[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-74007":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":10,"languages":10,"totalLinesOfCode":10,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":10,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":23,"hasPages":21,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":36,"readmeContent":37,"aiSummary":38,"trendingCount":15,"starSnapshotCount":15,"syncStatus":39,"lastSyncTime":40,"discoverSource":41},74007,"awesome-claude-skills","travisvn\u002Fawesome-claude-skills","travisvn","A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows — particularly Claude Code","",null,13357,1502,105,42,0,126,302,954,378,44.53,false,"main",true,[25,26,27,28,29,30,31,32,33,34,35],"agentic-coding","anthropic","awesome","awesome-list","awesome-lists","claude","claude-ai","claude-code","claude-desktop","claude-skills","claudeskills","2026-06-12 02:03:21","\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftravisvn\u002Fawesome-claude-skills\">\n    \u003Cimg alt=\"Awesome Claude Skills\" src=\"https:\u002F\u002Fpc0o4oduww.ufs.sh\u002Ff\u002Fcrfz5GypRfo0lI4924gMSJKLY6297aVP0zZpilXBvqTbDyrs\"\u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n# Awesome Claude Skills\n\n[![Awesome](https:\u002F\u002Fawesome.re\u002Fbadge.svg)](https:\u002F\u002Fawesome.re)\n[![Last Updated](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fupdated-Feb%202026-green.svg)]()\n[![PRs Welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg)](CONTRIBUTING.md)\n\n> A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows\n\n**Claude Skills** teach Claude how to **perform tasks in a repeatable way**\n\nThey are specialized folders containing instructions, scripts, and resources that Claude dynamically discovers and loads when relevant to tasks.\n\n### How Skills Work\n\nSkills employ a **progressive disclosure architecture** for efficiency:\n\n1. **Metadata loading** (~100 tokens): Claude scans available Skills to identify relevant matches\n2. **Full instructions** (\u003C5k tokens): Load when Claude determines the Skill applies\n3. **Bundled resources**: Files and executable code load only as needed\n\nThis design allows multiple Skills to remain available without overwhelming Claude's context window.\n\n## 🚀 Getting Started\n\n### Claude.ai Web Interface\n\n1. Go to [Settings > Capabilities](https:\u002F\u002Fclaude.ai\u002Fsettings\u002Fcapabilities)\n2. Enable Skills toggle\n3. Browse available skills or upload custom skills\n4. **For Team\u002FEnterprise**: Admin must enable Skills organization-wide first\n\n### Claude Code CLI\n\n```bash\n# Install skills from marketplace\n\u002Fplugin marketplace add anthropics\u002Fskills\n\n# Or install from local directory\n\u002Fplugin add \u002Fpath\u002Fto\u002Fskill-directory\n```\n\n### Claude API\n\nSkills are accessible via the `\u002Fv1\u002Fskills` API endpoint. See the [Skills API documentation](https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fapi\u002Fbeta\u002Fskills) for detailed integration examples.\n\n```python\nimport anthropic\n\nclient = anthropic.Client(api_key=\"your-api-key\")\n# See API docs for full implementation details\n```\n\n## 🎯 Official Skills\n\n### Document Skills\n\nSkills for working with complex file formats:\n\n- **[docx](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fdocx)** - Create, edit, and analyze Word documents with support for tracked changes, comments, formatting preservation, and text extraction\n- **[pdf](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fpdf)** - Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging\u002Fsplitting documents, and handling forms\n- **[pptx](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fpptx)** - Create, edit, and analyze PowerPoint presentations with support for layouts, templates, charts, and automated slide generation\n- **[xlsx](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fxlsx)** - Create, edit, and analyze Excel spreadsheets with support for formulas, formatting, data analysis, and visualization\n\n### Design & Creative\n\n- **[algorithmic-art](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Falgorithmic-art)** - Create generative art using p5.js with seeded randomness, flow fields, and particle systems\n- **[canvas-design](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fcanvas-design)** - Design beautiful visual art in .png and .pdf formats using design philosophies\n- **[slack-gif-creator](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fslack-gif-creator)** - Create animated GIFs optimized for Slack's size constraints\n\n### Development\n\n- **[frontend-design](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffrontend-design)** - Instructs Claude to avoid \"AI slop\" or generic aesthetics and to make bold design decisions. Works very well for React & Tailwind.\n- **[web-artifacts-builder](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fweb-artifacts-builder)** - Build complex claude.ai HTML artifacts using React, Tailwind CSS, and shadcn\u002Fui components\n- **[mcp-builder](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fmcp-builder)** - Guide for creating high-quality MCP servers to integrate external APIs and services\n- **[webapp-testing](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fwebapp-testing)** - Test local web applications using Playwright for UI verification and debugging\n\n### Communication\n\n- **[brand-guidelines](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fbrand-guidelines)** - Apply Anthropic's official brand colors and typography to artifacts\n- **[internal-comms](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Finternal-comms)** - Write internal communications like status reports, newsletters, and FAQs\n\n### Skill Creation\n\n- **[skill-creator](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fskill-creator)** - Interactive skill creation tool that guides you through building new skills with Q&A\n\n## 🌟 Community Skills\n\n> [!Warning]\n> Skills can execute arbitrary code in Claude's environment.\n> \n> See [Security & Best Practices](#-security--best-practices) for more information\n\n### Collections & Libraries\n\n- **[obra\u002Fsuperpowers](https:\u002F\u002Fgithub.com\u002Fobra\u002Fsuperpowers)** - Core skills library for Claude Code with 20+ battle-tested skills including TDD, debugging, and collaboration patterns\n  - Features `\u002Fbrainstorm`, `\u002Fwrite-plan`, `\u002Fexecute-plan` commands and skills-search tool\n  - [superpowers-skills](https:\u002F\u002Fgithub.com\u002Fobra\u002Fsuperpowers-skills) - Community-editable skills repository\n  - [Blog: Superpowers](https:\u002F\u002Fblog.fsck.com\u002F2025\u002F10\u002F09\u002Fsuperpowers\u002F) - Author's overview by Jesse Vincent\n  - Installation: `\u002Fplugin marketplace add obra\u002Fsuperpowers-marketplace`\n \n- **[obra\u002Fsuperpowers-lab](https:\u002F\u002Fgithub.com\u002Fobra\u002Fsuperpowers-lab)** - Experimental skills for `Claude Code Superpowers` (see above)\n  - Uses new techniques that are still being refined and tested (i.e. skills here may change over time)\n  - [Blog post about its development](https:\u002F\u002Fblog.fsck.com\u002F2025\u002F10\u002F23\u002Fnaming-claude-plugins\u002F)\n  - Install from `superpowers-marketplace` plugin\n\n\n### Individual Skills\n\n> These will be broken down into categories once there are enough community skills available to list\n\n| Skill | Description |\n| --- | --- |\n| **[ios-simulator-skill](https:\u002F\u002Fgithub.com\u002Fconorluddy\u002Fios-simulator-skill)** | iOS app building, navigation, and testing through automation |\n| **[ffuf-web-fuzzing](https:\u002F\u002Fgithub.com\u002Fjthack\u002Fffuf_claude_skill)** | Expert guidance for ffuf web fuzzing during penetration testing, including authenticated fuzzing with raw requests, auto-calibration, and result analysis |\n| **[playwright-skill](https:\u002F\u002Fgithub.com\u002Flackeyjb\u002Fplaywright-skill)** | General-purpose browser automation using Playwright |\n| **[claude-d3js-skill](https:\u002F\u002Fgithub.com\u002Fchrisvoncsefalvay\u002Fclaude-d3js-skill)** | Visualizations in d3.js |\n| **[claude-scientific-skills](https:\u002F\u002Fgithub.com\u002FK-Dense-AI\u002Fclaude-scientific-skills)** | Comprehensive collection of ready-to-use scientific skills, including working with specialized scientific libraries and databases |\n| **[web-asset-generator](https:\u002F\u002Fgithub.com\u002Falonw0\u002Fweb-asset-generator)** | Generates web assets like favicons, app icons, and social media images |\n| **[loki-mode](https:\u002F\u002Fgithub.com\u002Fasklokesh\u002Fclaudeskill-loki-mode)** | Multi-agent autonomous startup system - orchestrates 37 AI agents across 6 swarms to build, deploy, and operate a complete startup from PRD to revenue |\n| **[Trail of Bits Security Skills](https:\u002F\u002Fgithub.com\u002Ftrailofbits\u002Fskills)** | Security skills for static analysis with CodeQL\u002FSemgrep, variant analysis, code auditing, and vulnerability detection |\n| **[frontend-slides](https:\u002F\u002Fgithub.com\u002Fzarazhangrui\u002Ffrontend-slides)** | Create animation-rich HTML presentations — from scratch or by converting PowerPoint files |\n| **[Expo Skills](https:\u002F\u002Fgithub.com\u002Fexpo\u002Fskills)** | Official skills by the Expo team for developing Expo apps |\n| **[shadcn\u002Fui](https:\u002F\u002Fui.shadcn.com\u002Fdocs\u002Fskills)** | Give Claude Code context on shadcn components as well as pattern enforcement |\n| **[get-shit-done](https:\u002F\u002Fgithub.com\u002Fgsd-build\u002Fget-shit-done)** | Lightweight meta-prompting, context engineering, and spec-driven development system for Claude Code by TÂCHES |\n\n_More community skills coming soon! Submit a PR to add your skill._\n\n### Tools\n\n- **[yusufkaraaslan\u002FSkill_Seekers](https:\u002F\u002Fgithub.com\u002Fyusufkaraaslan\u002FSkill_Seekers)** - Convert documentation websites into Claude Skills\n\n## ✏️ Creating Your First Skill\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Step-by-Step Guide\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n### Method 1: Use skill-creator (Recommended)\n\nThe easiest way to create a skill is to use the built-in `skill-creator`:\n\n1. Enable the skill-creator skill in Claude\n2. Ask Claude: \"Use the skill-creator to help me build a skill for [your task]\"\n3. Answer the interactive questions about your workflow\n4. Claude generates the complete skill structure for you\n\n### Method 2: Manual Creation\n\n1. **Create folder structure**:\n\n   ```\n   my-skill\u002F\n   ├── SKILL.md          # Main skill file with frontmatter\n   ├── scripts\u002F          # Optional executable scripts\n   │   └── helper.py\n   └── resources\u002F        # Optional supporting files\n       └── template.json\n   ```\n\n2. **Create SKILL.md with frontmatter**:\n\n   ```yaml\n   ---\n   name: my-skill\n   description: Brief description for skill discovery (keep concise)\n   ---\n\n   # Detailed Instructions\n\n   Claude will read these instructions when the skill is activated.\n\n   ## Usage\n   Explain how to use this skill...\n\n   ## Examples\n   Provide clear examples...\n   ```\n\n3. **Add executable scripts** (optional):\n\n   - Python, JavaScript, or other scripts Claude can execute\n   - Reference them in your SKILL.md instructions\n\n4. **Test locally**:\n\n   - Install the skill in Claude Code or Claude Desktop\n   - Test with relevant tasks\n   - Iterate and refine\n\n5. **Share**:\n   - Publish to GitHub\n   - Submit to this awesome list via PR\n   - Share with your team via git repos or internal distribution\n\n### Best Practices\n\n- **Keep descriptions concise** - The frontmatter description is used for skill discovery\n- **Use clear, actionable instructions** - Write instructions as if for a human collaborator\n- **Include examples** - Show specific examples in your SKILL.md\n- **Version your skills** - Use git tags for version management\n- **Document dependencies** - List any prerequisites or required packages\n- **Test thoroughly** - Verify your skill works across different scenarios\n\n\u003C\u002Fdetails>\n\n## 📚 Official Documentation & Resources\n\n### Getting Started\n\n- [What are Skills?](https:\u002F\u002Fsupport.claude.com\u002Fen\u002Farticles\u002F12512176-what-are-skills) - Official