Skip to content

heilcheng/awesome-agent-skills

Repository files navigation

Agent Skill Index

English | 繁體中文 | 简体中文 | 日本語 | 한국어 | Español

Agent Skill Index Banner

🌐 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.


Quick Start (30 seconds)

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.


Table of Contents


What Are Agent Skills?

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.

How It Works

Skills load in three stages:

  1. Browse: The AI sees a list of available skills (just names and short descriptions)
  2. Load: When a skill is needed, the AI reads the full instructions
  3. Use: The AI follows the instructions and accesses any helper files

Why This Matters

  • 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.


How to Find Skills (Recommended)

SkillsMP Marketplace

SkillsMP Marketplace

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.

skills.sh Leaderboard by Vercel

skills.sh Leaderboard

You can also use skills.sh — Vercel's leaderboard — to intuitively view the most popular Skills repositories and individual Skill usage statistics.

npx skills CLI Tool

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

Compatible Agents

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 Skill Directories

AI Platforms & Models

Skills by Anthropic

Official built-in skills for common document types and creative workflows.

Skills by OpenAI (Codex)

Official curated skills from OpenAI's catalog.

Skills by Google Gemini

Install via google-gemini/gemini-api-dev.

Skills by Hugging Face

Official skills for ML workflows.

Skills by Replicate

Skills by fal.ai

Skills by MiniMax

Cloud & Infrastructure

Skills by Cloudflare

Skills by Netlify

Skills by Vercel

Skills by HashiCorp (Terraform)

Skills by Neon

Skill by ClickHouse

Skills by Supabase

Skills by Tinybird


Developer Tools & Frameworks

Skills by VoltAgent

Skills by CallStack

Skills by Expo

Skills by Remotion

Skills by DuckDB

Skills by GSAP (GreenSock)

Skills by WordPress

Skills by Figma


Google Ecosystem

Skills by Google Labs (Stitch)

Skills by Google Workspace CLI


Business, Productivity & Marketing

Skills by Stripe

Skills by Courier

Skills by Typefully

Skills by Composio

Skills by Notion

Skills by Resend

Skills by Sanity

Skills by Better Auth

Marketing Skills by Corey Haines

Comprehensive SaaS marketing stack skills by Corey Haines.

Product Manager Skills by Dean Peters

46 battle-tested PM skills by Dean Peters.

Product Management Skills by Pawel Huryn

65 PM skills by Paweł Huryn, creator of The Product Compass.

Skills by Garry Tan (gstack)

28 engineering leadership skills by Garry Tan.


Security & Web Intelligence

Skills by Trail of Bits

Skills by Sentry

Skills by Firecrawl

Skills by Microsoft

133 domain-specific skills for Azure SDK and Microsoft AI Foundry.

Skills by Binance

Skills by Sanity

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

Skills by Better Auth

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

Marketing Skills by Corey Haines

Skill Description
agent-gtm-skills 18 go-to-market skills: pricing, outbound, SEO, ads, retention, and ops

Product Manager Skills by Dean Peters

Skill Description
pm-skills 24 product management skills covering discovery, definition, delivery, and optimization

Product Management Skills by Pawel Huryn

Skill Description
pm-skills-huryn Advanced product management frameworks, OKRs, and strategy skills

Skills by Garry Tan (gstack)

Skill Description
gstack YC founder stack recommendations for infra, tooling, and deployment

Security & Web Intelligence

Skills by Trail of Bits

Skill Description
safe-encryption-skill Modern encryption alternative to GPG/PGP with post-quantum support
threat-hunting Hunt for threats using Sigma detection rules

Skills by Sentry

Install from getsentry/skills.

Skill Description
sentry-skills Debug errors, performance issues, and traces directly with Sentry integration

Skills by Firecrawl

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

Skills by Microsoft

Install from microsoft/agent-skills.

Skill Description
agent-skills Official Microsoft agent skills collection

Skills by Binance

Skill Description
kyberswap-skills Token swap quotes and transactions across 18 EVM chains

Community Skills

Vector Databases
  • qdrant/skills - Agent skills for Qdrant vector search, scaling, and performance
Marketing
Productivity and Collaboration
Development and Testing
Context Engineering

Skill Quality Standards

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

Using Skills

Using Skills in Claude.ai

  1. Click the skill icon in your chat interface.
  2. Add skills from the marketplace or upload custom skills.
  3. Claude automatically activates relevant skills based on your task.

Using Skills in Google Antigravity

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.

Using Skills in Claude Code

mkdir -p ~/.claude/skills/
cp -r skill-name ~/.claude/skills/

Verify skill metadata:

head ~/.claude/skills/skill-name/SKILL.md

The skill loads automatically and activates when relevant.

Using Skills in Codex

Use the built-in $skill-creator skill in Codex. Or install manually:

$skill-installer linear

Restart Codex after installing a skill to pick it up.

Using Skills in VS Code / GitHub Copilot

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 spaces
  • description (required): What the skill does and when the agent should use it
  • Markdown body with instructions, examples, and guidelines

Using MCP Servers (Claude Desktop)

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"]
    }
  }
}

Creating Skills

Skills are instruction bundles that tell the agent how to perform specific tasks. They are not executable code.

Skill Structure

skill-name/
├── SKILL.md          # Required: Instructions and metadata
├── scripts/          # Optional: Helper scripts
├── templates/        # Optional: Document templates
└── resources/        # Optional: Reference files

Basic SKILL.md Template

---
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]

MCP Server Example (Python)

For skills that need to connect to external data sources:

pip install fastmcp
from 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()

Official Tutorials and Guides

Claude and Anthropic

GitHub Copilot

Model Context Protocol (MCP)



Trends & Capabilities (2026)

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."

1. Autonomous Execution

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.

2. Multi-Agent Orchestration

Complex tasks are managed by specialized agent teams (documentation, testing, coding) coordinated by "manager" agents that synthesize deliverables and resolve conflicts.

3. Agentic IDEs

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.

4. Domain-Specific Skills at Scale

Organizations are moving from general-purpose prompting to highly specialized skills for each platform and workflow — reducing hallucinations and improving reliability in production deployments.


Frequently Asked Questions

What are Agent Skills?

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.

How are Agent Skills different from fine-tuning?

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.

What's the difference between Agent Skills and MCP?

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)

Which AI tools support Agent Skills?

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.

Do Agent Skills run code?

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.

How do I create my first Agent Skill?

  1. Create a SKILL.md file with a name and description at the top
  2. Write clear, step-by-step instructions in the file
  3. Put it in your .github/skills/ or .claude/skills/ folder
  4. Test it out!

Full guide: How to create custom skills

I'm not a developer — can I still use 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.

Are skills free?

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.

How do I know if a skill is safe to use?

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.

Related Awesome Lists


Contributing

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

Contact

Questions, partnership inquiries, or feedback about this project:


Citation

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}}
}

License

MIT License. See LICENSE file for details.