alchaincyf /
darwin-skill
达尔文.skill —— 一个让你的Skill无限进化的系统：评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.
Updated 1 h ago
+96 stars gained this week
Stars gained each day, last 30 days
Usual pace · 22 / day
Oct 10Oct 25
This week Before Usual pace
In short
An autonomous optimization loop for Claude Code agent skills that evaluates a SKILL.md, improves it, tests it, and keeps or reverts each change. Aimed at developers who author and refine agent skills.
Summary written by AI from the repository’s description and README.
What this repo contains
- Skills
- 1 SKILL.md file
- Scripts
- 1 in skill folders JavaScript 1
- Its README
- Asks you to install software (npm -g, pip, brew…)
No executables, hook files or MCP settings.
Read from the repository's files and README: facts to check on GitHub, not a review.
alchaincyf / darwin-skill
View on GitHub(opens in new tab)