Skip to content
Back to search

awesome-claude-skills

MarketplaceWorks with Claude CodeGitHub

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows — particularly Claude Code

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/travisvn-awesome-claude-skills/badge.svg)](/listings/travisvn-awesome-claude-skills)

HTML

<a href="/listings/travisvn-awesome-claude-skills"><img src="/api/listings/travisvn-awesome-claude-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Claude.ai Web Interface

1. Go to [Settings > Capabilities](https://claude.ai/settings/capabilities) 2. Enable Skills toggle 3. Browse available skills or upload custom skills 4. **For Team/Enterprise**: Admin must enable Skills organization-wide first

Claude Code CLI

# Install skills from marketplace
/plugin marketplace add anthropics/skills

# Or install from local directory
/plugin add /path/to/skill-directory

Claude API

Skills are accessible via the `/v1/skills` API endpoint. See the [Skills API documentation](https://platform.claude.com/docs/en/api/beta/skills) for detailed integration examples.

import anthropic

client = anthropic.Client(api_key="your-api-key")
# See API docs for full implementation details

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 453 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <a href="https://github.com/travisvn/awesome-claude-skills">
  3. <img alt="Awesome Claude Skills" src="https://pc0o4oduww.ufs.sh/f/crfz5GypRfo0lI4924gMSJKLY6297aVP0zZpilXBvqTbDyrs"/>
  4. </a>
  5. </p>
  6. # Awesome Claude Skills
  7. [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)
  8. [![Last Updated](https://img.shields.io/badge/updated-Feb%202026-green.svg)]()
  9. [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)
  10. > A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
  11. **Claude Skills** teach Claude how to **perform tasks in a repeatable way**
  12. They are specialized folders containing instructions, scripts, and resources that Claude dynamically discovers and loads when relevant to tasks.
  13. ### How Skills Work
  14. Skills employ a **progressive disclosure architecture** for efficiency:
  15. 1. **Metadata loading** (~100 tokens): Claude scans available Skills to identify relevant matches
  16. 2. **Full instructions** (<5k tokens): Load when Claude determines the Skill applies
  17. 3. **Bundled resources**: Files and executable code load only as needed
  18. This design allows multiple Skills to remain available without overwhelming Claude's context window.
  19. ## 🚀 Getting Started
  20. ### Claude.ai Web Interface
  21. 1. Go to [Settings > Capabilities](https://claude.ai/settings/capabilities)
  22. 2. Enable Skills toggle
  23. 3. Browse available skills or upload custom skills
  24. 4. **For Team/Enterprise**: Admin must enable Skills organization-wide first
  25. ### Claude Code CLI
  26. ```bash
  27. # Install skills from marketplace
  28. /plugin marketplace add anthropics/skills
  29. # Or install from local directory
  30. /plugin add /path/to/skill-directory
  31. ```
  32. ### Claude API
  33. Skills are accessible via the `/v1/skills` API endpoint. See the [Skills API documentation](https://platform.claude.com/docs/en/api/beta/skills) for detailed integration examples.
  34. ```python
  35. import anthropic
  36. client = anthropic.Client(api_key="your-api-key")
  37. # See API docs for full implementation details
  38. ```
  39. ## 🎯 Official Skills
  40. ### Document Skills
  41. Skills for working with complex file formats:
  42. - **[docx](https://github.com/anthropics/skills/tree/main/skills/docx)** - Create, edit, and analyze Word documents with support for tracked changes, comments, formatting preservation, and text extraction
  43. - **[pdf](https://github.com/anthropics/skills/tree/main/skills/pdf)** - Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms
  44. - **[pptx](https://github.com/anthropics/skills/tree/main/skills/pptx)** - Create, edit, and analyze PowerPoint presentations with support for layouts, templates, charts, and automated slide generation
  45. - **[xlsx](https://github.com/anthropics/skills/tree/main/skills/xlsx)** - Create, edit, and analyze Excel spreadsheets with support for formulas, formatting, data analysis, and visualization
  46. ### Design & Creative
  47. - **[algorithmic-art](https://github.com/anthropics/skills/tree/main/skills/algorithmic-art)** - Create generative art using p5.js with seeded randomness, flow fields, and particle systems
  48. - **[canvas-design](https://github.com/anthropics/skills/tree/main/skills/canvas-design)** - Design beautiful visual art in .png and .pdf formats using design philosophies
