darwin-skill
Skill146 starsChanged 51 days agoNo licenceView on GitHub
Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch. Evaluates SKILL.md files using an 8-dimension rubric (structure + effectiveness), runs hill-climbing with git version control, validates improvements through test prompts, 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\".
15 other projects use a version of this, 14 of them edited.
Adopted by
Most recently taken up by
- cjh-solver/MathModeling-Skills-Arsenaledited, first seen Nov 8, 2026
- joe-qai/qa-skillsedited, first seen Nov 8, 2026
- iasiv5/skillsedited, first seen Nov 1, 2026
- hua695/MathModeling-Skills-Arsenaledited, first seen Oct 25, 2026
- kingxiaozhe/cm-workflowedited, first seen Oct 20, 2026
- michoney/hermes-skillsedited, first seen Oct 17, 2026
Used with
Projects with it also use humanizer-zh.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
huangservaSkillhumanizer-zh
Also in 3 projects that use this
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 14
- alchaincyf/darwin-skill★ 6.1k28% same
- kingxiaozhe/cm-workflow★ 9737% same
- joe-qai/qa-skills★ 3057% same
- ChouChiu/heya-skill★ 2037% same
- cjh-solver/MathModeling-Skills-Arsenal★ 1479% same
- hua695/MathModeling-Skills-Arsenal★ 1279% same
- liumeixin/hermes-skills★ 457% same
- michoney/hermes-skills★ 429% same
- iasiv5/skills★ 328% same
- xigua0626/darwin-skill-public★ 338% same
4 more not listed
Wrote their own version · 1
- leishifu666/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository41 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- android-native-devSkill
- book2skillSkill
- exp-reflectSkill
- exp-searchSkill
- exp-writeSkill
- find-skillsSkill
- frontend-devSkill
- fullstack-devSkill
- gif-sticker-makerSkill
- git-workSkill
- guizang-ppt-skillSkill
- html-reportSkill
- huashu-designSkill
- intent-confirmationSkill
- ios-application-devSkill
- loop-designSkill
- mao-zedong-perspectiveSkill
- huashu-nuwaSkill
- officecliSkill
- project-overviewSkill
- shader-devSkill
- skill-creatorSkill
- spec-branch-reviewSkill
- spec-debugSkill
- spec-endSkill
- spec-executeSkill
- spec-exploreSkill
- spec-initSkill
- spec-reviewSkill
- spec-startSkill
- spec-swarmSkill
- spec-testSkill
- spec-updateSkill
- spec-writeSkill
- token-efficiencySkill
- version-endSkill
- version-releaseSkill
- version-startSkill
- version-updateSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.