English | 繁體中文 | 简体中文 | 日本語 | 한국어 | Español
🌐 Browse the live directory at agent-skill.co
Maintained by Hailey Cheng (Cheng Hei Lam) · X @haileyhmt · haileycheng@proton.me
Never heard of "agent skills" before? You're in the right place. This is a community-curated list of simple text files that teach AI assistants (like Claude, Copilot, or Codex) how to do new things on demand, without retraining. Unlike bulk-generated skill repositories, this collection focuses on real-world Agent Skills created and used by actual engineering teams. Compatible with Claude Code, Codex, Antigravity, Gemini CLI, Cursor, GitHub Copilot, Windsurf, and more.
Step 1: Pick a skill from the directory below (or browse at agent-skill.co)
Step 2: Load it into your AI agent:
- Claude Code:
/skills add <github-url> - Claude.ai: paste the raw SKILL.md URL in a new conversation
- Codex / Copilot: follow platform docs linked in Using Skills
Step 3: Ask your AI to use it. Just describe what you want in plain English.
That's it. No installation. No configuration. No coding required.
- What Are Agent Skills?
- How to Find Skills (Recommended)
- Compatible Agents
- Official Skill Directories
- Community Skills
- Skill Quality Standards
- Using Skills
- Creating Skills
- Official Tutorials and Guides
- Trends & Capabilities (2026)
- Frequently Asked Questions
- Contributing
- Contact
- License
Think of Agent Skills as "how-to guides" for AI assistants. Instead of the AI needing to know everything upfront, skills let it learn new abilities on the fly, like giving someone a recipe card instead of making them memorize an entire cookbook.
Skills are simple text files (called SKILL.md) that teach an AI how to do specific tasks. When you ask the AI to do something, it finds the right skill, reads the instructions, and gets to work.
Skills load in three stages:
- Browse: The AI sees a list of available skills (just names and short descriptions)
- Load: When a skill is needed, the AI reads the full instructions
- Use: The AI follows the instructions and accesses any helper files
- Faster and lighter: The AI only loads what it needs, when it needs it
- Works everywhere: Create a skill once, use it with any compatible AI tool
- Easy to share: Skills are just files you can copy, download, or share on GitHub
Skills are instructions, not code. The AI reads them like a human would read a guide, then follows the steps.
It is recommended to use the SkillsMP Marketplace, which automatically indexes all Skill projects on GitHub and organizes them by category, update time, star count, and other tags — making it the easiest way to discover and evaluate skills.
You can also use skills.sh — Vercel's leaderboard — to intuitively view the most popular Skills repositories and individual Skill usage statistics.
For specific skills, use the npx skills command-line tool to quickly discover, add, and manage skills. For detailed parameters, see vercel-labs/skills.
npx skills find [query] # Search for related skills
npx skills add <owner/repo> # Install skills (supports GitHub shorthand, full URL, local path)
npx skills list # List installed skills
npx skills check # Check for available updates
npx skills update # Upgrade all skills
npx skills remove [skill-name] # Uninstall skills| Agent | Documentation |
|---|---|
| Claude Code | code.claude.com/docs/en/skills |
| Claude.ai | support.claude.com |
| Codex (OpenAI) | developers.openai.com |
| GitHub Copilot | docs.github.com |
| VS Code | code.visualstudio.com |
| Antigravity | antigravity.google |
| Kiro | kiro.dev |
| Gemini CLI | geminicli.com |
| Junie | junie.jetbrains.com |
Official built-in skills for common document types and creative workflows.
- 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
- 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
- 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
- anthropics/brand-guidelines - Apply Anthropic's brand colors and typography to artifacts
- anthropics/internal-comms - Write status reports, newsletters, and FAQs
- anthropics/skill-creator - Guide for creating skills that extend Claude's capabilities
- anthropics/template - Basic template for creating new skills
Official curated skills from OpenAI's catalog.
