← Back to Skills Marketplace
689
Downloads
3
Stars
4
Active Installs
13
Versions
Install in OpenClaw
/install ai-court
Description
以明朝内阁制为蓝本的多 Agent 协作系统 - 一键部署你的 AI 朝廷
README (SKILL.md)
AI 朝廷 · 多 Agent 协作系统
一行命令起王朝，三省六部皆 AI。
以中国古代三省六部制为蓝本，用 OpenClaw 框架构建的多 Agent 协作系统。 一台服务器 + OpenClaw = 一支 7×24 在线的 AI 协作团队。
📦 技能信息
| 项目 | 说明 |
|---|---|
| 名称 | AI 朝廷 (AI Court) |
| 版本 | 2.1.0 |
| 作者 | 菠萝王朝团队 |
| License | MIT |
| 类型 | 多 Agent 协作框架 |
🏛️ 核心特性
三种制度可选
| 制度 | Bot 数量 | 核心角色 | 适用场景 |
|---|---|---|---|
| 明朝内阁制 | 1-9 Bot | 司礼监/内阁/六部 | 传统层级管理 |
| 唐朝三省制 | 1-11 Bot | 三省/御史台/六部 | 分权制衡管理 |
| 现代企业制 | 1-9 Bot | CEO/Board/CxO | 现代企业管理 |
灵活配置模板
| 模板 | Bot 数量 | 适用场景 |
|---|---|---|
| 1 Bot | 1 | 个人开发者/快速部署 |
| 3 Bot | 3 | 小团队⭐推荐 |
| 5 Bot | 5 | 中型团队 |
| 9/11 Bot | 9-11 | 大型团队/完整功能 |
多平台支持
| 平台 | 适用地区 | 优势 |
|---|---|---|
| 飞书 | 中国大陆 | 无需翻墙、WebSocket 长连接 |
| Discord | 国际 | 功能强大、机器人生态好 |
📋 制度详情
明朝内阁制（9 Bot）
以中国古代政治制度为蓝本，司礼监秉笔太监调度，内阁优化 Prompt，六部分工执行。
| Bot | 职责 | 推荐度 |
|---|---|---|
| 司礼监 | 调度中心/接旨派活 | ⭐⭐⭐ 必需 |
| 内阁 | Prompt 优化/计划生成 | ⭐⭐⭐ 必需 |
| 都察院 | 代码审查/质量监督 | ⭐⭐ 推荐 |
| 兵部 | 编码开发/技术实现 | ⭐⭐ 推荐 |
| 户部 | 财务分析/数据处理 | ⭐ 可选 |
| 礼部 | 品牌营销/内容创作 | ⭐ 可选 |
| 工部 | 运维部署/基础设施 | ⭐⭐ 推荐 |
| 吏部 | 项目管理/任务跟踪 | ⭐ 可选 |
| 刑部 | 法务合规/风险评估 | ⭐ 可选 |
唐朝三省制（11 Bot）
以唐朝三省六部制为蓝本，中书省起草、门下省审核、尚书省执行，分权制衡。
| Bot | 职责 | 推荐度 |
|---|---|---|
| 中书省 | 起草诏令/任务分解 | ⭐⭐⭐ 必需 |
| 门下省 | 审核封驳/质量把关 | ⭐⭐⭐ 必需 |
| 尚书省 | 派发执行/协调六部 | ⭐⭐⭐ 必需 |
| 御史台 | 监察审计/绩效评估 | ⭐⭐ 推荐 |
| 史官 | 记录朝政/文档管理 | ⭐ 可选 |
| 六部 | 执行部门 | ⭐⭐ 复用 |
现代企业制（9 Bot）
以现代企业架构为蓝本，CEO 决策，Board 审议，CxO 各司其职。
| Bot | 职责 | 推荐度 |
|---|---|---|
| CEO | 决策调度/战略规划 | ⭐⭐⭐ 必需 |
| Board | 战略审议/方向把控 | ⭐⭐ 推荐 |
| QA | 质量审查/测试验证 | ⭐⭐ 推荐 |
| CTO | 技术执行/架构设计 | ⭐⭐⭐ 必需 |
| CFO | 财务分析/成本控制 | ⭐ 可选 |
| CMO | 品牌营销/市场推广 | ⭐ 可选 |
| COO | 运营部署/流程优化 | ⭐⭐ 推荐 |
| CLO | 法务合规/风险管理 | ⭐ 可选 |
| CoS | 项目协调/资源调度 | ⭐ 可选 |
🚀 快速开始
1. 安装技能
# 通过 clawdhub 安装
clawdhub install ai-court
# 或手动克隆
git clone https://github.com/wanikua/ai-court-skill.git
2. 选择制度 + 配置模板
# 明朝 3 Bot（推荐）
cp configs/feishu-ming/openclaw-3bot.json ~/.openclaw/openclaw.json
# 唐朝 3 Bot
cp configs/feishu-tang/openclaw-3bot.json ~/.openclaw/openclaw.json
# 现代 3 Bot
cp configs/feishu-modern/openclaw-3bot.json ~/.openclaw/openclaw.json
3. 配置 Bot 凭证
编辑 ~/.openclaw/openclaw.json，填入你的飞书应用凭证：
{
"channels": {
"feishu": {
"enabled": true,
"accounts": {
"silijian": {
"appId": "cli_xxx",
"appSecret": "xxx"
}
}
}
}
}
4. 重启 Gateway
openclaw gateway restart
📖 文档
| 文档 | 说明 |
|---|---|
| 飞书配置指南 | 5 分钟快速配置 |
| 灵活配置指南 | 按需选择 Bot 数量 |
| Docker 部署 | 容器化部署 |
🔗 相关项目
| 项目 | 说明 |
|---|---|
| danghuangshang | 生产部署实例 - https://github.com/wanikua/danghuangshang |
| OpenClaw | 底层框架 - https://github.com/openclaw/openclaw |
| Become CEO | 现代企业版 - https://github.com/wanikua/become-ceo |
📝 License
MIT License - 详见 LICENSE
Usage Guidance
This package is largely a collection of OpenClaw configuration templates and agent prompt identities; it matches its stated purpose but carries operational risks you should address before using it:
