heilcheng/awesome-agent-skills

Tutorials, Guides and Agent Skills Directories

awesome-agent-skills — What It Is

awesome-agent-skills is a community-curated directory of Agent Skills — small text files that teach AI assistants (like Claude, Copilot, or Codex) how to do specific tasks on demand, without retraining the AI. Think of them as recipe cards for AI: instead of the AI memorizing everything upfront, it reads the right card when needed.

What the Project Does

  • Collects real-world skills: Unlike bulk-generated skill lists, this project focuses on skills actually created and used by engineering teams.
  • Organizes them by category: Official skills from companies like Anthropic, OpenAI, Google, Hugging Face, Cloudflare, and more, plus community-contributed skills.
  • Makes them easy to find: You can browse the directory on GitHub or the live website at agent-skill.co.

How Skills Work

A skill is a simple text file (called SKILL.md) that loads in three stages:

  1. Browse — The AI sees a list of available skills (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.

Skills are instructions, not code — the AI reads them like a human reads a guide, then follows the steps.

Quick Start (30 seconds)

  1. Pick a skill from the directory or agent-skill.co.
  2. Load it into your AI agent — e.g., for Claude Code: /skills add <github-url>; for Claude.ai: paste the raw SKILL.md URL; for Codex/Copilot: follow platform docs.
  3. Ask your AI to use it — just describe what you want in plain English.

No installation, no configuration, no coding required.

Why It 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 (Claude Code, Codex, GitHub Copilot, Gemini CLI, Cursor, Windsurf, and more).
  • Easy to share: Skills are just files you can copy, download, or share on GitHub.

What's Inside the README

  • Official Skill Directories — Skills by Anthropic (docx, pptx, pdf, canvas-design, etc.), OpenAI/Codex (cloudflare-deploy, imagegen, playwright, etc.), Google Gemini, Hugging Face, Replicate, fal.ai, MiniMax, Bria AI, Cloudflare, Netlify, Vercel, HashiCorp, Neon, ClickHouse, Supabase, and more.
  • Community Skills — Categorized into vector databases, data & analytics, marketing, career, productivity, development, security, creative, writing, and more.
  • Finding Skills — Recommended tools: SkillsMP Marketplace (auto-indexes GitHub skill projects), skills.sh (Vercel's leaderboard), and the npx skills CLI tool for searching, installing, and managing skills.
  • Skill Quality Standards — Guidelines for what makes a good skill.
  • Using & Creating Skills — How to load skills into different agents and how to write your own.
  • Trends & Capabilities (2026) — Forward-looking section on where agent skills are heading.
  • FAQ, Contributing, Contact, License — Standard project documentation.

Project Details

  • Maintainer: Hailey Cheng (Cheng Hei Lam)
  • Website: agent-skill.co
  • Languages: README available in English, Traditional Chinese, Simplified Chinese, Japanese, Korean, and Spanish.
  • License: Referenced in the README's License section (not detailed in the excerpt).

Key Takeaway

This project is essentially a curated library of AI "how-to" guides — a place where you can find, evaluate, and use skills that teach AI assistants new abilities, without needing to retrain or code anything.

Related

  • Project
    KunAgent/Kun

    Kun is a local‑first AI desktop workspace that merges code editing, document management, and chat‑style agents into one Electron app. All data stays on your computer; you connect any OpenAI‑compatible, Anthropic‑compatible, or local model (e.g., Ollama, DeepSeek). Features include project‑wide code assistance, a research‑paper workspace, extensible plugins, and a terminal UI. It’s aimed at developers and researchers who want AI‑augmented productivity without cloud‑side data storage, and it’s released under a non‑commercial PolyForm license.

  • Project
    Eigenwise/atomic-agents

    Atomic Agents is a Python library for building modular, type‑safe LLM agents. It uses Pydantic schemas, system‑prompt generators, and plug‑in context providers to let developers compose small, reusable components (agents, tools, context providers) into chatbots, RAG systems, web‑search assistants, etc. A CLI (Atomic Forge) supplies ready‑made tools, and the package works with OpenAI and other providers via the Instructor SDK.

  • Project
    aisingapore/TagUI

    An open-source robotic process automation (RPA) tool that lets users automate web, desktop, and command-line tasks using a simple, natural-language syntax.

  • Project
    Sylinko/Everywhere

    Everywhere is a cross‑platform desktop AI assistant (Windows/macOS) built with .NET 10 and Avalonia. It captures on‑screen context via accessibility APIs and lets you query LLMs (OpenAI, Anthropic, Gemini, etc.) through a global hot‑key, returning markdown‑rich answers. Features include browser/file/terminal agents, rich UI, multi‑language UI, and support for local Ollama models. The project is open source under its LICENSE and provides installers, a portable zip, and full build instructions.