World Examples**: Complete e-commerce discount calculation refactoring case\n- **Best Practices**: Includes common pitfalls, testing strategies, and gradual refactoring approach\n\n**Trigger Keywords:** `\"DRY\"`, `\"code duplication\"`, `\"refactor repetitive code\"`, `\"eliminate duplication\"`, `\"magic numbers\"`, `\"code smell\"`, `\"extract function\"`\n\n**Installation:**\n```bash\ncp -r dry-refactoring .claude/skills/\n```\n\n---\n\n#### 🔧 frontend-design\n**Version:** [Chinese](./frontend-design)\n\nAn expert skill for creating unique, production-grade frontend interfaces with exceptional design quality that avoids generic AI aesthetics.\n\n**What's included:**\n- ✅ Design thinking framework (Purpose, Style, Constraints, Differentiation)\n- ✅ Typography guide (unique font selection, avoid common fonts)\n- ✅ Color & theme systems (CSS variables, accessibility)\n- ✅ Animation best practices (CSS animations, Framer Motion)\n- ✅ Spatial composition techniques (asymmetric layouts, overlapping elements)\n- ✅ Background & visual details (gradients, noise textures, glass morphism)\n\n**Key Features:**\n- **Bold Aesthetic Choices**: Guides selection of extreme, intentional design styles\n- **Anti-Generic AI Design**: Explicitly avoids overused fonts (Inter, Roboto) and cliché color schemes\n- **Implementation Complexity Matching**: Complex designs get complex code, minimal designs get precise code\n- **Production-Ready Code**: Semantic HTML, accessibility, responsive design, performance optimization\n\n**Trigger Keywords:** `\"web component\"`, `\"landing page\"`, `\"dashboard\"`, `\"React component\"`, `\"UI design\"`, `\"beautify\"`, `\"frontend\"`\n\n**Installation:**\n```bash\ncp -r frontend-design .claude/skills/\n```\n\n---\n\n#### 🔧 mcp-builder\n**Version:** [English](./mcp-builder)\n\nA comprehensive guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.\n\n**What's included:**\n- ✅ Phase 1: Deep Research and Planning (MCP design patterns, API coverage)\n- ✅ Phase 2: Tool Design (naming conventions, parameter schemas, error handling)\n- ✅ Phase 3: Implementation (FastMCP/Python, MCP SDK/TypeScript)\n- ✅ Phase 4: Testing and Publishing (integration tests, documentation)\n\n**Key Features:**\n- **Modern MCP Design Patterns**: Balances comprehensive API coverage with specialized workflow tools\n- **Framework-Specific Guidance**: Detailed examples for both FastMCP (Python) and MCP SDK (TypeScript)\n- **Quality Standards**: Emphasizes clear naming, actionable error messages, and proper context management\n- **Complete Workflow**: From initial research through testing and publishing\n\n**Supported Frameworks:**\n- FastMCP (Python) - Recommended for rapid development\n- MCP SDK (TypeScript/Node.js) - For JavaScript ecosystem integration\n\n**Trigger Keywords:** `\"MCP server\"`, `\"Model Context Protocol\"`, `\"build MCP\"`, `\"FastMCP\"`, `\"MCP SDK\"`, `\"tool integration\"`\n\n**Installation:**\n```bash\ncp -r mcp-builder .claude/skills/\n```\n\n---\n\n#### 🔧 daily-ai-news\n**Version:** [Chinese & English](./daily-ai-news)\n\nAn intelligent skill that aggregates and summarizes the latest AI news from multiple sources (AI news websites and web search) with concise briefs and direct links to original articles.\n\n**What's included:**\n- ✅ Phase 1: Information Gathering (WebSearch + mcp__web_reader__webReader)\n- ✅ Phase 2: Content Filtering (last 24-48 hours, deduplication)\n- ✅ Phase 3: Categorization (Major Announcements, Research, Industry, Tools, Policy)\n- ✅ Phase 4: Output Formatting (structured template with links)\n- ✅ Comprehensive news sources database (20+ sources)\n- ✅ Search query templates by category\n- ✅ Multiple output format templates\n\n**Key Features:**\n- **Multi-Source Aggregation**: Fetches from 3-5 major AI news sites plus web search\n- **Smart Filtering**: Keeps only recent news (24-48 hours) with major significance\n- **Structured Categorization**: 5 categories - Major Announcements, Research & Papers, Industry & Business, Tools & Applications, Policy & Ethics\n- **Direct Links**: Every news item includes a direct link to the original article\n- **Customization Options**: Focus areas, depth levels, time ranges, and format preferences\n- **Bilingual Support**: Works with both Chinese and English news sources\n\n**Trigger Keywords:** `\"给我今天的AI资讯\"`, `\"today's AI news\"`, `\"AI updates\"`, `\"latest AI developments\"`, `\"daily AI briefing\"`, `\"AI industry news\"`, `\"artificial intelligence news\"`\n\n**Installation:**\n```bash\ncp -r daily-ai-news .claude/skills/\n```\n\n---\n\n#### 🔧 fastgpt-workflow-generator\n**Version:** [English](./fastgpt-workflow-generator)\n\nAn intelligent skill that automatically generates production-ready FastGPT workflow JSON from natural language requirements using AI-powered semantic template matching and comprehensive three-layer validation.\n\n**What's included:**\n- ✅ Phase 1: Requirements Analysis (AI semantic extraction)\n- ✅ Phase 2: Template Matching (two-stage: coarse + fine filtering)\n- ✅ Phase 3: JSON Generation (NodeId generation, auto-layout, reference handling)\n- ✅ Phase 4: Validation (format, connections, logic completeness)\n- ✅ Phase 5: Incremental Modification (add/remove/modify nodes)\n- ✅ Built-in templates (document translation, sales training, resume screening, financial news)\n- ✅ Complete references (40+ node types, validation rules, JSON structure specs)\n- ✅ Validation script (Node.js)\n\n**Key Features:**\n- **AI-Powered Template Matching**: Two-stage semantic matching (metadata + AI analysis) to find the most similar template\n- **Automatic JSON Generation**: Generates complete workflow with semantic NodeIds, auto-layout positions, and proper references\n- **Three-Layer Validation**: Format (JSON structure) → Connections (node references) → Logic (workflow completeness)\n- **Incremental Modification Support**: Add, delete, or modify nodes in existing workflows\n- **Built-in Templates**: 4 production-ready templates covering different domains and complexities\n- **Portable Design**: Self-contained with relative paths, works in any project\n\n**Built-in Templates:**\n- `文档翻译助手.json` - Simple workflow (document processing)\n- `销售陪练大师.json` - Medium complexity (conversational AI)\n- `简历筛选助手_飞书.json` - Complex workflow (data + external integration)\n- `AI金融日报.json` - Scheduled trigger + multi-agent (news aggregation)\n\n**Reference Format:**\n- Array reference: `[\"nodeId\", \"key\"]` - for direct values\n- Template reference: `{{$nodeId.key$}}` - for string interpolation (double braces!)\n\n**Trigger Keywords:** `\"create FastGPT workflow\"`, `\"generate workflow JSON\"`, `\"design FastGPT application\"`, `\"工作流\"`, `\"workflow automation\"`, `\"multi-agent systems\"`, `\"FastGPT templates\"`\n\n**Installation:**\n```bash\ncp -r fastgpt-workflow-generator .claude/skills/\n```\n\n**Quick Start:**\n```\n# Example 1: Create from natural language\n\"生成一个旅游规划的工作流，收集用户的目的地、天数、预算等信息，然后AI生成详细的旅游规划\"\n\n# Example 2: Modify existing workflow\n\"在现有问答工作流前添加知识库搜索节点\"\n\n# Example 3: Validate workflow\n\"验证这个workflow JSON是否正确\"\n```\n\n---\n\n#### 🔧 planning-with-files\n**Version:** [English](./planning-with-files)\n\nA Manus-style workflow skill that transforms how you work with Claude by using persistent markdown files as \"working memory on disk\" for planning, progress tracking, and knowledge storage.