🎯 Awesome Agent Skills

💡 What Are Agent Skills?

Agent Skills mark a fundamental shift from monolithic AI systems to composable agent architectures. Rather than embedding capabilities through expensive fine-tuning or bloating context windows with static documentation, skills provide modular, on-demand knowledge injection through standardized SKILL.md packages.

The Architecture

Progressive Disclosure at Scale: Skills leverage a three-tier context management strategy:

1. Discovery (~50 tokens): Lightweight metadata (name + description) loads at startup
2. Activation (~2-5K tokens): Full SKILL.md instructions load when task-relevant
3. Execution: Referenced scripts and resources accessed dynamically

This architecture delivers:

• 🧠 Infinite capability scaling - No context window trade-offs
• ⚡ Sub-second skill loading - Zero startup latency penalty
• 🔄 Cross-platform portability - Write once, deploy to any compatible agent
• 📦 Frictionless distribution - Share via Git, install like packages

The Revolution

From specialized agents to universal platforms: Instead of building separate coding agents, research agents, and analysis agents, the industry is converging on general-purpose agents with skill libraries. One agent. Unlimited specializations. Dynamic composition.

"We used to think agents in different domains will look very different. The agent underneath is actually more universal than we thought."
— Barry Zhang, Anthropic Research

The open standard advantage: Major platforms (OpenAI, GitHub, Microsoft, Cursor) have adopted the Agent Skills specification, creating network effects: every skill you create works across the entire ecosystem. This is the npm moment for AI agents.

🏷️ Key Topics

agent-skills · ai-agents · claude-code · gemini-cli ·codex · skill-md · progressive-disclosure · context-management · ai-development · mcp · agent-architecture · agentic-ai · automation · productivity

👉 New to Agent Skills? Start here: agentskills.io

📚 What's Inside?

• Start Here - Introduction to the concepts
• Phase 1: Learn the Fundamentals - Articles and videos to get started
• Phase 2: Use Existing Skills - Platforms and ready-to-use libraries
• Phase 3: Build & Integrate - Create your own skills and tools
• Phase 4: Master & Research - Advanced engineering and theory
• Frequently Asked Questions - Common questions answered
• Community & Contributing - Join the movement

🏁 Start Here

New to Agent Skills? These resources will take you from zero to understanding the core concepts in minutes.

🎓 Getting Started

• What are skills? - Perfect introduction for beginners
• Using skills in Claude - Quick start guide
• Agent Skills Review - 25-second feature highlight

🎓 Phase 1: Learn the Fundamentals

Understand the "Why" and "How". Before diving into code, grasp the architectural shift and best practices.

📰 Key Concepts & Articles

• Equipping agents for the real world with Agent Skills - The original announcement from Anthropic Engineering
• Agent Skills Explained: Why This Changes Everything - 17-minute analysis of why Skills matter for AI development
• Claude Skills vs MCP: Complete Guide - Comparison of Skills and Model Context Protocol architectures
• The Great AI Agent Configuration Confusion - Understanding configuration standards (SKILL.md, AGENTS.md)
• Using skills with Deep Agents - How generalist agents use skills for efficiency

🎬 Video Introductions

• Don’t Build Agents, Build Skills Instead (Anthropic) - Why “skills” are the scalable abstraction for agent capability
• A better way to build agents? Claude Agent Skills Tutorial + Demo - 11-minute intro: Is Agent Skills the next big standard after MCP?
• Claude's new 'Agent Skills' - 1-minute quick overview - installable "mini-brains"
• Claude Code Skills just Built me an AI Agent Team (2026 Guide) - 27-minute beginner guide to building general AI agents

🛠️ Phase 2: Use Existing Skills

Experience the power. Don't build from scratch—leverage the ecosystem of platforms and pre-built libraries.

🎨 Supported Platforms & IDEs

Where can you use Agent Skills today?

• Claude Code - Anthropic's coding tool with first-class skills support (docs)
• OpenAI Codex - OpenAI's CLI agent with Agent Skills support (docs)
• Gemini CLI - Google's solution for bringing Gemini into the terminal (docs)
• Cursor - AI-powered code editor with native skills integration (docs)
• VS Code - Microsoft's editor with Agent Skills in Insiders build (docs)
• GitHub Copilot - GitHub's AI coding assistant with Agent Skills support (docs)
• OpenCode - AI development tool with built-in Agent Skills support (docs)
• Amp - Next-gen AI coding assistant (docs)
• Goose - Open source AI agent framework (docs)
• Letta - Build stateful LLM agents with memory (docs)

📦 Ready-to-Use Skill Libraries

Tap into battle-tested capabilities.

🔥 Top Picks

• Official collection from Anthropic (document editing, data analysis, etc.)
• Official collection from OpenAI (Codex skills catalog)
• Official collection from Hugging Face (compatible with Claude, Codex, Gemini)
• 50+ verified skills for Claude Code and Claude.ai
• Skills for specialized capabilities

📂 More Collections

• Multi-agent collaboration skills
• Pydantic AI integration
• Skills for DSPy framework
• Document editing, data analysis, and project management
• Curated Claude Agent Skills collection
• Freeact agent library skills

🏪 Skill Marketplaces

• SkillsMP - Agent Skills marketplace for Claude Code/Codex (discover, install, and share skills)
• Skillstore - Curated, security-audited Agent Skills marketplace for Claude Code and Codex

🏗️ Phase 3: Build & Integrate

Create your own. Learn to author SKILL.md files and integrate them into your workflows.

📝 How to Build Skills

• How to create custom skills - Step-by-step authoring guide
• Skills API Quickstart - Technical documentation
• How I Built Agent Skills for Claude Code - 8-minute tutorial on building custom Agent Skills from scratch
• Claude Agent Skills Tutorial - Comprehensive implementation tutorial with SKILL.md format

🔧 Developer Tools

Frameworks and utilities for building and loading skills.

• LangChain Multi-Agent Skills - Official documentation on implementing the skills pattern in LangChain
• [SkillCheck](https://github.com/agen