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.

Stars: 6.9k
Skills: 1
License: MIT
Last commit: Sep 18, 2026

install.sh

# every skill in this repo, via the skills CLI

npx skills add alchaincyf/darwin-skill

# or, for Claude Code, copy one skill folder into

~/.claude/skills/ (all projects)

.claude/skills/ (this project)

View alchaincyf/darwin-skill on GitHub

Inside this pack

1 skill in darwin-skill

Each skill is a SKILL.md file your agent loads when a task matches its description.

01
darwin-skill
Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt (arXiv 2605.23904) validation-gated design + human-in-the-loop checkpoints. Evaluates SKILL.md files using a 9-dimension rubric (structure + effectiveness + meta-skill blacklists), runs hill-climbing with git version control, spawns independent judge agents for blind evaluation, validates improvements through test prompts with auto-break on diminishing returns, and generates visual result cards. Use when user mentions \"优化skill\", \"skill评分\", \"自动优化\", \"auto optimize\", \"skill质量检查\", \"达尔文\", \"darwin\", \"帮我改改skill\", \"skill怎么样\", \"提升skill质量\", \"skill review\", \"skill打分\".
Preview SKILL.md