Claude Skill
KimYx0207/Meta_Kim
Meta_Kim 是 AI 编码的治理层,提供元代理、工作流合约和元理论。规范配置位于 .claude/ 目录,并附带 Codex 和 OpenClaw 的配套资产。
概览
仓库信息
安装这个 Skill
npx --yes github:KimYx0207/Meta_Kim meta-kimRegistry 信息
npx --yes github:KimYx0207/Meta_Kim meta-kimgit clone https://github.com/KimYx0207/Meta_Kim.gitnpm install
项目简介
Meta_Kim 是 AI 辅助编码的治理层,提供元代理、工作流合约和元理论。其规范配置位于 .claude/ 目录中,并附带为 Codex 和 OpenClaw 生成的配套资产。
Governance layer for AI coding: meta agents, workflow contract, meta-theory; canonical in .claude/, with generated companion assets for Codex and OpenClaw.
要点
- AI 编码工作流的治理层
- 用于编排 AI 交互的元代理
- 定义结构化流程的工作流合约
- AI 行为的元理论框架
- 位于 .claude/ 目录中的规范配置
- 为 Codex 和 OpenClaw 生成的配套资产
使用场景
- 标准化 AI 编码助手的行为
- 管理多代理编码工作流
- 通过合约强制执行编码规范
- 与 Codex 和 OpenClaw 工具集成
- 为 AI 驱动的开发建立治理机制
README 摘要
<div align="center"> <h1 style="font-size: 6em; font-weight: 900; margin-bottom: 0.2em; letter-spacing: 0.1em;">元</h1> <p style="font-size: 1.2em; color: #7c3aed; font-weight: 600; margin-top: 0;">META_KIM</p> <p> Language: <a href="README.md">English</a> | <a href="README.zh-CN.md">简体中文</a> | <a href="README.ja-JP.md">日本語</a> | <a href="README.ko-KR.md">한국어</a> </p> <p> <img alt="Projection tiers" src="https://img.shields.io/badge/default-Claude%20Code%20%7C%20Codex%20%2B%20compat-OpenClaw%20%7C%20Cursor-111827"/> <img alt="Candidate compatibility probes" src="https://img.shields.io/badge/candidate-Qoder%20%7C%20Trae%20%7C%20Kiro%20%7C%20Cascade%20%7C%20Cline%20%7C%20Roo%20%7C%20Continue-475569"/> <img alt="Stars" src="https://img.shields.io/github/stars/KimYx0207/Meta_Kim?style=flat&logo=github"/> <img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-green"/> </p> <p> <img alt="Meta_Kim turns chaotic AI coding into governed execution" src="docs/images/meta-kim-social-card.png" width="100%"/> </p> </div> ## Overview **Meta_Kim** is not another AI coding tool. It is a governance layer for durable AI coding work. The hard part of AI coding is no longer getting a model to change files. The hard part is deciding what should happen first, which capability should own it, what evidence proves it worked, and how the lesson survives the next run. Claude Code, Codex, OpenClaw, and Cursor are all hands: they can write code and change files. But who decides which file to change first? Who reviews the result? Who fixes the problems that show up? And how do we make sure the same mistake does not repeat next time? Meta_Kim is built for that. It is the governance layer above the coding hands: a runnable set of agents, skills, contracts,
话题
暂无话题