workflow-debate - Structured adversarial debate to evaluate ideas and plans
Evaluates proposals, plans, or decisions through structured adversarial debate and peer cross-examination among specialized AI councillors.
Tags
Updated: 2026-09-19Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Parse execution flags and input topic
- Spawn specialized AI councillor roles
- Collect independent opening statements
- Orchestrate cross-examination debate rounds
- Facilitate peer messaging between councillors
- Track position evolution across rounds
- Synthesize consensus and dissensus points
- Generate structured verdict and risk matrix
- Save debate transcript file
Inputs
- Idea or plan to evaluate
- Debate configuration flags
Outputs
- Structured evaluation verdict
- Risk assessment matrix
- Transcript file
Requirements
- CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS environment variable
- Plan subagent support