Our take
Newless than six months old and changing fast- Activity
- 66
- Community
- 8
- Issues
- 47
- Pull requests
- 21
- Fewer contributors than 86% of the projects we track
This is a young, actively changing discovery list, but its single-contributor concentration and undocumented vetting process make it a starting point for research rather than a quality guarantee.
Good fit if
- You want a frequently refreshed index of GitHub projects related to AI agent skills.
- You are comfortable checking a listed repository's code, maintenance, and suitability yourself.
- You want to contribute a data-source issue or table suggestion to a small project.
Look elsewhere if
- You need a documented, reproducible quality-rating or validation process before choosing skills.
- You need a skill installer, runtime, or integration layer rather than a directory.
- You want a project with broader maintainer participation or an established release history.
All health signals
| Last commit | 2026-10-14 (today) |
|---|---|
| Commits, last 90 days | 100+ |
| Releases, last 12 months | 1 (latest v0.1.0, 2026-05-24) |
| Contributors | 2 (top contributor: 100% of commits) |
| Issues closed, last 90 days | 1 |
| Pull requests merged, last 90 days | 0 |
| Project age | 5 months |
Checked on 2026-10-14 with the GitHub API.
Overview
awesome-agent-skills maintains a searchable-in-practice directory of GitHub repositories related to AI agent skills. Its scheduled tracker queries GitHub Search, compares results with a saved snapshot, and updates the README table when items change.
It is aimed at developers exploring the agent-skill ecosystem, rather than teams looking for a skill runtime or installation manager. The README describes items as vetted and quality-rated, but does not document a rating or testing process; the visible table primarily shows repository metadata.
Key Features
- Refreshes the tracked repository list on a 15-minute schedule using GitHub Actions.
- Uses GitHub Search API results as its data source.
- Compares new results with a stored snapshot in
data/items.json. - Rewrites the README table between tracker markers when the data changes.
- Commits updates only when the tracked data has changed.
- Provides translated README versions in several languages.
- Links to related trackers maintained by the same author.
Use Cases
- An AI tooling developer can scan recently updated repositories when researching agent-skill formats or integrations.
- A team evaluating the ecosystem can use the directory as a starting point, then inspect candidate repositories directly before adoption.
- A maintainer tracking agent tooling can monitor additions and removals without manually refreshing a static list.
- A contributor can open an issue to report a data-source problem or suggest a change to the table.
What you need
Detected in the repository
- Python (from requirements.txt)
- Automated checks on GitHub Actions
Getting Started
Open the README and browse the current-items table. For details on contributing or the tracker implementation, consult the repository documentation and source files.
License in Plain Words
No standard license was detected. Without a license, the default copyright rules apply: you may read the code, but not reuse it. Check the repository or ask the authors.
Alternatives
- awesome-agent-skills: It curates skills by provider and task for several coding agents, rather than refreshing a repository-discovery list every 15 minutes.
- awesome-agent-skills: It catalogs skills alongside plugins, rules, and tools across agent ecosystems, rather than focusing on a frequently refreshed list of skill repositories.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| awesome-agent-skills | Python | – | 39 | New |
| awesome-agent-skills | not specified | MIT | 35.2k | Active |
| awesome-agent-skills | TypeScript | CC0-1.0 | 20 | Active |
Considerations
The project is less than six months old and changing quickly. Although it has recent commits and a release, nearly all contributions are concentrated in one person, and there have been no merged pull requests in the measured recent period. The repository has CI configured but no tests are reported, so the tracker’s behavior is not backed by a test suite in the supplied project data.
The README explains the search-and-diff update flow, but does not specify what makes an entry vetted or how quality ratings are calculated. The table should therefore be treated as a discovery aid, not an independent endorsement. The README states that the project is MIT-licensed; check the included license file for the terms before reuse.
Found this useful?
Share it with someone who would like awesome-agent-skills.