My Custom Skill【免费下载链接】ruflo The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated项目地址: https://gitcode.com/GitHub_Trending/cl/rufloInstructions for what this skill does...UsageInvoke with$my-skill若需要元数据按上面 3.1 的 frontmatter 模板补上 name 与 description含 Use when / Skip when并可选添加 ## Commands命令 示例、## Scripts、## References、## Best Practices 段落再在 [config.toml](https://link.gitcode.com/i/e82ebb2dbe07b59188afbb8f878277cf) 中以 [[skills.config]] 启用。 ## 四、生成与校验.agents 文件从何而来 从源码结构看.agents/ 目录并非手写维护而是由仓库内的 claude-flow/codex 适配器包生成[v3/claude-flow/codex/src/](https://link.gitcode.com/i/1312e275d369b3621c42f7b848d74d2a) 下存在专门的生成器模块generators/ 目录中的 config-toml.ts、skill-md.ts、agents-md.ts由 initializer.ts 中的 CodexInitializer / initializeCodexProject 统一调用并有 tests/generators.test.ts、tests/initializer.test.ts 等测试用例保障行为。其对外入口命令为 bash # Codex 专用初始化推荐 npx ruflolatest init --codex # 全量技能安装 npx ruflolatest init --codex --full # 双平台模式同时生成 CLAUDE.md 与 AGENTS.md npx ruflolatest init --dual【免费下载链接】ruflo The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated项目地址: https://gitcode.com/GitHub_Trending/cl/ruflo创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考