llm-council - Pressure-test decisions with an AI council
Runs a question through five independent AI advisors, anonymous peer review, and a chairman synthesis to produce a recommendation.
Tags
Updated: 2026-10-02Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Scan workspace context
- Frame decision questions
- Run five advisors in parallel
- Conduct anonymous peer review
- Synthesize a council verdict
Inputs
- Decision question or tradeoff
- Workspace context files
- Referenced files or attachments
Outputs
- Council verdict
- Actionable recommendation
- Framed question transcript
Requirements
- Claude with sub-agent support
- Workspace read access
- Glob and Read tools
- Parallel sub-agent execution