Court — Development skill for Claude Code
Council debate — 4 agents argue an idea in 2 rounds, the judge issues a verdict and plan.
How to install Court
Installs to ~/.claude/skills/germandok-ai-team-court/SKILL.md
mkdir -p ~/.claude/skills/germandok-ai-team-court && curl -fsSL https://raw.githubusercontent.com/GermanDOK/ai-team/HEAD/commands/court.md -o ~/.claude/skills/germandok-ai-team-court/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Court does
description: Council debate — 4 agents argue an idea in 2 rounds, the judge issues a verdict and plan argument-hint:
Run a council debate on: $ARGUMENTS
You are the orchestrator. Subagents cannot call each other, so you run every step.
**Context.** Briefly gather project context (README, top-level structure, CLAUDE.md, recent git log). If `.council/decisions/` exists, list it and read decisions related to this idea. Write a 10-15 line context brief.
**Round 1
Alternatives in Development
- Validate Plan — You are tasked with validating that an implementation plan was correctly executed, verifying all success crite 10k ★
- Internet Court Skill — The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 4.9k ★
- Discuss — Act as a planning interviewer 2.9k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Worth Idea
Run the worth-idea council on a business idea — Believer, Skeptic, Investor argue in parallel, the Judge gives
Spar
Make the models argue before you build — Codex attacks the plan in bounded read-only rounds, then one builds a
Claude Council Of Five
Claude Code skill: five personas (Chair, Devil's Advocate, Principles Purist, Outsider, Executor) debate your
Cad Roast
Convene the 4-agent Idea Roast Council (Believer, Skeptic, Investor, Judge) for commercial/startup ideas.
Idea Review
A Claude skill that takes a raw product idea and gives you back an honest verdict and an executable build plan
Simmer
Iterative artifact refinement using judge subagents that score against user-defined criteria across multiple r
Related Agents
Council Judge
Chair of the council for /court and /full. Does not argue. Reads all positions and rebuttals, weighs arguments
Debate Tribunal
Multi-agent structured debate protocol where 3-5 persona-driven debaters argue positions through claim-evidenc
Debate Judge
L0.97 Adversarial Verification — reads all 3 rounds of prosecution and defense transcripts plus the original d