agentsclimarketplace
Sign in

Great ming court

Skill zhongyi67/great-ming-court

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。From its SKILL.md

Install
npx -y skills add zhongyi67/great-ming-court

Assembled 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.

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

AgentID模型角色核心约束
🐉 太子mainDeepSeek V4 Flash皇上的唯一接口不越级派活，不自己动手
🏛️ 丞相chengxiangDeepSeek 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sanshengMiniMax M2.7丞相智库，搜信息只用 web_search/web_fetch/read
⚒️ 六部liubuDeepSeek 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：

  1. 丞相拆解任务，如需信息支撑先派三省搜集资料
  2. 三省返回资料后，丞相综合制定方案，派六部执行
  3. 六部产出后 auto-announce 回报丞相
  4. 丞相审核：通过→汇总上报，不通过→打回重做
  5. 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

  1. 将 config/agents.partial.json 中的内容合并到 ~/.openclaw/openclaw.json 的 agents 字段
  2. 将 agents/*.md 复制到 ~/.openclaw/agents/{agent_id}/agent/ 目录
  3. 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）

What ships with it: 10 files

45.7 KB alongside SKILL.md, 1 of them executable

agents/

config/

docs/

Gives 0 of the 12 instructions most legal skills give in 878 tokens

Counted across 234 of the 234 authors here whose files we hold, read 2026-08-07

  • Use text operators for text fieldsin 11 of 234, across 6 files
  • Consult qualified counsel before usein 11 of 234, across 3 files
  • Use PatentSearch API for patent searchesin 10 of 234, across 5 files
  • Confirm jurisdiction, employment type, and required clausesin 9 of 234, across 2 files
  • Choose a document template and tailor role-specific termsin 9 of 234, across 2 files
  • Validate compensation, benefits, and compliance requirementsin 9 of 234, across 2 files
  • Add signature, confidentiality, and IP assignment terms as neededin 9 of 234, across 2 files
  • Open the implementation playbook for detailed templatesin 9 of 234, across 2 files
  • Use TSDR for trademark data retrievalin 9 of 234, across 4 files
  • Ask for clarification if required inputs are missingin 8 of 234, across 2 files
  • Set the USPTO_API_KEY environment variablein 8 of 234, across 3 files
  • Use the uspto-opendata-python library for PEDSin 8 of 234, across 3 files

Said here and by no other author read

  • forward major tasks to the chengxiang agent
  • decompose tasks before assigning work
  • assign information gathering to sansheng agent
  • assign execution work to liubu agent
  • restrict sansheng agent to read-only tools
  • restrict liubu agent to the designated workspace

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.