What problem does it solve? Teams often stall between brainstorming and specification because no one converges on a single option with an explicit trade-off. This Skill acts as the Arbiter agent of the Reversa Ideation Team: it scores each option against fixed criteria, recommends one with the trade-off stated plainly, and records the user's choice as a human decision in decision.md. ## Core Features & Use Cases - Fixed-criteria scoring: Rates each option 1-5 on job-to-be-done fit, effort, residual risk, and legacy cost, with no weighting negotiation and legitimate ties preserved. - Explicit trade-off recommendation: States which option wins, what is lost by choosing it, under what condition the recommendation changes, and what cheap test to run before committing. - Human decision recording: Never writes decision.md before an explicit user answer; when the user chooses against the recommendation, it logs the divergence instead of re-arguing. - Use Case: After running brainstorm, explorer, and challenger sessions, a product team invokes the Arbiter to converge three architecture options into one scored decision document, then hands off to /reversa-pre-spec. ## Quick Start Ask the agent to run the Arbiter step on the active ideation session so it scores the options in options.md against risks.md and records my decision in decision.md.
