decision-councillisted

Forces 5 AI advisor personas to argue about a decision, anonymously peer-review each other, and synthesize a verdict with anti-false-consensus guardrails. Auto-detects high-stakes decisions from context. Trigger on: pricing, deal terms, partnerships, market entry, investments, exit strategies, go/no-go calls, trading decisions, DeFi/protocol entry, market entry/exit, futures positions, training program changes, competition prep, injury decisions, career moves, big purchases, financial planning, macro economic events (central-bank decisions, FX, inflation), geopolitical developments affecting markets, major AI/Web3/tech releases that change capability or competitive landscape, or any question where being wrong costs money, health, or reputation. Also trigger on "run council", "stress test", "what am I missing", "devil's advocate", "sanity check", or when the user leans toward an answer already. Do NOT trigger for brainstorming, writing, code, factual lookups, routine daily choices, or low-stakes ops.
0xUrsanomics/utopia-os · ★ 2 · AI & Automation · score 76

Install: claude install-skill 0xUrsanomics/utopia-os

# Decision Council A structured adversarial analysis framework that forces cognitive diversity onto strategic decisions. Compensates for the model's sycophancy bias by running 5 constrained personas, anonymous peer review, and anti-false-consensus detection. > **Looking for forward-failure analysis instead?** If the user wants "every way this could die before I commit" rather than "multi-perspective debate now", route to `skills-shared/premortem/SKILL.md`. Different psychological mechanism, different output. The two skills complement each other; do not run both unless explicitly asked. ## Why This Exists An assistant model agrees with how you frame questions. Same question, different framing, opposite answers. That's fine for writing. Dangerous for decisions where being wrong costs money or reputation. This skill forces structured disagreement. It can't eliminate same-model bias entirely (if all 5 personas share one model's weights), but it catches single-frame blindness, logic gaps, and assumption leaks. ## Limitations (Be Honest About These) - If all 5 personas run on the same model instance, they share training and blind spots at the model level. The cross-provider routing below (Step 2a) mitigates this by routing some seats to a different provider for true cross-architecture diversity. - The disagreement at same-provider seats is prompt-engineered, not architectural. Mixed-model routing makes 2-3 seats genuinely diverse. - For triple-redundancy on extremely high-st