support article explaining Claude Skills\n- [Using Skills in Claude](https:\u002F\u002Fsupport.claude.com\u002Fen\u002Farticles\u002F12512180-using-skills-in-claude) - How to enable and use skills\n\n### Documentation\n\n- [Claude Skills Announcement](https:\u002F\u002Fwww.anthropic.com\u002Fnews\u002Fskills) - Official announcement from Anthropic\n- [Equipping Agents with Skills](https:\u002F\u002Fwww.anthropic.com\u002Fengineering\u002Fequipping-agents-for-the-real-world-with-agent-skills) - Engineering deep dive on Agent Skills\n- [Claude Developer Platform](https:\u002F\u002Fdocs.claude.com\u002F) - Official documentation\n- [Skills API Endpoint](https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fapi\u002Fbeta\u002Fskills) - `\u002Fv1\u002Fskills` API documentation\n\n### Repositories & Examples\n\n- [anthropics\u002Fskills](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills) - Official public repository for Skills\n- [Claude Cookbooks - Skills](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-cookbooks\u002Ftree\u002Fmain\u002Fskills) - Example notebooks and tutorials\n\n## 📅 Recent Updates\n\n### November 2025\n\n- **Nov 13**: Anthropic publishes [Skills Explained](https:\u002F\u002Fclaude.com\u002Fblog\u002Fskills-explained) - Comprehensive guide covering progressive disclosure architecture, decision matrices for Skills vs Prompts\u002FSubagents\u002FProjects, and best practices\n\n### October 2025\n\n- **Oct 18**: Major community repositories emerge: [obra\u002Fsuperpowers](https:\u002F\u002Fgithub.com\u002Fobra\u002Fsuperpowers) skills library\n- **Oct 17**: Community publishes practical tutorials on DEV.to and Medium\n- **Oct 16**: 🎉 **Claude Skills officially announced** - Available across Claude.ai, Code, and API\n- **Oct 16**: Initial skills released including docx, pdf, pptx, xlsx, algorithmic-art, canvas-design, and more\n\n## 💡 Skills vs Other Approaches\n\n### Quick Reference: When to Use What\n\n| Tool | Best For |\n|------|----------|\n| **Skills** | Reusable procedural knowledge across conversations |\n| **Prompts** | One-time instructions and immediate context |\n| **Projects** | Persistent background knowledge within workspaces |\n| **Subagents** | Independent task execution with specific permissions |\n| **MCP** | Connecting Claude to external data sources |\n\n**Use Skills when**: Capabilities should be accessible to any Claude instance. They're portable expertise.\n\n**Use Subagents when**: You need self-contained agents designed for specific purposes with independent workflows and restricted tool access.\n\n**Combined approach**: Subagents can leverage Skills for specialized expertise, merging independence with portable knowledge.\n\n**Key insight**: *If you find yourself typing the same prompt repeatedly across multiple conversations, it's time to create a Skill.*\n\n### Skills vs MCP (Model Context Protocol)\n\n| Feature              | Skills                                        | MCP                               |\n| -------------------- | --------------------------------------------- | --------------------------------- |\n| **Purpose**          | Task-specific expertise and workflows         | External data\u002FAPI integration     |\n| **Portability**      | Same format everywhere (Claude.ai, Code, API) | Requires server configuration     |\n| **Code Execution**   | Can include executable scripts                | Provides tools\u002Fresources          |\n| **Token Efficiency** | 30-50 tokens until loaded                     | Varies by implementation          |\n| **Best For**         | Repeatable tasks, document workflows          | Database access, API integrations |\n\n**Use Together**: Skills can create MCP servers! The `mcp-builder` skill helps build high-quality MCP integrations.