\n\n**🔗 Reference:** Based on [OthmanAdi/planning-with-files](https://github.com/OthmanAdi/planning-with-files)\n\n**What's included:**\n- ✅ 3-File Pattern System (task_plan.md, notes.md, deliverable.md)\n- ✅ Task plan template with phases, decisions, and errors tracking\n- ✅ Notes template for research and findings\n- ✅ Progress tracking with checkboxes and status updates\n- ✅ Knowledge persistence outside attention window\n- ✅ Complete workflow loop patterns\n- ✅ Real-world examples and anti-patterns\n\n**Key Features:**\n- **Persistent Memory**: Store plans, research, and decisions in files instead of context window\n- **3-File Pattern**: Systematic approach with task_plan.md (progress), notes.md (research), and deliverable.md (output)\n- **Structured Tracking**: Phase-based planning with checkboxes, decisions log, and error tracking\n- **Loop-Based Workflow**: Read → Work → Update cycle keeps goals fresh in attention\n- **Context Management**: Prevents context stuffing by storing information in files\n- **Multi-Session Support**: Persist work across conversation sessions\n\n**The 3-File Pattern:**\n- **task_plan.md** - Track phases and progress (update after each phase)\n- **notes.md** - Store findings and research (during research)\n- **[deliverable].md** - Final output (at completion)\n\n**Core Workflow Loop:**\n```\n1. Create task_plan.md with goal and phases\n2. Research → save to notes.md → update task_plan.md\n3. Read notes.md → create deliverable → update task_plan.md\n4. Deliver final output\n```\n\n**When to Use:**\n- Starting complex multi-step projects\n- Research tasks requiring information gathering\n- Tasks requiring progress tracking across sessions\n- User mentions \"planning\", \"organizing work\", \"tracking progress\"\n- Need structured output with clear phases\n\n**Trigger Keywords:** `\"complex task\"`, `\"multi-step project\"`, `\"planning\"`, `\"organize work\"`, `\"track progress\"`, `\"research task\"`, `\"structured output\"`\n\n**Installation:**\n```bash\ncp -r planning-with-files .claude/skills/\n```\n\n**Quick Start:**\n```\n# Example: Plan a feature implementation\n\"I need to implement a new authentication system\"\n\n→ Claude creates:\n  - task_plan.md (phases: design, implementation, testing, deployment)\n  - notes.md (stores API research and design decisions)\n  - Updates plan after each phase completion\n```\n\n---\n\n#### 🔧 local-diff-review\n**Version:** [Chinese](./local-diff-review)\n\nA pre-PR self-review skill that runs git diff locally and applies the same three-dimension review standards as a formal PR review — no custom weakening of criteria allowed.\n\n**What's included:**\n- ✅ Code quality standards (`code-quality-standards.md`)\n- ✅ Common issues checklist (`common-issues-checklist.md`)\n- ✅ 5 diff scope modes (unstaged, staged, HEAD, branch-vs-baseline, specific commit)\n- ✅ Three-level issue grading (🔴 Critical / 🟡 Suggested / 🟢 Optional)\n- ✅ Structured output: change overview → issue list → overall conclusion\n\n**Key Features:**\n- **Review First, Fix Later**: Outputs an issue list by default; only modifies code when explicitly asked\n- **Actionable Results**: Every issue includes file path, line number, risk explanation, and a concrete fix suggestion\n- **Regression Risk Summary**: Highlights i18n, type safety, edge cases, compatibility, and performance impact\n- **Consistent Standards**: Strictly reuses the same criteria as `pr-review`; no softened rules\n\n**Trigger Keywords:** `\"review 我本地改动\"`, `\"local diff review\"`, `\"review 我当前改动\"`, `\"git diff review\"`, `\"暂存区 review\"`, `\"分支差异审查\"`, `\"提 PR 前 review\"`\n\n**Installation:**\n```bash\ncp -r local-diff-review .claude/skills/\n```\n\n**Quick Start:**\n```\n# Example 1: Review all unstaged changes\n\"请按 PR 标准 review 我本地当前改动。\"\n\n# Example 2: Review only staged changes\n\"请 review 我的 git diff --staged，只给问题清单。\"\n\n# Example 3: Review branch diff against baseline\n\"请按 FastGPT 规范审查我当前分支相对 upstream/v4.14.7-dev 的改动。