- openai/cloudflare-deploy - Deploy apps to Cloudflare using Workers and Pages
- openai/develop-web-game - Build and test web games iteratively using Playwright
- openai/doc - Read, create, and edit .docx documents with formatting
- openai/gh-address-comments - Address review and issue comments on open GitHub PRs via CLI
- openai/gh-fix-ci - Debug and fix failing GitHub Actions PR checks
- openai/imagegen - Generate and edit images using OpenAI's Image API
- openai/jupyter-notebook - Create clean, reproducible Jupyter notebooks
- openai/linear - Manage issues, projects, and team workflows in Linear
- openai/netlify-deploy - Automate Netlify deployments with CLI support
- openai/notion-knowledge-capture - Convert conversations into structured Notion wiki entries
- openai/pdf - Read, create, and review PDFs with layout integrity
- openai/playwright - Automate real browser interactions for navigation and forms
- openai/sora - Generate, remix, and manage short video clips via Sora API
- openai/speech - Generate spoken audio from text using OpenAI's API
- openai/spreadsheet - Create, edit, analyze, and visualize spreadsheets
- openai/figma - Use the Figma MCP server to fetch design context
- openai/figma-implement-design - Translate Figma designs into production-ready code
- openai/frontend-skill - Create visually strong landing pages and web apps
Install via google-gemini/gemini-api-dev.
- google-gemini/gemini-api-dev - Best practices for developing Gemini-powered apps
- google-gemini/vertex-ai-api-dev - Developing Gemini apps on Google Cloud Vertex AI
- google-gemini/gemini-live-api-dev - Building real-time bidirectional streaming apps
- google-gemini/gemini-interactions-api - Text, chat, streaming, and image generation
Official skills for ML workflows.
- huggingface/hf-cli - HF CLI tool for Hub operations
- huggingface/hugging-face-datasets - Create and manage datasets with SQL querying
- huggingface/hugging-face-model-trainer - Train models with TRL: SFT, DPO, GRPO
- huggingface/transformers.js - Run ML models in the browser with Transformers.js
- replicate/replicate - Discover and run AI models via API
- fal-ai-community/fal-generate - Generate images and videos using fal.ai
- fal-ai-community/fal-realtime - Real-time and streaming AI image generation
- fal-ai-community/fal-upscale - Upscale and enhance image resolution
- MiniMax-AI/frontend-dev - Frontend with animations and AI media via MiniMax
- MiniMax-AI/minimax-pdf - Generate, fill, and reformat PDFs
- 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/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
- netlify/netlify-functions - Build serverless API endpoints and background tasks
- netlify/netlify-edge-functions - Low-latency edge middleware and geolocation logic
- netlify/netlify-blobs - Key-value object storage for files and data
- netlify/netlify-db - Managed Postgres with deploy preview branching
- netlify/netlify-deploy - Automated deployment workflow for Netlify sites
- netlify/netlify-ai-gateway - Access AI models via unified gateway endpoint
- vercel-labs/react-best-practices - React best practices and patterns
- vercel-labs/web-design-guidelines - Web design guidelines and standards
- 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/react-native-skills - React Native best practices and performance guidelines
- hashicorp/new-terraform-provider - Scaffold a new Terraform provider project using the Plugin Framework
- hashicorp/provider-resources - Implement Terraform Provider resources and data sources
- hashicorp/provider-test-patterns - Acceptance test patterns for Terraform providers
- hashicorp/refactor-module - Transform monolithic Terraform configurations into reusable modules
- hashicorp/terraform-style-guide - Generate Terraform HCL code following HashiCorp's official style conventions
- hashicorp/terraform-stacks - Manage infrastructure across multiple environments, regions, and cloud accounts
- neondatabase/neon-postgres - Best practices for Neon Serverless Postgres
- neondatabase/claimable-postgres - Claimable Postgres database provisioning with Neon
- neondatabase/neon-postgres-egress-optimizer - Optimize Neon Postgres egress and data transfer
- clickhouse/clickhouse-best-practices - Best practices for working with ClickHouse
- supabase/postgres-best-practices - PostgreSQL best practices for Supabase
- tinybirdco/tinybird-best-practices - Tinybird project guidelines for datasources, pipes, endpoints, and SQL
- tinybirdco/tinybird-cli-guidelines - Tinybird CLI usage guidelines and commands
- tinybirdco/tinybird-typescript-sdk-guidelines - Tinybird TypeScript SDK usage guidelines
