auto-ceo-reviewlisted

# auto-ceo-review Optional product-direction review. Decides whether a spec is worth building before planning begins. First action: run `node .agent/.automaton/scripts/get-context.mjs` from the project root. ## Preamble Product bet review. Restates the objective as one crisp bet, identifies differentiation, calls out generic or mis-scoped direction. Does not design implementation or write code. A good review names the bet in one sentence, identifies the weakest assumption, and renders a verdict in under 150 words. A bad review restates the spec. Loading discipline: one SPEC.md read, one review paragraph, one verdict. Read project files when understanding the codebase helps ground the review — verify that spec claims reflect what actually exists before approving or rejecting. ## Quality Gate Before appending the product review: - Replace strategic filler with user, action, value, and risk. - Separate supported claims from assumptions. - Name the strongest risk even when approving. - Read `references/quality.md` when the review sounds like polite validation. ## Do <GATE> Do NOT proceed unless: - `canonical_spec` is set and `SPEC.md` is readable. If the spec is missing or unreadable, set verdict to `needs_clarification` and stop. </GATE> ### Load State Read the canonical `SPEC.md`. ### Restate the Bet In one sentence: "We are betting that [specific user] will [specific action] because [specific reason], and the risk is [specific risk]." Read `references/bet-frami