\"\n```\n\n---\n\n#### 🔧 software-copyright-writer\n**Version:** [Chinese](./software-copyright-writer)\n\nA material-preparation skill for legitimate software copyright registration. It analyzes real repositories, product pages, running UI evidence, module scopes, and source ranges to propose reasonable registration topics, generate long-form Chinese application content, assemble source-code excerpts, capture web evidence, and export `.docx` deliverables.\n\n**Compliance Boundary:**\n- Only use it for real software projects with authentic source code and actual running interfaces\n- Do not use it to fabricate software, screenshots, ownership, domain filings, trademarks, or features\n- If evidence is missing or the requested topic count is unrealistic, the skill must report gaps and risks instead of inventing material\n\n**What's included:**\n- ✅ Topic splitting rules for coarse/fine software copyright applications\n- ✅ Intake checklist for owner name, Logo, copyright notice, ICP/domain evidence, screenshots, and source-code constraints\n- ✅ Standard and extended Chinese content templates targeting 30-page style application materials\n- ✅ Source-code assembly script using the front/back 1500-line rule\n- ✅ Playwright-based web evidence screenshot script with login-state support\n- ✅ Markdown-to-DOCX export script for content and source documents\n\n**Requirements for helper scripts:**\n- Python 3 with `python-docx` for `.docx` export (`python3 -m pip install -r scripts/requirements.txt`)\n- Node.js, Playwright, and Chrome/Chromium for screenshot evidence capture (`npm install --prefix scripts`)\n- Optional environment variables: `SOFTWARE_COPYRIGHT_WRITER_PYTHON`, `SOFTWARE_COPYRIGHT_WRITER_NODE`, `SOFTWARE_COPYRIGHT_WRITER_NODE_MODULES`, `SOFTWARE_COPYRIGHT_WRITER_CHROME_PATH`\n\n**Trigger Keywords:** `\"软著\"`, `\"软件著作权\"`, `\"生成软著材料\"`, `\"软著正文\"`, `\"源码原文\"`, `\"软件著作权登记\"`, `\"copyright registration material\"`\n\n**Installation:**\n```bash\ncp -r software-copyright-writer .claude/skills/\n```\n\n**Quick Start:**\n```\n# Example 1: Evaluate whether a repository can support multiple registration topics\n\"请根据这个仓库和官网，判断能拆几份软著，并给出主题边界和截图清单。\"\n\n# Example 2: Generate full materials after evidence is ready\n\"按已确认的主题生成软著正文、源码原文，并导出 docx。\"\n```\n\n---\n\n## 🚀 How to Use\n\n### Installation Steps\n\n1. **Navigate to your project**\n   ```bash\n   cd /path/to/your/project\n   ```\n\n2. **Create the skills directory** (if not exists)\n   ```bash\n   mkdir -p .claude/skills\n   ```\n\n3. **Copy the skill you want**\n   \n   Example - Adding the skill creation guide:\n   ```bash\n   # clone this repository if you haven't already\n   git clone https://github.com/YYH211/Claude-meta-skill.git\n   \n   # For Chinese version\n   cp -r /Claude-meta-skill/create-skill-file .claude/skills/\n\n   # OR for English version\n   cp -r /Claude-meta-skill/create-skill-file-EN .claude/skills/\n   ```\n\n4. **Verify installation**\n   ```bash\n   ls .claude/skills/\n   ```\n\n   You should see your copied skill directory:\n   ```\n   .claude/skills/\n   ├── create-skill-file/    (or create-skill-file-EN/)\n   │   ├── SKILL.md\n   │   ├── templates/\n   │   └── examples/\n   ```\n\n### Verifying Configuration\n\n#### ✅ Method 1: Check File Structure\n\n```bash\ncat .claude/skills/create-skill-file/SKILL.md | head -10\n```\n\nExpected output should show the YAML frontmatter:\n```yaml\n---\nname: create-skill-file\ndescription: Guides Claude in creating well-structured SKILL.md files...\n---\n```\n\n#### ✅ Method 2: Test with Claude\n\nStart Claude Code and try triggering the skill:\n\n```bash\nclaude\n```\n\nThen ask:\n- \"Help me create a new skill\"\n- \"I want to write a SKILL.md file\"\n- \"Guide me on skill best practices\"\n\nIf Claude provides structured guidance referencing templates and examples, the skill is working! 🎉\n\n#### ✅ Method 3: List All Skills\n\nYou can check what skills are available by asking Claude:\n```\nWhat skills do you have access to?