\n\n#### Skills vs System Prompts\n\n| Feature           | Skills                                              | System Prompts                    |\n| ----------------- | --------------------------------------------------- | --------------------------------- |\n| **Structure**     | Folder with YAML frontmatter, instructions, scripts | Plain text instructions           |\n| **Reusability**   | Version-controlled, shareable, composable           | Copy-paste, conversation-specific |\n| **Loading**       | On-demand (only when relevant)                      | Always in context                 |\n| **Maintenance**   | Centralized updates                                 | Manual updates per conversation   |\n| **Composability** | Multiple skills stack automatically                 | Manual combination                |\n\n## 📖 Tutorials & Guides\n\n### Written Tutorials\n\n- [How to Create Your First Claude Skill](https:\u002F\u002Fskywork.ai\u002Fblog\u002Fai-agent\u002Fhow-to-create-claude-skill-step-by-step-guide\u002F) - Step-by-step tutorial with examples\n- [How to Use Skills in Claude Code](https:\u002F\u002Fskywork.ai\u002Fblog\u002Fhow-to-use-skills-in-claude-code-install-path-project-scoping-testing\u002F) - Installation, project scoping, and testing guide\n\n### Video Tutorials\n\n_Video tutorials coming soon! Have a good video about Claude Skills? Submit a PR!_\n\n\u003Cdetails>\n\u003Csummary>Example topics we'd love to see\u003C\u002Fsummary>\n\n- Getting started with Claude Skills\n- Building your first custom skill\n- Skills vs MCP comparison\n- Enterprise deployment strategies\n\u003C\u002Fdetails>\n\n## 📰 Articles & Blog Posts\n\n- [Skills Explained](https:\u002F\u002Fclaude.com\u002Fblog\u002Fskills-explained) - Official Anthropic blog post covering progressive disclosure, use cases, and when to use Skills vs other tools\n- [Simon Willison: Claude Skills are awesome, maybe a bigger deal than MCP](https:\u002F\u002Fsimonwillison.net\u002F2025\u002FOct\u002F16\u002Fclaude-skills\u002F) - Technical deep dive and analysis\n\n## 🔒 Security & Best Practices\n\n⚠️ **Important**: Skills can execute arbitrary code in Claude's environment. Only install skills from trusted sources.\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Security Guidelines & Best Practices\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n### Vetting Skills\n\n- **Only install skills from trusted sources**\n- **Review SKILL.md and all scripts** before enabling a skill\n- **Be cautious of skills** that request sensitive data access\n- **Audit carefully** before deploying to production or enterprise environments\n\n### Security Concerns\n\n- **Malicious skills** may introduce vulnerabilities or enable data exfiltration\n- **Prompt injection attacks** could be amplified through compromised skills\n- **Sandboxing limitations** - Understand the security model before enterprise deployment\n- **Security research**: [Weaponizing Claude Code Skills](https:\u002F\u002Fmedium.com\u002F@yossifqassim\u002Fweaponizing-claude-code-skills-from-5-5-to-remote-shell-a14af2d109c9) - Analysis of potential security risks\n\n### Best Practices\n\n- **Version control** - Track all skills in git with proper version tags\n- **Code review** - Peer review custom skills before team distribution\n- **Least privilege** - Only grant necessary permissions and access\n- **Regular audits** - Periodically review installed skills\n- **Documentation** - Maintain clear documentation for custom skills\n- **Testing** - Thoroughly test skills in non-production environments first\n\n### Enterprise Considerations\n\n- As of October 2025, Claude.ai does not support centralized admin management for custom skills\n- Use version control and internal repositories for team skill distribution\n- Establish clear policies for skill vetting and approval\n- Monitor skill usage and performance\n\n\u003C\u002Fdetails>\n\n## 🛠️ Troubleshooting\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Known Issues & Common Problems\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n### Known Issues\n\n- **Linux path bug (Oct 18, 2025)**: Agent SDK uses hardcoded macOS paths instead of environment home directory\n\n  - [Issue #268](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-agent-sdk-python\u002Fissues\u002F268)\n  - Workaround: Manually specify skill paths\n\n- **Enterprise distribution**: No centralized admin management yet