- voltagent/create-voltagent - Project setup guide with CLI and manual steps
- voltagent/voltagent-best-practices - Architecture and usage patterns for agents, workflows, memory, and servers
- voltagent/voltagent-core-reference - Reference for the VoltAgent class options and lifecycle methods
- voltagent/voltagent-docs-bundle - Lookup embedded docs from @voltagent/core for version-matched documentation
- callstackincubator/react-native-best-practices - Performance optimization for React Native apps
- callstackincubator/github - GitHub workflow patterns for PRs, code review, branching
- callstackincubator/upgrading-react-native - React Native upgrade workflow: templates, dependencies, and pitfalls
- expo/building-native-ui - Build apps with Expo Router, styling, components, and animations
- expo/expo-api-routes - Create API routes in Expo Router with EAS Hosting
- expo/expo-deployment - Deploy Expo apps to production
- expo/upgrading-expo - Upgrade Expo SDK versions
- expo/use-dom - Run web code in a webview on native using DOM components
- remotion-dev/remotion - Programmatic video creation with React
- duckdb/attach-db - Attach a DuckDB database file for interactive querying
- duckdb/query - Run SQL queries against attached databases or ad-hoc files
- duckdb/duckdb-docs - Search DuckDB and DuckLake documentation
- greensock/gsap-core - Core API: gsap.to(), from(), fromTo(), easing, duration, stagger
- greensock/gsap-scrolltrigger - ScrollTrigger for scroll-linked animations and pinning
- greensock/gsap-react - React integration with useGSAP hook and SSR patterns
- WordPress/wp-block-development - Gutenberg blocks: block.json, attributes, rendering
- WordPress/wp-plugin-development - Plugin architecture, hooks, settings API, security
- WordPress/wp-playground - WordPress Playground for instant local environments
- figma/figma-implement-design - Translate Figma designs into production-ready code with 1:1 fidelity
- figma/figma-generate-library - Build or update a design system library in Figma from a codebase
- figma/figma-use - Run Figma Plugin API scripts for canvas writes and inspections
- google-labs-code/design-md - Create and manage DESIGN.md files
- google-labs-code/enhance-prompt - Improve prompts with design specs and UI/UX vocabulary
- google-labs-code/react-components - Stitch to React components conversion
- google-labs-code/shadcn-ui - Build UI components with shadcn/ui
- google-labs-code/stitch-loop - Iterative design-to-code feedback loop
- googleworkspace/gws-drive - Manage Google Drive files, folders, and shared drives
- googleworkspace/gws-sheets - Read and write Google Sheets spreadsheets
- googleworkspace/gws-gmail - Send, read, and manage Gmail email
- googleworkspace/gws-calendar - Manage Google Calendar calendars and events
- googleworkspace/gws-workflow - Cross-service Google Workspace productivity workflows
- stripe/stripe-best-practices - Best practices for building Stripe integrations
- stripe/upgrade-stripe - Upgrade Stripe SDK and API versions
- trycourier/courier-skills - Multi-channel notifications via email, SMS, push, and chat
- typefully/typefully - Create, schedule, and publish social media content
- composiohq/composio - Connect AI agents to 1000+ external apps with managed authentication
- makenotion/knowledge-capture - Transform conversations into structured Notion documentation
- makenotion/meeting-intelligence - Prepare meeting materials by gathering Notion context
- makenotion/spec-to-implementation - Turn tech specs into concrete Notion tasks
- resend/resend - Send and manage emails via the Resend API
- resend/react-email - Build emails with React Email components
- resend/email-best-practices - Email deliverability and design best practices
- sanity-io/sanity-best-practices - Best practices for Sanity Studio 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
- better-auth/best-practices - Best practices for Better Auth integration
- better-auth/create-auth - Create authentication setup with Better Auth
- better-auth/twoFactor - Two-factor authentication with Better Auth
Marketing Skills by Corey Haines
Comprehensive SaaS marketing stack skills by Corey Haines.
- coreyhaines31/ai-seo - Optimize content for AI-generated answers
- coreyhaines31/copywriting - Write marketing copy for landing pages and ads
- coreyhaines31/email-sequence - Build email sequences and drip campaigns
- coreyhaines31/page-cro - Improve conversion rates on marketing pages
- coreyhaines31/pricing-strategy - Define pricing and packaging for SaaS
- coreyhaines31/social-content - Create and schedule social media content
Product Manager Skills by Dean Peters
46 battle-tested PM skills by Dean Peters.