- Inspect configs before copying: do not blindly cp templates to ~/.openclaw. Back up your current ~/.openclaw/openclaw.json first.
- Secrets handling: the templates expect Feishu appId/appSecret and LLM API keys inside the JSON. Avoid storing long‑lived secrets in plaintext in repo files; use a secrets manager or environment variables where possible and remove secrets from any repository clones.
- Channel visibility: the SKILL explicitly says workflow/dispatch is public in channels. Using public group channels to coordinate actions or push diffs can leak secrets (DB connection strings, API keys, code containing secrets). Configure DM policies and channel access conservatively.
- Minimize blast radius: create limited-scope Feishu apps/service accounts for bots (rotate credentials), and do not reuse high‑privilege credentials. Limit which agents can run with sandbox 'off' and avoid enabling wide subagent lists until you trust the deployment.
- Verify provenance: the skill links to external GitHub repos (wanikua, danghuangshang). Review those repos and their Docker/deployment instructions before cloning or running them.
- Run in isolated environment first: test in a non‑production VM or container, review what files/directories are created (workspaces under $HOME/clawd-*) and confirm webhooks endpoints and who can trigger them.
If you want, I can: (1) list the exact files that will be overwritten/created from the templates; (2) produce a short checklist of configuration changes to harden secrets and channel visibility; or (3) review the linked GitHub repos for suspicious contents if you provide their URLs.
Capability Analysis
Type: OpenClaw Skill
Name: ai-court
Version: 2.3.0
The bundle is a comprehensive multi-agent orchestration framework themed around historical Chinese government structures (Ming/Tang Dynasties) and modern corporate hierarchies. It provides configuration templates for Feishu and Discord integration, defining specialized roles for task dispatching, prompt optimization, and code review. While several agents are configured with sandboxing disabled (e.g., in configs/feishu-ming/openclaw.json), this appears to be a functional requirement for their stated purposes (DevOps, system administration, and agent management) rather than a malicious backdoor. The instructions in SKILL.md and SOUL.md focus on maintaining the role-play hierarchy and operational efficiency without any evidence of exfiltration, persistence, or harmful prompt injection.
Capability Assessment
Purpose & Capability
The name/description (multi‑agent OpenClaw 'AI Court') match the provided assets: many OpenClaw config templates and agent identities for Feishu/Discord deployment. The credential types implied (Feishu appId/appSecret, LLM provider API key) are expected for this purpose.
