idea-scoringlisted

<!-- version: 0.5.0 | outputs: memory/ideas/<slug>/scores.json (or pivot_scores.json for pivot-rescore) --> # Skill: idea-scoring ## Purpose Produce a single, defensible verdict on an idea by aggregating all available dimension scores using a **multiplicative-floor algorithm** — a single catastrophic weakness kills the score, just like it kills a real startup. Includes a **Riskiest Assumption Test (RAT)** to convert the verdict into a concrete next action. ## Input - Idea slug - One or more of the following (uses whatever is available): - `memory/ideas/<slug>/idea.md` - `memory/ideas/<slug>/desire_scores.json` - `memory/ideas/<slug>/competitors.json` - `memory/ideas/<slug>/pricing.json` - `memory/ideas/<slug>/cac.json` - `memory/ideas/<slug>/market_size.json` - `memory/ideas/<slug>/distribution.json` - `memory/ideas/<slug>/retention.json` - Optional: `memory/user_profile.md` (for founder-market fit) - `memory/market_insights/<niche>-*-<YYYY>-<MM>.md` (`trend_velocity` for the Demand rubric) ### Lane selection Read `business_model` from `idea.md` frontmatter. `b2c` and `prosumer` use the B2C rows of every rubric below; `b2b-smb` and `b2b2c` use the B2B rows. Where a rubric has only one table, it applies to both lanes. Record the lane in `scores.json` as `lane`. ### Minimum Viable Input At least **3 of 6 dimensions** must have source data. If fewer are available, refuse to score and list what's missing. Two dimensions are **mandatory** — Demand and Dist