nobrainer-decide

NoBrainer Decide

Deliver one ranked decision with evidence, confidence, watchpoints and kill criteria. Do not hide behind several flavors of "it depends". This skill decides; it does not diagnose an unknown failure or execute the chosen option.

Use nobrainer-rca first when the unresolved question is causal. Use nobrainer-research when current external facts or a broader option space must be established before scoring.

Calibrate rigor

Do not run a panel for a factual lookup, an already-made choice, or an obvious reversible edit.

• LIGHT: one explicit pass for reversible, low-cost choices with clear facts.
• STANDARD: at least three independent perspectives for meaningful tradeoffs: option generation, scoring, and blind attack/cold review.
• HIGH: at least six bounded independent runs for architecture, material cost, difficult rollback, public commitments, safety, or long lock-in. Separate two option generators, scorer, blind attacker, cold reviewer, and synthesizer.

Use fresh or deliberately bounded contexts. Independence means different evidence/roles and no inherited rationale, not merely several calls to the same prompt. When independent execution is unavailable, mark the analysis partial; do not claim a panel. Never hardcode a provider or model family into the protocol; select the strongest available capability appropriate to each role.

1. Frame the actual decision

Restate:

• decision, owner, deadline and observable outcome;
• baseline/status quo and what happens if nothing changes;
• hard constraints, reversible vs irreversible effects, and owner gates;
• evidence freshness and consequential unknowns.

Rewrite the problem once without project nouns. Ask "what system property makes this decision necessary?" until symptom and root cause are separated. If a candidate appears immediately, record it as an anchor to challenge, not the answer.

Ask at most one focused clarification round. Then either decide or identify the single missing owner choice/evidence that truly blocks a decision.