What problem does it solve?
Product teams often rank backlogs with a single framework or gut feel, hiding the assumptions that drive the ranking. This Skill runs every applicable prioritization framework against a candidate list, surfaces where rankings agree and diverge, and refuses to fabricate scores when input data is missing.
Core Features & Use Cases
- Multi-framework scoring: Runs RICE, ICE, MoSCoW, Weighted Scoring, and Kano, filtered by data availability, with per-framework scoring tables and rankings.
- Cross-framework divergence analysis: Produces a comparison table showing rank positions per item and explains each divergent item by naming the driving dimension.
- Honest refusal protocols: Declines to fabricate scores, offers an estimation scaffold when inputs are missing, and gates Kano on customer research with surveyed and inferred evidence tiers.
- Use Case: A PM with six Q3 roadmap candidates and rough reach, impact, and effort estimates gets RICE, ICE, and MoSCoW tables, a divergence analysis revealing that RICE under-weights a revenue-concentrated enterprise feature, and an executive recommendation on what to fund and defer.
Quick Start
Ask the AI to run the applicable prioritization frameworks against your list of candidate features and show where the rankings agree and diverge.