broaden: Claude Code Skill → Agent Skill, support Codex/OpenClaw/Trae/CodeBuddy

README.md

@@ -10,12 +10,12 @@
 
 # 达尔文.skill
 
-**像训练模型一样优化你的 Claude Code Skills。**
+**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。
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
-[![Claude Code](https://img.shields.io/badge/Claude%20Code-Skill-blueviolet)](https://claude.ai/code)
+[![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)
 
 ```
@@ -34,7 +34,7 @@ npx skills add alchaincyf/darwin-skill
 
 ## 为什么做这个
 
-Claude Code 的 Skill 生态在快速扩张。当你有 10 个 Skills 时可以手动维护；当你有 60+ 个 Skills 时，你需要一个系统。
+Agent Skill 生态在快速扩张。Claude Code、Codex、OpenClaw、Trae、CodeBuddy 等工具都支持 SKILL.md 格式。当你有 10 个 Skills 时可以手动维护；当你有 60+ 个 Skills 时，你需要一个系统。
 
 传统的 Skill 审查是**纯结构性的**：检查格式对不对、步骤有没有编号、路径能不能访问。但一个格式完美的 Skill，跑出来的效果可能很差。
 
@@ -114,7 +114,7 @@ Claude Code 的 Skill 生态在快速扩张。当你有 10 个 Skills 时可以
 npx skills add alchaincyf/darwin-skill
 ```
 
-安装后在 Claude Code 里说「优化所有skills」或「优化某个skill」就行。
+安装后在任何支持 Skill 的 Agent 工具中说「优化所有skills」或「优化某个skill」就行。
 
 无法访问 GitHub 的朋友，可以直接下载 zip 包：[darwin-skill.zip](https://pub-161ae4b5ed0644c4a43b5c6412287e03.r2.dev/skills/darwin-skill.zip)，解压后把 SKILL.md 放到 `~/.claude/skills/darwin-skill/` 目录即可。
 

README_EN.md

@@ -10,12 +10,12 @@ English | **[中文](README.md)**
 
 # darwin.skill
 
-**Optimize your Claude Code Skills the way you train models.**
+**Optimize your Agent Skills the way you train models.**
 
 Inspired by [Karpathy's autoresearch](https://github.com/karpathy/autoresearch). Autonomous experiment loops, applied to skill optimization. A ratchet that only turns forward.
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
-[![Claude Code](https://img.shields.io/badge/Claude%20Code-Skill-blueviolet)](https://claude.ai/code)
+[![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)
 
 ```
@@ -36,7 +36,7 @@ Evaluate → Improve → Test → Human Confirm → Keep or Revert. Repeat.
 
 ## Why This Exists
 
-When you have 10 skills, you can maintain them by hand. When you have 60+, you need a system.
+Agent skill ecosystems are expanding fast. Claude Code, Codex, OpenClaw, Trae, CodeBuddy and more all support the SKILL.md format. When you have 10 skills, you can maintain them by hand. When you have 60+, you need a system.
 
 Traditional skill review is purely structural: does the frontmatter look right? Are the steps numbered? Do the file paths exist? But a perfectly formatted skill can still produce terrible output.
 
@@ -116,7 +116,7 @@ Round 2 scored 75, below the current best of 78. Auto-reverted. Effective baseli
 npx skills add alchaincyf/darwin-skill
 ```
 
-After installation, tell Claude Code: "optimize all skills" or "optimize [skill-name]".
+After installation, tell your agent: "optimize all skills" or "optimize [skill-name]". Works with any tool that supports the SKILL.md format.
 
 Can't access GitHub? Download the zip: [darwin-skill.zip](https://pub-161ae4b5ed0644c4a43b5c6412287e03.r2.dev/skills/darwin-skill.zip). Extract and place SKILL.md in `~/.claude/skills/darwin-skill/`.