Great ming court
大明朝廷 v2.0 — 仿三省六部制的分层 AI Agent 调度架构
npx -y skills add zhongyi67/great-ming-courtAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
大明朝廷 v2.0 — 仿三省六部制的分层 AI Agent 调度架构。三省(智库)→丞相(拆解派活)→六部(执行干活)→太子(对话皇上),4 个 agent 各司其职,完整轮转闭环。
SKILL.md
2.4 KB, 878 tokens by cl100k_base, as published. Nobody here has run it
大明朝廷 v2.0 🏯
仿三省六部制的分层 AI Agent 调度架构。
架构理念
皇上 👑
↓ 下旨
太子 🐉 (main)
↓ 判断大小事,小事自回,大事交丞相
丞相 🏛️ (chengxiang)
↓ 第一步:输出拆解方案
↓ 第二步:如需信息支撑,派 三省📚 搜集
↓ 第三步:派 六部⚒️ 干活
三省 📚 (sansheng)
↓ 只提供信息,不做判断,不干活
六部 ⚒️ (liubu)
↓ 干活 → 汇报产出给丞相
丞相 🏛️
↓ 审核 → 裁定通过/打回重做
↓ 打回连续2次(即打回1次后再次不通过) → 报太子处理
↓ 通过 → 汇总报太子
太子 🐉
↓ 汇总报皇上
皇上 👑
四个 Agent
| Agent | ID | 模型 | 角色 | 核心约束 |
|---|---|---|---|---|
| 🐉 太子 | main | DeepSeek V4 Flash | 皇上的唯一接口 | 不越级派活,不自己动手 |
| 🏛️ 丞相 | chengxiang | DeepSeek V4 Pro | 拆解/派活/协调/验收 | 三大铁律:不干活、不堵全局、先拆解 |
| 📚 三省 | sansheng | MiniMax M2.7 | 丞相智库,搜信息 | 只用 web_search/web_fetch/read |
| ⚒️ 六部 | liubu | DeepSeek V4 Pro | 唯一干活部门 | 写入限定工作区 |
流转路径
三省→丞相→六部 是核心流转路径:
- 丞相拆解任务,如需信息支撑先派三省搜集资料
- 三省返回资料后,丞相综合制定方案,派六部执行
- 六部产出后 auto-announce 回报丞相
- 丞相审核:通过→汇总上报,不通过→打回重做
- 连续 2 次(即打回1次后再次不通过)→上报太子
安装方式
方式一:一键安装
cd projects/great-ming-court
chmod +x install.sh
./install.sh
方式二:手动安装
- 将
config/agents.partial.json中的内容合并到~/.openclaw/openclaw.json的agents字段 - 将
agents/*.md复制到~/.openclaw/agents/{agent_id}/agent/目录 - 重启 Gateway:
openclaw gateway restart
依赖要求
- OpenClaw Gateway v2026.5+
- DeepSeek API Key(太子、丞相、六部)
- MiniMax API Key(三省)
- 飞书通道(可选)