Awesome Agent Skills

Agent Skills are folders with instructions, scripts, and resources that teach AI coding assistants specific tasks

This collection features official skills published by leading development teams, including Anthropic, Google Labs, Vercel, Stripe, Cloudflare, Trail of Bits, Sentry, Expo, Hugging Face, and more, alongside community-built skills.

Compatible with Claude Code, Codex, Antigravity, Gemini CLI, Cursor, GitHub Copilot, OpenCode, Windsurf, and more. See the table below for paths and documentation.

The most contributed Agent Skills repository, built and maintained together with the community.

What a Basic Skill Looks Like?

---
name: api-tester
description: Test REST APIs and validate responses
---

# API Tester

Test HTTP endpoints and validate response structures.

## When to Use This Skill

Use this skill when you need to test API endpoints and verify response data.

## Instructions

When testing an API:

1. Send a request to the specified endpoint
2. Check the response status code
3. Validate the response body structure
4. Report any errors or unexpected results

## Response Validation

- Verify required fields exist
- Check data types match expected values
- Confirm nested objects have correct structure

See the official repo and creation guide for more details.

Skills Paths for Other AI Coding Assistants

Tool	Project Path	Global Path	Official Docs
Antigravity	.agent/skills/	~/.gemini/antigravity/skills/	Antigravity Skills
Claude Code	.claude/skills/	~/.claude/skills/	Claude Code Skills
Codex	.codex/skills/	~/.codex/skills/	Codex Skills
Cursor	.cursor/skills/	~/.cursor/skills/	Cursor Skills
Gemini CLI	.gemini/skills/	~/.gemini/skills/	Gemini CLI Skills
GitHub Copilot	.github/skills/	~/.copilot/skills/	Copilot Skills
OpenCode	.opencode/skills/	~/.config/opencode/skills/	OpenCode Skills
Windsurf	.windsurf/skills/	~/.codeium/windsurf/skills/	Windsurf Cascade Skills

Official Claude Skills

Document Creation

• anthropics/docx - Create, edit, and analyze Word documents
• anthropics/doc-coauthoring - Collaborative document editing and co-authoring
• anthropics/pptx - Create, edit, and analyze PowerPoint presentations
• anthropics/xlsx - Create, edit, and analyze Excel spreadsheets
• anthropics/pdf - Extract text, create PDFs, and handle forms

Creative and Design

• anthropics/algorithmic-art - Create generative art using p5.js with seeded randomness
• anthropics/canvas-design - Design visual art in PNG and PDF formats
• anthropics/frontend-design - Frontend design and UI/UX development tools
• anthropics/slack-gif-creator - Create animated GIFs optimized for Slack size constraints
• anthropics/theme-factory - Style artifacts with professional themes or generate custom themes

Development

• anthropics/web-artifacts-builder - Build complex claude.ai HTML artifacts with React and Tailwind
• anthropics/mcp-builder - Create MCP servers to integrate external APIs and services
• anthropics/webapp-testing - Test local web applications using Playwright

Branding and Communication

• anthropics/brand-guidelines - Apply Anthropic's brand colors and typography to artifacts
• anthropics/internal-comms - Write status reports, newsletters, and FAQs

Meta

• anthropics/skill-creator - Guide for creating skills that extend Claude's capabilities
• anthropics/template - Basic template for creating new skills

Skills by Vercel Engineering Team

• vercel-labs/react-best-practices - React best practices and patterns
• vercel-labs/vercel-deploy-claimable - Deploy projects to Vercel
• vercel-labs/web-design-guidelines - Web design guidelines and standards
• vercel-labs/composition-patterns - React component composition and reusable patterns
• vercel-labs/next-best-practices - Next.js best practices and recommended patterns
• vercel-labs/next-cache-components - Caching strategies and cache-aware components in Next.js
• vercel-labs/next-upgrade - Upgrade Next.js projects to newer versions
• vercel-labs/react-native-skills - React Native best practices and performance guidelines

Skills by Cloudflare Team

• cloudflare/agents-sdk - Build stateful AI agents with scheduling, RPC, and MCP servers
• cloudflare/building-ai-agent-on-cloudflare - Build AI agents with state and WebSockets on Cloudflare
• cloudflare/building-mcp-server-on-cloudflare - Build remote MCP servers with tools and OAuth
• cloudflare/commands - Cloudflare CLI commands reference
• cloudflare/durable-objects - Stateful coordination with RPC, SQLite, and WebSockets
• cloudflare/web-perf - Audit Core Web Vitals and render-blocking resources
• cloudflare/wrangler - Deploy and manage Workers, KV, R2, D1, Vectorize, Queues, Workflows

Skills by Supabase Team

• supabase/postgres-best-practices - PostgreSQL best practices for Supabase

Skills by Google Labs (Stitch)

Agent Skills for the Stitch MCP server, compatible with Claude Code, Gemini CLI, Cursor, and more.