- deanpeters/epic-hypothesis - Turn initiatives into testable hypotheses
- deanpeters/opportunity-solution-tree - Generate solution trees based on Teresa Torres' method
- deanpeters/prd-development - Structured PRD process: problem to metrics
- deanpeters/roadmap-planning - Strategic roadmap process and communication
Product Management Skills by Pawel Huryn
65 PM skills by Paweł Huryn, creator of The Product Compass.
- phuryn/create-prd - Create a PRD with 8-section template
- phuryn/product-strategy - Create product strategy using the Canvas
- phuryn/user-personas - Create user personas with JTBD, pains, and gains
- phuryn/market-sizing - Estimate TAM, SAM, SOM with top-down and bottom-up
Skills by Garry Tan (gstack)
28 engineering leadership skills by Garry Tan.
- garrytan/office-hours - YC Office Hours: reframing product before code
- garrytan/plan-ceo-review - CEO/Founder plan review modes
- garrytan/design-review - Visual audit and atomic fixes with screenshots
- garrytan/qa - QA Lead: find bugs and generate regression tests
- garrytan/ship - Release Engineer: sync, test, audit, and push
- trailofbits/audit-context-building - Deep architectural context via granular code analysis
- trailofbits/building-secure-contracts - Smart contract security toolkit for 6 blockchains
- trailofbits/modern-python - Modern Python tooling with uv, ruff, and pytest
- trailofbits/static-analysis - Static analysis toolkit with CodeQL and Semgrep
- getsentry/agents-md - Generate and manage AGENTS.md files
- getsentry/code-review - Perform structured code reviews
- getsentry/find-bugs - Find and identify bugs in code
- firecrawl/firecrawl-cli - Scrape, crawl, search, and map the web via CLI
- firecrawl/firecrawl-agent - AI agent for autonomous web scraping
- firecrawl/firecrawl-browser - Browser-based web scraping and interaction
Skills by Microsoft
133 domain-specific skills for Azure SDK and Microsoft AI Foundry.
- microsoft/cloud-solution-architect - Design well-architected Azure cloud systems
- microsoft/copilot-sdk - Build applications powered by GitHub Copilot SDK
- microsoft/azure-ai-openai-dotnet - GPT-4, embeddings, and DALL-E client for .NET
- microsoft/azure-ai-projects-python - AI Foundry project client and agents for Python
- microsoft/azure-identity-typescript - Microsoft Entra ID authentication for TypeScript
- binance/crypto-market-rank - Query crypto market rankings and leaderboards
- binance/query-token-audit - Audit token security to detect scams and honeypots
- binance/trading-signal - Monitor on-chain Smart Money buy/sell signals
Install from sanity-io/agent-toolkit.
| Skill | Description |
|---|---|
| sanity-best-practices | Best practices for Sanity Studio, GROQ queries, and content workflows |
| content-modeling-best-practices | Guidelines for designing scalable content models in Sanity |
| seo-aeo-best-practices | SEO and answer engine optimization patterns for content sites |
Install from better-auth/skills.
| Skill | Description |
|---|---|
| best-practices | Best practices for Better Auth integration |
| explain-error | Explain Better Auth error messages |
| create-auth | Create authentication setup with Better Auth |
| twoFactor | Two-factor authentication with Better Auth |
| Skill | Description |
|---|---|
| agent-gtm-skills | 18 go-to-market skills: pricing, outbound, SEO, ads, retention, and ops |
| Skill | Description |
|---|---|
| pm-skills | 24 product management skills covering discovery, definition, delivery, and optimization |
| Skill | Description |
|---|---|
| pm-skills-huryn | Advanced product management frameworks, OKRs, and strategy skills |
| Skill | Description |
|---|---|
| gstack | YC founder stack recommendations for infra, tooling, and deployment |
| Skill | Description |
|---|---|
| safe-encryption-skill | Modern encryption alternative to GPG/PGP with post-quantum support |
| threat-hunting | Hunt for threats using Sigma detection rules |
Install from getsentry/skills.
| Skill | Description |
|---|---|
| sentry-skills | Debug errors, performance issues, and traces directly with Sentry integration |
Install from firecrawl/cli.
