head to head · open source
zeroshot vs claude-code-skills
zeroshot has 2,090 GitHub stars, 198 forks, 3 open issues and last shipped yesterday. claude-code-skills has 587 stars, 88 forks, 0 open issues and last shipped 8 days ago. zeroshot leads on adoption by 256% (2,090 vs 587 stars). zeroshot is written in Rust under MIT; claude-code-skills is written in Shell under MIT. zeroshot has attracted 9% as many forks as stars, claude-code-skills 15%. zeroshot was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 4 topic tags (ai-agents, claude-code, code-review, codex), so they are genuine substitutes rather than adjacent tools.
Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.
← all 20902 open source comparisons
Side by side
| zeroshot | claude-code-skills | |
|---|---|---|
| GitHub stars | ★ 2.1K | ★ 587 |
| License | MIT | MIT |
| Written in | Rust | Shell |
| Last push | 2026-11-02 | 2026-10-26 |
| Forks | ⑂ 198 | ⑂ 88 |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick zeroshot if
- You weight community size — 2.1K stars and counting
- You want the MIT license terms
- Your stack matches Rust
- You value the larger contributor base for long-term maintenance
pick claude-code-skills if
- You want the claude-code-skills feature set and don't need the biggest community
- You prefer the MIT license terms
- Your stack matches Shell
- You evaluated both and claude-code-skills fits your workflow better
About zeroshot
Zeroshot The agent that writes the code should not be the one that decides it works. Zeroshot turns a software goal into an explicit multi agent graph: one agent implements, independent agents review, failures go back to a bounded repair loop, and nothing is delivered until the graph's checks pass. The implementing agent never approves its own work. Use the built in graph or bring your own topology. Add reviewers, tests, and repair loops, then save the setup as a profile for the next task. Opcore works alongside it: Opcore checks each edit while an agent writes code, and Zeroshot has independent agents review…
read the full zeroshot overview →
About claude-code-skills
Claude Codex Skills Give your AI agent a clear finish line. You ask for a fix and get a new abstraction. A review lists generic advice. The agent says “done,” but you still have to work out what it checked. These skills give Claude Code and Codex a concrete way to finish the task: establish the intended outcome, work within scope, verify the result, and make remaining gaps explicit. Choose the skill for the problem in front of you. Project page · Install · Full catalog What changes in your workflow A clearer target. Turn an idea, bug report, or incident into an outcome the agent can check. Focused work. Reuse…
read the full claude-code-skills overview →
More in Developer Tools
Related comparisons
More Version Control & Collaboration projects
Compare either of these against the rest of the Version Control & Collaboration field.
Frequently asked questions
Is zeroshot or claude-code-skills more popular?
zeroshot has 2,090 GitHub stars and claude-code-skills has 587. zeroshot has the larger community by that measure.
Are zeroshot and claude-code-skills free?
Both are open source. zeroshot is licensed under MIT and claude-code-skills under MIT. Neither carries a licence fee.
What is the difference between zeroshot and claude-code-skills?
zeroshot is written in Rust and claude-code-skills in Shell. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.
Which should I choose, zeroshot or claude-code-skills?
Choose zeroshot if you want the larger community (2,090 stars) or its MIT licence terms. Choose claude-code-skills if its feature set, stack or MIT licence fits better. Both are self-hostable.