alchaincyf

Darwin Skill

Name: Darwin Skill
Author: alchaincyf

Testing community

SOURCE https://github.com/alchaincyf/darwin-skill

Description

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.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

**[English](README_EN.md)** | 中文

![达尔文.skill](assets/banner.svg)

Darwin Skill Animation
动画由 huashu-design skill 制作

达尔文.skill 2.0

**像训练模型一样优化你的 Agent Skills。**

受 [Andrej Karpathy 的 autoresearch](https://github.com/karpathy/autoresearch) 启发，将自主实验循环从模型训练搬到 Skill 优化领域。一个只能向前转的棘轮。

**v2.0** · 更新于 2026-05-28 · 吸收微软研究院 [SkillLens](https://arxiv.org/abs/2605.23899) 与 [SkillOpt](https://arxiv.org/abs/2605.23904) 两篇论文做的系统性升级。

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![Version](https://img.shields.io/badge/version-2.0-blue.svg)](#whats-new-in-20) [![Agent Skill](https://img.shields.io/badge/Agent%20Skill-Compatible-blueviolet)](https://skills.sh) [![Skills](https://img.shields.io/badge/skills.sh-Compatible-green)](https://skills.sh) [![Microsoft SkillOpt](https://img.shields.io/badge/Microsoft_SkillOpt-Listed_Integration-0078D4?logo=microsoft&logoColor=white)](https://github.com/microsoft/SkillOpt)

npx skills add alchaincyf/darwin-skill

[!NOTE] **🤝 微软研究院把达尔文列进了 SkillOpt 的官方集成名单。** 2026-06-03，微软在 [SkillOpt 仓库](https://github.com/microsoft/SkillOpt) 的更新里写道： *「gbrain, gbrain-evals, and **darwin-skill** have all integrated SkillOpt.」* 我们吸收了它的 validation-gated 框架，它把达尔文写进了自己的集成名单。这是一次双向的致意。👉 [去 SkillOpt 仓库看看](https://github.com/microsoft/SkillOpt)

What's New in 2.0

2.0 不是缝缝补补，是系统性吸收微软研究院 2026-05-22 两篇论文后的结构性升级。五个变化：

**1. 评分标准 8 维 → 9 维**（吸收 [SkillLens](https://arxiv.org/abs/2605.23899) 实证的 73.8% rubric 药方）

原「错误处理」维度升级为 失败模式编码 (Failure Mechanism Encoding)：不只是「告诉 agent 别犯错」，而是把已知失败路径显式编码进 skill
原「明确性」维度升级为 可执行具体性 (Actionable Specificity)：明文禁止「建议/可以考虑/根据情况/灵活把握/视情况而定」等模糊词
新增第九维 高风险行动黑名单 (High-Risk Action Blacklist)：rm/git reset --hard/force push 等破坏性操作必须在 skill 中显式列禁

**2. 验证机制对齐 SkillO

Darwin Skill

Description

Installation

README

达尔文.skill 2.0

What's New in 2.0

Related Skills

Spec Kit

Webapp Testing

#29

Fix Issue

Pypict Test Design

gstack