| Skill | Description |
|---|---|
| firecrawl-cli | Scrape, crawl, search, and map the web via CLI |
| firecrawl-agent | AI agent for autonomous web scraping and data extraction |
| firecrawl-scrape | Scrape web pages and extract content |
| firecrawl-search | Search the web and extract results |
Install from microsoft/agent-skills.
| Skill | Description |
|---|---|
| agent-skills | Official Microsoft agent skills collection |
| Skill | Description |
|---|---|
| kyberswap-skills | Token swap quotes and transactions across 18 EVM chains |
Vector Databases
- qdrant/skills - Agent skills for Qdrant vector search, scaling, and performance
Marketing
- BrianRWagner/ai-marketing-skills - 17 marketing frameworks for outreach and audits
- AgriciDaniel/claude-seo - Universal SEO skill for website analysis
- smixs/creative-director-skill - 20+ creative methodologies (SIT, TRIZ, SCAMPER)
- SHADOWPR0/beautiful_prose - Hard-edged writing style contract for forceful English prose
Productivity and Collaboration
- PSPDFKit-labs/nutrient-agent-skill - Document processing: convert, OCR, and redact PII
- RoundTable02/tutor-skills - Transform docs or codebases into interactive StudyVaults
- hanfang/claude-memory-skill - Hierarchical memory system with filesystem persistence
- wrsmith108/linear-claude-skill - Manage Linear issues, projects, and teams
Development and Testing
- muthuishere/hand-drawn-diagrams - Generate hand-drawn Excalidraw diagrams from prompt
- coderabbitai/skills - Code review and PR autofix workflows
- massimodeluisa/recursive-decomposition-skill - Handle long-context tasks (100+ files) via decomposition
- mcollina/skills - Node.js core, Fastify, and TypeScript skills by Matteo Collina
- Leonxlnx/taste-skill - High-agency frontend skill to eliminate generic UI slop
Context Engineering
- muratcankoylan/context-compression - Compression strategies for long-running sessions
- muratcankoylan/memory-systems - Design short-term and graph-based memory architectures
- k-kolomeitsev/data-structure-protocol - Graph-based memory for faster context and safer refactors
When evaluating or contributing skills, look for:
- Clear instructions: Steps are unambiguous and actionable
- Appropriate scope: Skill handles one focused task, not everything
- Working examples: Demonstrates real usage, not just theory
- Documented trade-offs: Honest about limitations and edge cases
- Size limit: SKILL.md under 500 lines for optimal agent performance
- Tested: Verified to actually work with the agent it targets
- Click the skill icon in your chat interface.
- Add skills from the marketplace or upload custom skills.
- Claude automatically activates relevant skills based on your task.
Antigravity supports two types of skills:
- Workspace Skills: Project-specific skills located in
/.agent/skills/ - Global Skills: User-wide skills located in
~/.gemini/antigravity/skills
For more details, see the official documentation.
mkdir -p ~/.claude/skills/
cp -r skill-name ~/.claude/skills/Verify skill metadata:
head ~/.claude/skills/skill-name/SKILL.mdThe skill loads automatically and activates when relevant.
Use the built-in $skill-creator skill in Codex. Or install manually:
$skill-installer linearRestart Codex after installing a skill to pick it up.
Skills are stored in directories with a SKILL.md file:
.github/skills/— Recommended location for all new skills.claude/skills/— Legacy location, also supported
SKILL.md structure:
name(required): A unique lowercase identifier using hyphens for spacesdescription(required): What the skill does and when the agent should use it- Markdown body with instructions, examples, and guidelines
Edit your configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/username/Desktop"]
}
}
}Skills are instruction bundles that tell the agent how to perform specific tasks. They are not executable code.
skill-name/
├── SKILL.md # Required: Instructions and metadata
├── scripts/ # Optional: Helper scripts
├── templates/ # Optional: Document templates
└── resources/ # Optional: Reference files
---
name: my-skill-name
description: A clear description of what this skill does.
---
# My Skill Name
Detailed description of the skill's purpose.