  49. - **[slack-gif-creator](https://github.com/anthropics/skills/tree/main/skills/slack-gif-creator)** - Create animated GIFs optimized for Slack's size constraints
  50. ### Development
  51. - **[frontend-design](https://github.com/anthropics/skills/blob/main/skills/frontend-design)** - Instructs Claude to avoid "AI slop" or generic aesthetics and to make bold design decisions. Works very well for React & Tailwind.
  52. - **[web-artifacts-builder](https://github.com/anthropics/skills/tree/main/skills/web-artifacts-builder)** - Build complex claude.ai HTML artifacts using React, Tailwind CSS, and shadcn/ui components
  53. - **[mcp-builder](https://github.com/anthropics/skills/tree/main/skills/mcp-builder)** - Guide for creating high-quality MCP servers to integrate external APIs and services
  54. - **[webapp-testing](https://github.com/anthropics/skills/tree/main/skills/webapp-testing)** - Test local web applications using Playwright for UI verification and debugging
  55. ### Communication
  56. - **[brand-guidelines](https://github.com/anthropics/skills/tree/main/skills/brand-guidelines)** - Apply Anthropic's official brand colors and typography to artifacts
  57. - **[internal-comms](https://github.com/anthropics/skills/tree/main/skills/internal-comms)** - Write internal communications like status reports, newsletters, and FAQs
  58. ### Skill Creation
  59. - **[skill-creator](https://github.com/anthropics/skills/tree/main/skills/skill-creator)** - Interactive skill creation tool that guides you through building new skills with Q&A
  60. ## 🌟 Community Skills
  61. > [!Warning]
  62. > Skills can execute arbitrary code in Claude's environment.
  63. >
  64. > See [Security & Best Practices](#-security--best-practices) for more information
  65. ### Collections & Libraries
  66. - **[obra/superpowers](https://github.com/obra/superpowers)** - Core skills library for Claude Code with 20+ battle-tested skills including TDD, debugging, and collaboration patterns
  67. - Features `/brainstorm`, `/write-plan`, `/execute-plan` commands and skills-search tool
  68. - [superpowers-skills](https://github.com/obra/superpowers-skills) - Community-editable skills repository
  69. - [Blog: Superpowers](https://blog.fsck.com/2025/10/09/superpowers/) - Author's overview by Jesse Vincent
  70. - Installation: `/plugin marketplace add obra/superpowers-marketplace`
  71. - **[obra/superpowers-lab](https://github.com/obra/superpowers-lab)** - Experimental skills for `Claude Code Superpowers` (see above)
  72. - Uses new techniques that are still being refined and tested (i.e. skills here may change over time)
  73. - [Blog post about its development](https://blog.fsck.com/2025/10/23/naming-claude-plugins/)
  74. - Install from `superpowers-marketplace` plugin
  75. ### Individual Skills
  76. > These will be broken down into categories once there are enough community skills available to list
  77. | Skill | Description |
  78. | --- | --- |
  79. | **[ios-simulator-skill](https://github.com/conorluddy/ios-simulator-skill)** | iOS app building, navigation, and testing through automation |
  80. | **[ffuf-web-fuzzing](https://github.com/jthack/ffuf_claude_skill)** | Expert guidance for ffuf web fuzzing during penetration testing, including authenticated fuzzing with raw requests, auto-calibration, and result analysis |
  81. | **[playwright-skill](https://github.com/lackeyjb/playwright-skill)** | General-purpose browser automation using Playwright |
  82. | **[claude-d3js-skill](https://github.com/chrisvoncsefalvay/claude-d3js-skill)** | Visualizations in d3.js |
  83. | **[claude-scientific-skills](https://github.com/K-Dense-AI/claude-scientific-skills)** | Comprehensive collection of ready-to-use scientific skills, including working with specialized scientific libraries and databases |
  84. | **[web-asset-generator](https://github.com/alonw0/web-asset-generator)** | Generates web assets like favicons, app icons, and social media images |
  85. | **[loki-mode](https://github.com/asklokesh/claudeskill-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 |
  86. | **[Trail of Bits Security Skills](https://github.com/trailofbits/skills)** | Security skills for static analysis with CodeQL/Semgrep, variant analysis, code auditing, and vulnerability detection |
  87. | **[frontend-slides](https://github.com/zarazhangrui/frontend-slides)** | Create animation-rich HTML presentations — from scratch or by converting PowerPoint files |
  88. | **[Expo Skills](https://github.com/expo/skills)** | Official skills by the Expo team for developing Expo apps |