• google-labs-code/design-md - Create and manage DESIGN.md files
• google-labs-code/react-components - Stitch to React components conversion

Skills by Hugging Face Team

Official AI agent skills from the Hugging Face team for ML workflows.

• huggingface/hugging-face-cli - HF Hub CLI for models, datasets, repos, and compute jobs
• huggingface/hugging-face-datasets - Create and manage datasets with configs and SQL querying
• huggingface/hugging-face-evaluation - Model evaluation with vLLM/lighteval and eval tables
• huggingface/hugging-face-jobs - Run compute jobs and Python scripts on HF infrastructure
• huggingface/hugging-face-model-trainer - Train models with TRL: SFT, DPO, GRPO, GGUF conversion
• huggingface/hugging-face-paper-publisher - Publish papers on HF Hub with model/dataset links
• huggingface/hugging-face-tool-builder - Build reusable scripts for HF API operations
• huggingface/hugging-face-trackio - Track ML experiments with real-time dashboards

Skills by Stripe Team

• stripe/stripe-best-practices - Best practices for building Stripe integrations
• stripe/upgrade-stripe - Upgrade Stripe SDK and API versions

Security Skills by Trail of Bits Team

• trailofbits/ask-questions-if-underspecified - Prompt for clarification on ambiguous requirements
• trailofbits/audit-context-building - Deep architectural context via ultra-granular code analysis
• trailofbits/building-secure-contracts - Smart contract security toolkit with vulnerability scanners for 6 blockchains
• trailofbits/burpsuite-project-parser - Search and extract data from Burp Suite project files
• trailofbits/claude-in-chrome-troubleshooting - Diagnose and fix Claude in Chrome MCP extension connectivity issues
• trailofbits/constant-time-analysis - Detect compiler-induced timing side-channels in crypto code
• trailofbits/culture-index - Index and search culture documentation
• trailofbits/differential-review - Security-focused diff review with git history analysis
• trailofbits/dwarf-expert - DWARF debugging format expertise
• trailofbits/entry-point-analyzer - Identify state-changing entry points in smart contracts
• trailofbits/firebase-apk-scanner - Scan Android APKs for Firebase misconfigurations and security vulnerabilities
• trailofbits/fix-review - Verify fix commits address audit findings without new bugs
• trailofbits/insecure-defaults - Detect insecure default configurations like hardcoded secrets, default credentials, and weak crypto
• trailofbits/modern-python - Modern Python tooling with uv, ruff, ty, and pytest best practices
• trailofbits/property-based-testing - Property-based testing for multiple languages and smart contracts
• trailofbits/semgrep-rule-creator - Create and refine Semgrep rules for vulnerability detection
• trailofbits/semgrep-rule-variant-creator - Port existing Semgrep rules to new target languages with test-driven validation
• trailofbits/sharp-edges - Identify error-prone APIs and dangerous configurations
• trailofbits/spec-to-code-compliance - Specification-to-code compliance checker for blockchain audits
• trailofbits/static-analysis - Static analysis toolkit with CodeQL, Semgrep, and SARIF
• trailofbits/testing-handbook-skills - Testing Handbook skills: fuzzers, static analysis, sanitizers
• trailofbits/variant-analysis - Find similar vulnerabilities via pattern-based analysis

Skills by Expo Team

Official AI agent skills from the Expo team for building, deploying, and debugging Expo apps.

• expo/expo-app-design - Design and build Expo applications
• expo/expo-deployment - Deploy Expo apps to production
• expo/upgrading-expo - Upgrade Expo SDK versions

Skills by Sentry team for their dev team.

• getsentry/agents-md - Generate and manage AGENTS.md files
• getsentry/claude-settings-audit - Audit Claude settings configuration
• getsentry/code-review - Perform code reviews
• getsentry/commit - Create commits with best practices
• getsentry/create-pr - Create pull requests
• getsentry/find-bugs - Find and identify bugs in code
• getsentry/iterate-pr - Iterate on pull request feedback

Skills by Better Auth Team

• better-auth/best-practices - Best practices for Better Auth integration
• better-auth/commands - Better Auth CLI commands
• better-auth/create-auth - Create authentication setup with Better Auth

Skills by Tinybird Team

• tinybirdco/tinybird-best-practices - Tinybird project guidelines for datasources, pipes, endpoints, and SQL

Skills by Neon Team

• neondatabase/using-neon - Best practices for Neon Serverless Postgres

Skill by Cloudflare Engineer

• dmmulroy/cloudflare-skill - Cloudflare platform reference for Workers, Pages, storage, AI, and networking

