
Agentic Awesome Skills
A local catalog of 2,800+ reusable instruction files that helps coding agents pick and review skills.
- Stars
- 49k
- Forks
- 7.1k
- Licence
- MIT
- Language
- Python
- Last update
- 4 days ago
- Type
- Dev tool
What it is
Agentic Awesome Skills is a library of installable SKILL.md playbooks, which are instruction files that AI coding agents such as Codex or Claude can read and follow. AAS Core is a local tool that lets the agent search the full catalog, record the skills it chooses, validate that selection, and preview a plan you can review before anything changes. According to the README, Core does not rank or recommend skills itself.
- Have Codex or Claude search the local catalog and save a chosen set of skill IDs as aas-stack.json
- Run aas stack validate to check a manifest's structure and identifiers
- Generate an immutable plan preview with aas stack plan for review
- Preview a direct install of named skills with a --dry-run flag before committing
Great for
- Developers using Codex or Claude who want agent-chosen instructions for a project
- Teams that want to review an exact, saved list of skills before installing them
- People who want a local, inspectable workflow instead of a hosted service
- Users comfortable editing config files and running npm or CLI commands
Not ideal for
- Non-technical users, since setup involves MCP configuration and terminal commands
- People who want the tool to recommend skills for them, because the README says Core does not rank or recommend
- Users who need apply or recovery features in production, since the README says these remain experimental and outside the supported preview
How to get it
- 1
Install with a package manager
You'll need: Node.js (npm exec is used; version not stated in the README excerpt) · Codex or Claude client
Configure the local MCP for Codex (preview; returns an approval digest)
npm exec --yes --ignore-scripts --package=agentic-awesome-skills@20.2.0 -- aas mcp configure \ --host codex \ --scope user \ --config /absolute/path/to/codex/config.toml \ --cache-root /absolute/path/to/aas-cachePreview a direct install of selected skills
npm exec --yes --ignore-scripts --package=agentic-awesome-skills@20.2.0 -- \ agentic-awesome-skills --release 20.2.0 --path .agents/skills \ --skills brainstorming,systematic-debugging --dry-run - 2
Run it
- Configure the local MCP for Codex or Claude using the command in the README, replacing the placeholder paths.
- Ask the agent to inspect your project and save the exact skill selection.
- Run aas stack validate on the saved manifest.
- Run aas stack plan and review the resulting preview before any installation.
- Optionally run the direct installer with --dry-run to preview installing named skills.
- 3
Get the most out of it
- Use the Workbench in the browser to review stack and plan artifacts without giving it filesystem access.
- Use the --dry-run flag on the direct installer to check results before running without it.
- Read the Core guide for tool contracts and capability coverage before relying on a specific workflow.
- Use the hosted catalog at aaskills.tech to browse skills outside the terminal.
Downloads
Strengths
- Covers the full catalog locally, so every listed skill can be searched and read
- Keeps a reviewable record of which skills were chosen and why, via manifests and plans
- Explicit dry-run and preview steps before changes are applied
Trade-offs
- The README says apply and recovery are experimental, and it warns that validation does not certify semantic fit or safety to apply
- Setup depends on the Codex or Claude guides and on the README tracking main, so some features may need a later release than the one you install
- The skill count differs across the README and metadata (2,750+, 2,877+), so check the current catalog yourself
How it compares
| Project | Stars | Type | Level | Updated | Best for |
|---|---|---|---|---|---|
| agentic-awesome-skills (this) | 49k | Dev tool | intermediate | 4 days ago | Developers using Codex or Claude who want agent-chosen instructions for a project |
| agents | 42.1k | Dev tool | beginner | 4 days ago | Developers who already use one of the listed AI coding tools and want ready-made specialist agents |
| ECC | 295k | Dev tool | intermediate | 4 days ago | Developers who already use Claude Code and want a shared workflow for planning, testing and review |
| Trail-Code | 11k | Dev tool | beginner | 4 days ago | Developers who use Claude Code, Cursor, Codex or similar agents on a medium or large repository |
| ponytail | 182k | AI model / agent | beginner | 8 days ago | Developers who use Claude Code or similar AI agents and find the generated code too long |
| khazix-skills | 21.8k | Curated list | beginner | 1 months ago | Developers already using Claude Code, Codex, or another Agent Skills-compatible agent who want ready-made skills |
Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.