What problem does it solve? When a business metric misses its target, founders often see the total miss but not the root cause behind it. This Skill decomposes the variance into line-item drivers, checks co-moving related metrics to catch misleading readings, and recommends the single corrective lever most likely to fix it. ## Core Features & Use Cases - Top Movers Attribution: Decomposes a metric into its line items and ranks each by contribution to the total variance, identifying whether the cause is concentrated or diffuse. - Co-Movement Interpretation: Tests the variance against related metrics to distinguish a genuine performance change from an artifact, such as lower expenses caused by stalled activity rather than efficiency. - Root-Cause Classification and Lever Recommendation: Classifies the cause as execution failure, wrong assumption, external shift, or data error, then maps it to a corrective lever with owner, deadline, and approval requirements. - Use Case: A founder asks why gross margin came in at 48% against a 56% forecast. The Skill attributes 90% of the miss to one service line's direct costs, confirms via co-movement that pricing and demand are healthy, and recommends renegotiating the input cost. ## Quick Start Ask the AI to diagnose why a specific metric missed its forecast this month, providing the actual value, forecast value, and line-item breakdown.