Skills by fal.ai Team

• fal-ai-community/fal-audio - Text-to-speech and speech-to-text using fal.ai audio models
• fal-ai-community/fal-generate - Generate images and videos using fal.ai AI models
• fal-ai-community/fal-image-edit - AI-powered image editing with style transfer and object removal
• fal-ai-community/fal-platform - Platform APIs for model management, pricing, and usage tracking
• fal-ai-community/fal-upscale - Upscale and enhance image and video resolution using AI
• fal-ai-community/fal-workflow - Generate workflow JSON files for chaining AI models

Skills by Sanity Team

• sanity-io/sanity-best-practices - Best practices for Sanity Studio, GROQ queries, and content workflows
• sanity-io/content-modeling-best-practices - Guidelines for designing scalable content models in Sanity
• sanity-io/seo-aeo-best-practices - SEO and answer engine optimization patterns for content sites
• sanity-io/content-experimentation-best-practices - Content A/B testing and experimentation workflows

Skills by Remotion Team

• remotion-dev/remotion - Programmatic video creation with React

Community Skills

Marketing

• coreyhaines31/marketingskills - 23+ marketing skills for SEO, copywriting, email, and ads
• ComposioHQ/content-research-writer - Enhance writing with research
• ComposioHQ/competitive-ads-extractor - Analyze competitor advertising
• wshuyi/x-article-publisher-skill - Publish articles to X/Twitter

Productivity and Collaboration

• notiondevs/Notion Skills for Claude - Skills for working with Notion
• op7418/NanoBanana-PPT-Skills - AI-powered PPT generation with document analysis and styled images
• zarazhangrui/frontend-slides - Generate animation-rich HTML presentations with visual style previews
• gokapso/integrate-whatsapp - Connect WhatsApp, set up webhooks, and send messages
• gokapso/automate-whatsapp - Build WhatsApp automations with workflows and agents
• gokapso/observe-whatsapp - Debug WhatsApp delivery issues and run health checks
• PleasePrompto/notebooklm-skill - Interact with NotebookLM for document-based conversations
• obra/superpowers-lab - Lab environment for Claude superpowers
• obra/brainstorming - Generate and explore ideas
• obra/writing-plans - Create strategic documentation
• obra/executing-plans - Implement and run strategic plans
• obra/dispatching-parallel-agents - Coordinate multiple simultaneous agents
• obra/sharing-skills - Distribute and communicate capabilities
• obra/using-superpowers - Leverage core platform capabilities
• ComposioHQ/meeting-insights-analyzer - Analyze meeting communication patterns
• ComposioHQ/image-enhancer - Improve image quality
• wrsmith108/linear-claude-skill - Manage Linear issues, projects, and teams
• Shpigford/readme - Generate comprehensive project documentation

Development and Testing

• robzolkos/skill-rails-upgrade - Analyze Rails apps and provide upgrade assessments
• Shpigford/screenshots - Generate marketing screenshots with Playwright
• antonbabenko/terraform-skill - Terraform infrastructure as code best practices
• zxkane/aws-skills - AWS development with infrastructure automation and cloud architecture patterns
• Rootly-AI-Labs/rootly-incident-responder - AI-powered incident response with ML similarity matching, solution suggestions, and on-call coordination. Requires Rootly MCP Server
• conorluddy/ios-simulator-skill - Control iOS Simulator
• sanjay3290/postgres - Execute safe read-only SQL queries against PostgreSQL databases
• sanjay3290/deep-research - Autonomous multi-step research using Gemini Deep Research Agent
• jthack/ffuf-claude-skill - Web fuzzing with ffuf
• lackeyjb/playwright-skill - Browser automation with Playwright
• ibelick/ui-skills - Opinionated, evolving constraints to guide agents when building interfaces
• nextlevelbuilder/ui-ux-pro-max-skill - UI/UX design patterns and best practices
• scarletkc/vexor - Vector-powered CLI for semantic file search with a Claude/Codex skill
• obra/test-driven-development - Write tests before implementing code
• ComposioHQ/changelog-generator - Transform git commits into release notes
• obra/subagent-driven-development - Development using multiple sub-agents
• obra/systematic-debugging - Methodical problem-solving in code
• obra/root-cause-tracing - Investigate and identify fundamental problems
• obra/testing-skills-with-subagents - Collaborative testing approaches
• obra/testing-anti-patterns - Identify ineffective testing practices
• obra/finishing-a-development-branch - Complete Git code branches
• obra/requesting-code-review - Initiate code review processes
• obra/receiving-code-review - Process and incorporate code feedback
• obra/using-git-worktrees - Manage multiple Git working trees
• obra/verification-before-completion - Validate work before finalizing
• obra/condition-based-waiting - Manage conditional pauses or delays
• obra/commands - Create and manage command structures
• obra/writing-skills - Develop and document capabilities
• fvadicamo/dev-agent-skills - Git and GitHub workflow skills for commits, PRs, and code reviews
• omkamal/pypict-skill - Pairwise test generation
• alinaqi/claude-bootstrap - Opinionated project initialization with security-first guardrails, spec-driven atomic todos, LLM testing patterns, and CLI tool orchestration (gh, vercel, supabase)
• ZhangHanDong/makepad-skills - Makepad UI development skills for Rust apps: setup, patterns, shaders, packaging, and troubleshooting.
• massimodeluisa/recursive-decomposition-skill - Handle long-context tasks (100+ files, 50k+ tokens) through recursive decomposition strategies based on RLM research
• callstackincubator/react-native-best-practices - Performance optimization for React Native apps from Callstack
• AvdLee/swiftui-expert-skill - Modern SwiftUI best practices and iOS 26+ Liquid Glass adoption
• efremidze/swift-patterns-skill - Modern Swift/SwiftUI best practices
• CloudAI-X/threejs-skills - Three.js skills for creating 3D elements and interactive experiences

