← ClaudeAtlas

decision-bias-checklisted

Audit the decision before it ships. Use for "are we sure about this?", high-stakes choices made on fast intuition, plans with no failure scenario, estimates that are suspiciously optimistic, metrics being gamed (Goodhart), unfalsifiable claims, negotiation prep, or strategies that break in extreme conditions.
cdeust/zetetic-team-subagents · ★ 7 · AI & Automation · score 75
Install: claude install-skill cdeust/zetetic-team-subagents
# Decision Bias Check **Problem shape:** a decision, plan, or evaluation is about to be committed and nobody has run the adversarial pass: which bias produced it, what would refute it, how it behaves in the tails, and whether the metric still measures what it was meant to. ## Relevant geniuses | Agent | Use when | |---|---| | [kahneman](../../agents/genius/kahneman.md) | fast intuition on a high-stakes call; no pre-mortem; estimate needs a reference class; an easier question was answered instead of the hard one | | [taleb](../../agents/genius/taleb.md) | exposure to volatility unclassified (fragile/robust/antifragile); improvement always by addition; decision-makers carry no downside | | [popper](../../agents/genius/popper.md) | claim has no observation that could refute it; only easy confirmations offered as evidence; plan too big to test piecemeal | | [simon](../../agents/genius/simon.md) | optimizing where satisficing is rational; the search space needs decomposing before choosing | | [boyd](../../agents/genius/boyd.md) | adversarial setting — the other side adapts; tempo and orientation matter more than the single best move | | [zhuangzi](../../agents/genius/zhuangzi.md) | the metric has become the target (Goodhart); the evaluation framework itself needs auditing | | [ibnalhaytham](../../agents/genius/ibnalhaytham.md) | an authority's claim taken on trust — systematic doubt with controlled isolation of variables | | [rogerfisher](../../agents/genius/rogerfisher.md) | m