\n```\nclaude response：\n```\n  1. create-skill-file (Skill 文件创建指南)\n\n  功能: 指导创建结构良好的 SKILL.md 文件\n\n  触发场景:\n  - 当你询问如何创建 Skill\n  - 需要编写 SKILL.md 文档\n  - 想了解 Skill 编写最佳实践\n\n  核心能力:\n  - 提供清晰的命名、结构和内容组织指南\n  - 包含模板和示例\n  - 质量检查清单\n  - 常见问题解答\n\n  位置: .claude/skill/create-skill-file/SKILL.md\n\n```\n\nOr manually check:\n```bash\nfind .claude/skills -name \"SKILL.md\" -exec grep -A 2 \"^name:\" {} \\;\n```\n---\n\n## 💡 Usage Examples\n\n### Example 1: Creating a New Skill\n\n```\nYou: \"I need to create a skill for managing Docker deployments\"\n\nClaude: [Uses create-skill-file skill]\n\"I'll help you create a Docker deployment skill. Let's start by following\nthe skill creation guidelines...\"\n```\n\n### Example 2: Improving Existing Skills\n\n```\nYou: \"Can you review my database-migration skill and suggest improvements?\"\n\nClaude: [References best practices from create-skill-file]\n\"Let me review your skill against the best practices checklist...\"\n```\n\n---\n\n## 🛠️ Troubleshooting\n\n### Skill Not Working\n\n| Problem | Solution |\n|---------|----------|\n| Claude doesn't use the skill | Verify the skill is in `.claude/skills/` directory |\n| Skill file not found | Check that SKILL.md exists and has valid frontmatter |\n| Wrong skill activates | Make description more specific with unique keywords |\n| Skill seems ignored | Try using explicit trigger keywords from the description |\n\n### Common Issues\n\n**Q: Do I need to restart Claude after adding a skill?**\nA: Typically yes. Restart your Claude Code session after adding new skills.\n\n**Q: Can I modify the skills?**\nA: Absolutely! Feel free to customize them for your project needs.\n\n**Q: How many skills can I have?**\nA: No hard limit, but keep it manageable (5-10 skills per project is typical).\n\n**Q: Can I use multiple skills together?**\nA: Yes! Claude can use multiple skills in the same conversation as needed.\n\n---\n\n## 🚧 Coming Soon\n\nThis repository will grow with more useful skills:\n\n- [ ] **code-review-workflow** - Systematic code review process\n- [ ] **api-documentation-generator** - Generate API docs from code\n- [ ] **testing-strategy** - Guide for writing comprehensive tests\n- [ ] **deployment-checklist** - Pre-deployment verification\n- [ ] **refactoring-guide** - Code refactoring best practices\n\n**Want to contribute?** Create a skill following the guidelines in `create-skill-file` and submit it!\n\n---\n\n## 📚 Resources\n\n- [Claude Code Documentation](https://docs.claude.com/en/docs/claude-code)\n- [Agent Skills Official Guide](https://docs.claude.com/en/docs/agents-and-tools/agent-skills)\n- [Best Practices](https://docs.claude.com/en/docs/agents-and-tools/agent-skills/best-practices)\n\n---\n\n## ⭐ Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=YYH211/Claude-meta-skill&type=Date)](https://star-history.com/#YYH211/Claude-meta-skill&Date)\n\n---\n\n## 🤝 Partner Projects\n\n### FastGPT\n\n[FastGPT](https://github.com/labring/FastGPT) is a knowledge-based platform built on the LLM, offers out-of-the-box data processing and model invocation capabilities, allows for workflow orchestration through Flow visualization.\n\n---\n\n## 🤝 Contributing\n\nHave a useful skill to share? We'd love to include it!\n\n1. Create your skill following the `create-skill-file` guidelines\n2. Test it thoroughly in real projects\n3. Include clear documentation and examples\n4. Submit via pull request or issue\n\n---\n\n## 📄 License\n\nFree to use for any purpose. Customize and adapt as needed for your projects.\n\n---\n\n**Happy coding with Claude!** 🚀\n",
  "bytes": 25282,
  "sha": "f85487024834e48c42629e5a924eb3e169ac78abebc17963666ba037cb23307d",
  "repo_slug": "yyh211/claude-meta-skill",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_yyh211_claude_meta_skill_daily_ai_news_cc8815d4/readme"
}