Skills moot-court-ai
Simulate a full Chinese civil court hearing with 4 role-based agents (clerk, plaintiff, defendant, judge) orchestrated by deterministic Lobster workflow.
install
source · Clone the upstream repo
git clone https://github.com/openclaw/skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/baobaodawang-creater/moot-court-ai" ~/.claude/skills/openclaw-skills-moot-court-ai && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/baobaodawang-creater/moot-court-ai" ~/.openclaw/skills/openclaw-skills-moot-court-ai && rm -rf "$T"
manifest:
skills/baobaodawang-creater/moot-court-ai/SKILL.mdsource content
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
(书记员): announces opening, checks identity, controls stage transitions.clerk
(原告代理律师): argues for plaintiff, presents claim and evidence.plaintiff
(被告代理律师): performs three-validity challenges and defense.defendant
(审判长): stays neutral, summarizes issues, applies legal syllogism, and renders judgment.judge
Model stack
- DeepSeek:
,deepseek-chatdeepseek-reasoner - Qwen:
(DashScope compatible endpoint)qwen-max
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:
DEEPSEEK_API_KEYDASHSCOPE_API_KEY
Recommended usage
- Prepare case files (
,case-brief.md
,complaint.md
, evidence folders).defense.md - Initialize materials into agent workspaces.
- Run
through OpenClaw/Lobster.moot-court.lobster - Export judgment and hearing log for review.