Instruction Scope
Runtime instructions tell you to copy template JSONs into ~/.openclaw/openclaw.json, populate appId/appSecret and provider API keys, then restart the gateway. The SKILL explicitly requires workflows to be '公开在频道内' (all workflow visible in channels) and uses sessions_send/spawn and message tools — this increases the chance that sensitive content (prompts, configs, diffs) could be posted to chat channels. The configs reference GitHub webhook triggers and automatic code-review flows that will surface commit diffs into channels. These behaviors go beyond mere orchestration and create clear data‑exposure risks.
Install Mechanism
This is instruction‑only with no install spec or downloads; nothing is fetched or executed by the skill itself. That lowers supply‑chain/remote code risk. However, the README suggests cloning external GitHub repos (wanikua/danghuangshang) — cloning external code is an action left to the user and should be inspected before use.
Credentials
The skill declares no required env vars, but the templates require placing many secrets (Feishu appId/appSecret per bot, LLM provider baseUrl/apiKey) into a JSON config under the user home directory. Requiring multiple per-bot app secrets is expected for multi‑bot Feishu setups, but storing them in plaintext templates and then instructing agents to operate in publicly visible channels is disproportionate from a confidentiality viewpoint. There is no guidance in the SKILL.md to use a secret manager or restrict where those secrets are stored.
Persistence & Privilege
The skill does not set always:true and does not autonomously install binaries. However, it instructs the user to copy templates into ~/.openclaw (which may overwrite an existing OpenClaw config), create agent workspaces under $HOME, and enables broad agent-to-agent communication (many agents have sandbox mode 'off' or 'all' and subagent allowances). That grants the deployed agents substantial scope within the OpenClaw environment; consider backing up existing configs and limiting agent privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ai-court - After installation, invoke the skill by name or use
/ai-court - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.3.0
更新项目描述，更准确反映支持多种制度
v2.2.0
修复安装脚本 LLM API 配置，优化用户体验
v2.1.0
修复 node_modules 误提交问题，优化项目描述，完善配置模板
v2.0.0
Major cleanup and simplified onboarding for ai-court 2.0.0:
- Reorganized and greatly reduced repository files for easier navigation.
- Added concise setup and troubleshooting guides under the new references/ directory.
- Streamlined installation and usage instructions in SKILL.md.
- Updated documentation links; most old docs and maintenance files removed.
- Introduced a post-install script for improved setup.
v1.6.0
同步 danghuangshang 仓库最新更改 - 三种制度配置/完整 scripts/docs/skills
v1.5.0
Provider-agnostic: remove all vendor-specific model names, API URLs, and recommendations. Users choose their own LLM provider and models.
v1.4.1
Declare ANTHROPIC_API_KEY, DISCORD_BOT_TOKEN and config path in metadata to match runtime requirements
v1.4.0
Security hardening: minimal docs, env var placeholders, no rw/bridge/docker.env mentions
v1.3.1
Security fix: harden sandbox defaults (ro workspace, no network), remove credentials declaration, add adjustable permissions table
v1.3.0
Credentials declared via metadata.credentials instead of requires.env — skill now shows ready in Clawdbot.
v1.2.0
Fix security scan: declare ANTHROPIC_API_KEY in metadata requires.env, remove curl|bash from skill text.
v1.1.0
Move setup.sh out of skill package to fix security flag.
v1.0.0
Initial release: 明朝六部 multi-agent Discord skill
Metadata
Frequently Asked Questions
What is AI 朝廷 · 多 Agent 协作系统?
以明朝内阁制为蓝本的多 Agent 协作系统 - 一键部署你的 AI 朝廷. It is an AI Agent Skill for Claude Code / OpenClaw, with 689 downloads so far.
How do I install AI 朝廷 · 多 Agent 协作系统?
Run "/install ai-court" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is AI 朝廷 · 多 Agent 协作系统 free?
Yes, AI 朝廷 · 多 Agent 协作系统 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does AI 朝廷 · 多 Agent 协作系统 support?
AI 朝廷 · 多 Agent 协作系统 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created AI 朝廷 · 多 Agent 协作系统?
It is built and maintained by boluobobo (@wanikua); the current version is v2.3.0.
More Skills