## When to Use This Skill
- Use case 1
- Use case 2
## Instructions
[Detailed instructions for the agent on how to execute this skill]
## Examples
[Real-world examples]For skills that need to connect to external data sources:
pip install fastmcpfrom fastmcp import FastMCP
mcp = FastMCP("My Server")
@mcp.tool()
def hello_world(name: str = "World") -> str:
"""A simple tool that says hello."""
return f"Hello, {name}!"
if __name__ == "__main__":
mcp.run()- Using skills in Claude — Official quick start guide
- How to create custom skills — Step-by-step authoring
- Claude Code Skills Documentation — Official reference
- About Agent Skills — GitHub documentation
- VS Code Agent Skills — VS Code integration
- MCP Official Documentation — The open standard
- Build your first MCP Server — Python/TypeScript guide
- MCP Server Examples — Official server implementations
The AI agent ecosystem has dramatically shifted from reactive chat interfaces to autonomous, goal-driven systems executing end-to-end multi-step workflows — a period often called the "Agent Leap."
Modern agents move past simple "prompt-response" models. They break down broad objectives into multi-step strategic plans, weighing trade-offs and executing sequences independently.
Complex tasks are managed by specialized agent teams (documentation, testing, coding) coordinated by "manager" agents that synthesize deliverables and resolve conflicts.
Environments like Cursor, Windsurf, Claude Code, and GitHub Copilot have evolved into full "Agentic IDEs" where agents execute terminal commands, monitor telemetry, and manage files natively via MCP and direct filesystem access.
Organizations are moving from general-purpose prompting to highly specialized skills for each platform and workflow — reducing hallucinations and improving reliability in production deployments.
Agent Skills are instruction files that teach AI assistants how to do specific tasks. They only load when needed, so the AI stays fast and focused.
Fine-tuning permanently changes how an AI thinks (expensive and hard to update). Agent Skills are just instruction files — you can update, swap, or share them anytime without touching the AI itself.
They work great together:
- Agent Skills — teach the AI how to do something (workflows, best practices)
- MCP — help the AI access things (APIs, databases, external tools)
Currently supported: Claude (Claude.ai and Claude Code), GitHub Copilot, VS Code, Codex (OpenAI), Antigravity (Google), Gemini CLI, Kiro, and Junie. The ecosystem is growing rapidly.
No. Skills are just text instructions — the AI reads and follows them like a recipe. If you need to run actual code, you'd use MCP servers alongside skills.
- Create a
SKILL.mdfile with a name and description at the top - Write clear, step-by-step instructions in the file
- Put it in your
.github/skills/or.claude/skills/folder - Test it out!
Full guide: How to create custom skills
Yes. Skills are plain-English instruction files, not code. You need an AI assistant (like Claude.ai) and nothing else. No terminal, no GitHub account, no technical background required. Just paste a skill's URL into your AI chat and start using it.
Skills themselves are free text files — you can download and use any skill in this list at no cost. You do need an AI subscription (e.g., Claude Pro, GitHub Copilot) to run them, since skills are read and followed by the AI.
Every skill in this list is a public GitHub repository — you can read the full instructions before loading anything. Check the repo's stars, last update date, and README. Skills are plain text: there's no executable code that can run on your machine.
- awesome-claude-code - Curated list of skills and tools for Claude Code.
- awesome-design-md - Standards and tools for the DESIGN.md protocol.
- awesome-openclaw-skills - Open source agent skills for OpenClaw.
- awesome-mcp-servers - A collection of Model Context Protocol (MCP) servers.
Contributions are welcome. See CONTRIBUTING.md for full guidelines.
Quick summary:
- Follow the skill template structure
- Provide clear, actionable instructions
- Include working examples where appropriate
- Document trade-offs and potential issues
- Keep SKILL.md under 500 lines for optimal performance
- Verify that skills actually exist before adding them
Questions, partnership inquiries, or feedback about this project:
- LinkedIn: Hailey Cheng (Cheng Hei Lam)
- X / Twitter: @haileyhmt
- Email: haileycheng@proton.me
If you use these skill patterns in your research or project, please cite:
@misc{awesome-agent-skills,
author = {Hailey Cheng (Cheng Hei Lam)},
title = {Agent Skill Index},
year = {2026},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/heilcheng/awesome-agent-skills}}
}MIT License. See LICENSE file for details.