  89. | **[shadcn/ui](https://ui.shadcn.com/docs/skills)** | Give Claude Code context on shadcn components as well as pattern enforcement |
  90. | **[get-shit-done](https://github.com/gsd-build/get-shit-done)** | Lightweight meta-prompting, context engineering, and spec-driven development system for Claude Code by TÂCHES |
  91. _More community skills coming soon! Submit a PR to add your skill._
  92. ### Tools
  93. - **[yusufkaraaslan/Skill_Seekers](https://github.com/yusufkaraaslan/Skill_Seekers)** - Convert documentation websites into Claude Skills
  94. ## ✏️ Creating Your First Skill
  95. <details>
  96. <summary><strong>Step-by-Step Guide</strong></summary>
  97. ### Method 1: Use skill-creator (Recommended)
  98. The easiest way to create a skill is to use the built-in `skill-creator`:
  99. 1. Enable the skill-creator skill in Claude
  100. 2. Ask Claude: "Use the skill-creator to help me build a skill for [your task]"
  101. 3. Answer the interactive questions about your workflow
  102. 4. Claude generates the complete skill structure for you
  103. ### Method 2: Manual Creation
  104. 1. **Create folder structure**:
  105. ```
  106. my-skill/
  107. ├── SKILL.md # Main skill file with frontmatter
  108. ├── scripts/ # Optional executable scripts
  109. │ └── helper.py
  110. └── resources/ # Optional supporting files
  111. └── template.json
  112. ```
  113. 2. **Create SKILL.md with frontmatter**:
  114. ```yaml
  115. ---
  116. name: my-skill
  117. description: Brief description for skill discovery (keep concise)
  118. ---
  119. # Detailed Instructions
  120. Claude will read these instructions when the skill is activated.
  121. ## Usage
  122. Explain how to use this skill...
  123. ## Examples
  124. Provide clear examples...
  125. ```
  126. 3. **Add executable scripts** (optional):
  127. - Python, JavaScript, or other scripts Claude can execute
  128. - Reference them in your SKILL.md instructions
  129. 4. **Test locally**:
  130. - Install the skill in Claude Code or Claude Desktop
  131. - Test with relevant tasks
  132. - Iterate and refine
  133. 5. **Share**:
  134. - Publish to GitHub
  135. - Submit to this awesome list via PR
  136. - Share with your team via git repos or internal distribution
  137. ### Best Practices
  138. - **Keep descriptions concise** - The frontmatter description is used for skill discovery
  139. - **Use clear, actionable instructions** - Write instructions as if for a human collaborator
  140. - **Include examples** - Show specific examples in your SKILL.md
  141. - **Version your skills** - Use git tags for version management
  142. - **Document dependencies** - List any prerequisites or required packages
  143. - **Test thoroughly** - Verify your skill works across different scenarios
  144. </details>
  145. ## 📚 Official Documentation & Resources
  146. ### Getting Started
  147. - [What are Skills?](https://support.claude.com/en/articles/12512176-what-are-skills) - Official support article explaining Claude Skills
  148. - [Using Skills in Claude](https://support.claude.com/en/articles/12512180-using-skills-in-claude) - How to enable and use skills
  149. ### Documentation
  150. - [Claude Skills Announcement](https://www.anthropic.com/news/skills) - Official announcement from Anthropic
  151. - [Equipping Agents with Skills](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills) - Engineering deep dive on Agent Skills
  152. - [Claude Developer Platform](https://docs.claude.com/) - Official documentation
  153. - [Skills API Endpoint](https://platform.claude.com/docs/en/api/beta/skills) - `/v1/skills` API documentation
  154. ### Repositories & Examples
  155. - [anthropics/skills](https://github.com/anthropics/skills) - Official public repository for Skills
  156. - [Claude Cookbooks - Skills](https://github.com/anthropics/claude-cookbooks/tree/main/skills) - Example notebooks and tutorials
  157. ## 📅 Recent Updates
  158. ### November 2025
  159. - **Nov 13**: Anthropic publishes [Skills Explained](https://claude.com/blog/skills-explained) - Comprehensive guide covering progressive disclosure architecture, decision matrices for Skills vs Prompts/Subagents/Projects, and best practices
  160. ### October 2025
  161. - **Oct 18**: Major community repositories emerge: [obra/superpowers](https://github.com/obra/superpowers) skills library
  162. - **Oct 17**: Community publishes practical tutorials on DEV.to and Medium
  163. - **Oct 16**: 🎉 **Claude Skills officially announced** - Available across Claude.ai, Code, and API
  164. - **Oct 16**: Initial skills released including docx, pdf, pptx, xlsx, algorithmic-art, canvas-design, and more
  165. ## 💡 Skills vs Other Approaches
