claude-council
Convene a council of 5 AI advisors to pressure-test any decision and eliminate Claude's yes-man bias. Five advisors with opposing thinking styles analyze in parallel, 5 peer-reviewers evaluate anonymized outputs, then a Chairman synthesizes one verdict and one concrete next step. Based on the LLM Council methodology by Ole Lehmann and Andrej Karpathy. Trigger on: "council this", "run the council", "war room this", "pressure-test this", "stress-test this", "debate this", "should I X or Y" (when a real tradeoff exists).
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
No security issues found
Scanned
- Repository
valeriibeck-star/claude-skills
- Revision
0bda8b8
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.