Context Engineering

• muratcankoylan/context-fundamentals - Understand what context is, why it matters, and the anatomy of context in agent systems
• muratcankoylan/context-degradation - Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash
• muratcankoylan/context-compression - Design and evaluate compression strategies for long-running sessions
• muratcankoylan/context-optimization - Apply compaction, masking, and caching strategies
• muratcankoylan/multi-agent-patterns - Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures
• muratcankoylan/memory-systems - Design short-term, long-term, and graph-based memory architectures
• muratcankoylan/tool-design - Build tools that agents can use effectively, including architectural reduction patterns
• muratcankoylan/evaluation - Build evaluation frameworks for agent systems

Specialized Domains

• K-Dense-AI/claude-scientific-skills - Scientific research and analysis skills
• NotMyself/claude-win11-speckit-update-skill - Windows 11 system management
• sanjay3290/imagen - Generate images using Google Gemini's API
• jeffersonwarrior/claudisms - SMS messaging integration
• SHADOWPR0/security-bluebook-builder - Build security Blue Books for sensitive apps
• obra/defense-in-depth - Multi-layered security approaches
• huifer/Claude-Ally-Health - A health assistant skill for medical information analysis, symptom tracking, and wellness guidance.
• frmoretto/clarity-gate - Pre-ingestion verification for epistemic quality in RAG systems with 9-point verification and Two-Round HITL workflow
• zechenzhangAGI/AI-research-SKILLs - Comprehensive library of 77 AI research engineering skills across 20 categories including model architecture, fine-tuning, distributed training, inference, evaluation, and MLOps

n8n Automation

• czlonkowski/n8n-code-javascript - JavaScript in n8n Code nodes with data access patterns
• czlonkowski/n8n-code-python - Python coding in n8n Code nodes with limitations
• czlonkowski/n8n-expression-syntax - n8n expression syntax with {{}} and $json/$node variables
• czlonkowski/n8n-mcp-tools-expert - MCP tools guide with tool selection and node formats
• czlonkowski/n8n-node-configuration - Node configuration with dependency rules and AI connections
• czlonkowski/n8n-validation-expert - Fix n8n validation errors with error catalog
• czlonkowski/n8n-workflow-patterns - Workflow patterns for webhook, HTTP, database, and AI tasks

Other

• materials-simulation-skills - Agent skills for computational materials science: numerical stability, time-stepping, linear solvers, mesh generation, simulation validation, parameter optimization, and post-processing
• wrsmith108/varlock-claude-skill - Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits
• SHADOWPR0/beautiful_prose - Hard-edged writing style contract for timeless, forceful English prose without AI tics
• SeanZoR/claude-speed-reader -Speed read Claude's responses at 600+ WPM using RSVP with Spritz-style ORP highlighting
• Skill_Seekers -Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes.

🤝 Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

• Submit new skills via PR
• Improve existing definitions

Note: Please don't submit skills you created 3 hours ago. We're now focusing on community-adopted skills, especially those published by development teams and proven in real-world usage. Quality over quantity.

Contributor ♥️ Thanks

License

MIT License - see LICENSE

This is a curated list. Skills listed here are created and maintained by their respective authors and teams, not by us. We select community-adopted, proven skills and do not audit, endorse, or guarantee the security or correctness of listed projects. They are not security-audited and should be reviewed before production use.

If you find an issue with a listed skill or want your skill removed, please open an issue and we'll take care of it promptly.