  166. ### Quick Reference: When to Use What
  167. | Tool | Best For |
  168. |------|----------|
  169. | **Skills** | Reusable procedural knowledge across conversations |
  170. | **Prompts** | One-time instructions and immediate context |
  171. | **Projects** | Persistent background knowledge within workspaces |
  172. | **Subagents** | Independent task execution with specific permissions |
  173. | **MCP** | Connecting Claude to external data sources |
  174. **Use Skills when**: Capabilities should be accessible to any Claude instance. They're portable expertise.
  175. **Use Subagents when**: You need self-contained agents designed for specific purposes with independent workflows and restricted tool access.
  176. **Combined approach**: Subagents can leverage Skills for specialized expertise, merging independence with portable knowledge.
  177. **Key insight**: *If you find yourself typing the same prompt repeatedly across multiple conversations, it's time to create a Skill.*
  178. ### Skills vs MCP (Model Context Protocol)
  179. | Feature | Skills | MCP |
  180. | -------------------- | --------------------------------------------- | --------------------------------- |
  181. | **Purpose** | Task-specific expertise and workflows | External data/API integration |
  182. | **Portability** | Same format everywhere (Claude.ai, Code, API) | Requires server configuration |
  183. | **Code Execution** | Can include executable scripts | Provides tools/resources |
  184. | **Token Efficiency** | 30-50 tokens until loaded | Varies by implementation |
  185. | **Best For** | Repeatable tasks, document workflows | Database access, API integrations |
  186. **Use Together**: Skills can create MCP servers! The `mcp-builder` skill helps build high-quality MCP integrations.
  187. #### Skills vs System Prompts
  188. | Feature | Skills | System Prompts |
  189. | ----------------- | --------------------------------------------------- | --------------------------------- |
  190. | **Structure** | Folder with YAML frontmatter, instructions, scripts | Plain text instructions |
  191. | **Reusability** | Version-controlled, shareable, composable | Copy-paste, conversation-specific |
  192. | **Loading** | On-demand (only when relevant) | Always in context |
  193. | **Maintenance** | Centralized updates | Manual updates per conversation |
  194. | **Composability** | Multiple skills stack automatically | Manual combination |
  195. ## 📖 Tutorials & Guides
  196. ### Written Tutorials
  197. - [How to Create Your First Claude Skill](https://skywork.ai/blog/ai-agent/how-to-create-claude-skill-step-by-step-guide/) - Step-by-step tutorial with examples
  198. - [How to Use Skills in Claude Code](https://skywork.ai/blog/how-to-use-skills-in-claude-code-install-path-project-scoping-testing/) - Installation, project scoping, and testing guide
  199. ### Video Tutorials
  200. _Video tutorials coming soon! Have a good video about Claude Skills? Submit a PR!_
  201. <details>
  202. <summary>Example topics we'd love to see</summary>
  203. - Getting started with Claude Skills
  204. - Building your first custom skill
  205. - Skills vs MCP comparison
  206. - Enterprise deployment strategies
  207. </details>
  208. ## 📰 Articles & Blog Posts
  209. - [Skills Explained](https://claude.com/blog/skills-explained) - Official Anthropic blog post covering progressive disclosure, use cases, and when to use Skills vs other tools
  210. - [Simon Willison: Claude Skills are awesome, maybe a bigger deal than MCP](https://simonwillison.net/2025/Oct/16/claude-skills/) - Technical deep dive and analysis
  211. ## 🔒 Security & Best Practices
  212. ⚠️ **Important**: Skills can execute arbitrary code in Claude's environment. Only install skills from trusted sources.
  213. <details>
  214. <summary><strong>Security Guidelines & Best Practices</strong></summary>
  215. ### Vetting Skills
  216. - **Only install skills from trusted sources**
  217. - **Review SKILL.md and all scripts** before enabling a skill
  218. - **Be cautious of skills** that request sensitive data access
  219. - **Audit carefully** before deploying to production or enterprise environments
  220. ### Security Concerns
  221. - **Malicious skills** may introduce vulnerabilities or enable data exfiltration
  222. - **Prompt injection attacks** could be amplified through compromised skills
  223. - **Sandboxing limitations** - Understand the security model before enterprise deployment
  224. - **Security research**: [Weaponizing Claude Code Skills](https://medium.com/@yossifqassim/weaponizing-claude-code-skills-from-5-5-to-remote-shell-a14af2d109c9) - Analysis of potential security risks
