Moot Court AI
Moot Court AI is an OpenClaw skill that runs a 4-agent Chinese civil court simulation with strict workflow control.
Agent system
- -
clerk (书记员): announces opening, checks identity, controls stage transitions. - INLINECODE1 (原告代理律师): argues for plaintiff, presents claim and evidence.
- INLINECODE2 (被告代理律师): performs three-validity challenges and defense.
- INLINECODE3 (审判长): stays neutral, summarizes issues, applies legal syllogism, and renders judgment.
Model stack
- - DeepSeek:
deepseek-chat, INLINECODE5 - Qwen:
qwen-max (DashScope compatible endpoint)
Workflow principle
- - Deterministic orchestration with Lobster.
- Agent communication follows fixed hearing stages.
- Process follows Chinese civil procedure order (庭前准备 -> 诉辩交换 -> 举证质证 -> 法庭辩论 -> 最后陈述 -> 宣判).
Installation requirements
You must configure both API keys before running:
Recommended usage
- 1. Prepare case files (
case-brief.md, complaint.md, defense.md, evidence folders). - Initialize materials into agent workspaces.
- Run
moot-court.lobster through OpenClaw/Lobster. - Export judgment and hearing log for review.
模拟法庭AI
模拟法庭AI是一项OpenClaw技能，可运行具有严格工作流控制的4智能体中国民事法庭模拟。
智能体系统
- - 书记员：宣布开庭，核对身份，控制阶段转换。
- 原告代理律师：为原告辩护，提出诉讼请求和证据。
- 被告代理律师：进行三性抗辩和辩护。
- 审判长：保持中立，归纳争议焦点，运用法律三段论，作出判决。
模型栈
- - DeepSeek：deepseek-chat、deepseek-reasoner
- Qwen：qwen-max（兼容DashScope端点）
工作流原则
- - 使用Lobster进行确定性编排。
- 智能体通信遵循固定庭审阶段。
- 流程遵循中国民事诉讼程序顺序（庭前准备→诉辩交换→举证质证→法庭辩论→最后陈述→宣判）。
安装要求
运行前必须配置两个API密钥：
- - DEEPSEEKAPIKEY
- DASHSCOPEAPIKEY
推荐用法
- 1. 准备案件文件（case-brief.md、complaint.md、defense.md、证据文件夹）。
- 将材料初始化到智能体工作区。
- 通过OpenClaw/Lobster运行moot-court.lobster。
- 导出判决书和庭审记录以供审查。
