What problem does it solve? Teams often pick a prioritization framework by habit, then fill in scores with invented numbers, producing rankings that look rigorous but rest on guesses. This Skill forces the framework choice to match the team's stage and data maturity, labels every input as Fact, Inference, or Assumption, and adds a sensitivity note showing what would change the ranking. ## Core Features & Use Cases - Framework selection: Chooses among RICE, ICE, Value vs Effort, Kano, MoSCoW, WSJF, and Opportunity Scoring based on stage, data availability, and audience, recording rejected candidates and each framework's characteristic failure mode. - Evidence-labeled scoring: Scores column-first with every Reach, Impact, Confidence, and Effort cell labeled Fact, Inference, or Assumption, and leaves items with insufficient evidence unscored rather than guessed. - Sensitivity analysis: Names the smallest input change that would reorder the top three, and declares ties when scores cannot bear the weight of a decision. - Use Case: A product team with seven backlog items and one quarter of capacity runs the skill, rejects MoSCoW based on last quarter's everything-is-Must failure, scores with RICE using real analytics for Reach, and exports a ranked CSV with a sensitivity note for the planning review. ## Quick Start Ask the assistant to help prioritize your backlog of candidate items by choosing the right framework and scoring them with evidence labels.