  225. ### Best Practices
  226. - **Version control** - Track all skills in git with proper version tags
  227. - **Code review** - Peer review custom skills before team distribution
  228. - **Least privilege** - Only grant necessary permissions and access
  229. - **Regular audits** - Periodically review installed skills
  230. - **Documentation** - Maintain clear documentation for custom skills
  231. - **Testing** - Thoroughly test skills in non-production environments first
  232. ### Enterprise Considerations
  233. - As of October 2025, Claude.ai does not support centralized admin management for custom skills
  234. - Use version control and internal repositories for team skill distribution
  235. - Establish clear policies for skill vetting and approval
  236. - Monitor skill usage and performance
  237. </details>
  238. ## 🛠️ Troubleshooting
  239. <details>
  240. <summary><strong>Known Issues & Common Problems</strong></summary>
  241. ### Known Issues
  242. - **Linux path bug (Oct 18, 2025)**: Agent SDK uses hardcoded macOS paths instead of environment home directory
  243. - [Issue #268](https://github.com/anthropics/claude-agent-sdk-python/issues/268)
  244. - Workaround: Manually specify skill paths
  245. - **Enterprise distribution**: No centralized admin management yet for custom skills on claude.ai
  246. - Use git repositories for team distribution
  247. - API integration provides more control
  248. ### Common Problems
  249. **Skills not appearing in Claude**
  250. - Check Settings > Capabilities to ensure Skills are enabled
  251. - For Team/Enterprise: Verify admin has enabled Skills organization-wide
  252. - Restart Claude after installing new skills
  253. **Skills not loading/activating**
  254. - Verify SKILL.md has proper YAML frontmatter format
  255. - Check that `name` and `description` fields are present
  256. - Ensure file structure matches expected format
  257. **Permission errors**
  258. - Review admin settings for Team/Enterprise accounts
  259. - Check file permissions in skill directories
  260. - Verify API key has appropriate permissions
  261. **Skill execution failures**
  262. - Check script dependencies are installed
  263. - Review error logs for specific issues
  264. - Test scripts independently outside of Claude
  265. ### Getting Help
  266. - [Official Skills Repository Issues](https://github.com/anthropics/skills/issues)
  267. - [Claude Documentation](https://docs.claude.com/)
  268. - [Community Discussions](https://github.com/anthropics/skills/discussions)
  269. </details>
  270. ## ❓ FAQ
  271. <details>
  272. <summary><strong>Common Questions</strong></summary>
  273. **Q: How much do skills impact token usage?**
  274. A: 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 <5k tokens. Bundled resources only load as needed.
  275. **Q: What's the difference between Claude Skills and Agent Skills?**
  276. A: They are the same thing.
  277. **Q: Can I share skills with my team?**
  278. A: Yes! Skills can be shared via:
  279. - Git repositories (recommended)
  280. - Internal file sharing
  281. - Claude API for programmatic distribution
  282. - Enterprise-wide deployment features (coming soon)
  283. **Q: Do skills work with all Claude models?**
  284. A: Skills are available for Pro, Max, Team, and Enterprise users. Free tier users do not have access to Skills.
  285. **Q: Can skills call external APIs?**
  286. A: Yes, skills can include scripts that call external APIs. For complex API integrations, consider using MCP (Model Context Protocol) alongside skills.
  287. **Q: How does Claude decide which skill to use?**
  288. A: 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.
  289. **Q: Can I use Skills and MCP together?**
  290. A: Absolutely! They complement each other. Use Skills for task-specific workflows and MCP for external data/API integration. The `mcp-builder` skill can even help you build MCP servers.
  291. **Q: Are there any costs beyond my Claude subscription?**
  292. A: 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.
  293. **Q: Can I monetize custom skills?**
  294. A: Currently, there is no official marketplace for paid skills. Anthropic has mentioned plans for community contributions and a potential marketplace in the future.
  295. **Q: How do I update a skill?**
  296. A: 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.
  297. </details>
  298. ## 🤝 Contributing
  299. Contributions welcome! See [contribution guidelines](CONTRIBUTING.md) for details. To add a skill or resource: fork, add to appropriate section, submit PR.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.