for custom skills on claude.ai\n  - Use git repositories for team distribution\n  - API integration provides more control\n\n### Common Problems\n\n**Skills not appearing in Claude**\n\n- Check Settings > Capabilities to ensure Skills are enabled\n- For Team\u002FEnterprise: Verify admin has enabled Skills organization-wide\n- Restart Claude after installing new skills\n\n**Skills not loading\u002Factivating**\n\n- Verify SKILL.md has proper YAML frontmatter format\n- Check that `name` and `description` fields are present\n- Ensure file structure matches expected format\n\n**Permission errors**\n\n- Review admin settings for Team\u002FEnterprise accounts\n- Check file permissions in skill directories\n- Verify API key has appropriate permissions\n\n**Skill execution failures**\n\n- Check script dependencies are installed\n- Review error logs for specific issues\n- Test scripts independently outside of Claude\n\n### Getting Help\n\n- [Official Skills Repository Issues](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Fissues)\n- [Claude Documentation](https:\u002F\u002Fdocs.claude.com\u002F)\n- [Community Discussions](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Fdiscussions)\n\n\u003C\u002Fdetails>\n\n## ❓ FAQ\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Common Questions\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n**Q: How much do skills impact token usage?**\n\nA: Skills are highly efficient thanks to progressive disclosure. Each skill uses only ~100 tokens during metadata scanning to determine relevance. When activated, the full skill content loads at \u003C5k tokens. Bundled resources only load as needed.\n\n**Q: What's the difference between Claude Skills and Agent Skills?**\n\nA: They are the same thing.\n\n**Q: Can I share skills with my team?**\n\nA: Yes! Skills can be shared via:\n\n- Git repositories (recommended)\n- Internal file sharing\n- Claude API for programmatic distribution\n- Enterprise-wide deployment features (coming soon)\n\n**Q: Do skills work with all Claude models?**\n\nA: Skills are available for Pro, Max, Team, and Enterprise users. Free tier users do not have access to Skills.\n\n**Q: Can skills call external APIs?**\n\nA: Yes, skills can include scripts that call external APIs. For complex API integrations, consider using MCP (Model Context Protocol) alongside skills.\n\n**Q: How does Claude decide which skill to use?**\n\nA: Claude scans all available skills' frontmatter (name and description), evaluates relevance to the current task, then loads the full content of relevant skills. Multiple skills can be loaded and composed together automatically.\n\n**Q: Can I use Skills and MCP together?**\n\nA: Absolutely! They complement each other. Use Skills for task-specific workflows and MCP for external data\u002FAPI integration. The `mcp-builder` skill can even help you build MCP servers.\n\n**Q: Are there any costs beyond my Claude subscription?**\n\nA: No additional costs for using official skills. Community and custom skills are free to use, though some may require external services (APIs, databases, etc.) that have their own costs.\n\n**Q: Can I monetize custom skills?**\n\nA: Currently, there is no official marketplace for paid skills. Anthropic has mentioned plans for community contributions and a potential marketplace in the future.\n\n**Q: How do I update a skill?**\n\nA: For skills from git repositories, pull the latest changes. For manually installed skills, replace the skill folder with the updated version. Always test updates in a non-production environment first.\n\n\u003C\u002Fdetails>\n\n## 🤝 Contributing\n\nContributions welcome! See [contribution guidelines](CONTRIBUTING.md) for details. To add a skill or resource: fork, add to appropriate section, submit PR.\n","awesome-claude-skills 是一个精心整理的 Claude AI 技能、资源和工具列表，特别适用于定制 Claude AI 工作流。项目提供了多种技能，通过元数据加载、完整指令加载及按需加载资源的方式，实现高效的任务执行。这些技能以文件夹形式存在，包含执行特定任务所需的指令、脚本和资源。适合需要利用 Claude AI 处理文档操作（如 Word、PDF、PowerPoint 和 Excel 文件）、设计与创意等场景的专业人士或团队使用。用户可以通过 Claude.ai 网页界面、命令行接口或 API 接入这些技能，从而增强 Claude AI 的功能并提高工作效率。",2,"2026-06-11 03:48:21","high_star"]