Metrics Design

Use when the user is designing the metric tree for a feature (especially an AI feature) — picking a north star, leading and lagging indicators, quality metrics, and counter-metrics. Trigger phrases include "what should we measure for…", "how do we know if this is working?", "I need to define success for…", or any spec where the success metrics section is fuzzy. Distinct from `the-eval-designer`, which measures model quality; this skill measures business success and guards against optimizing the model into a worse product.

shwetank Updated 4 repo stars

File contents

shwetank/bettersense commit 9c67240085

Frequently asked questions

npx get-skill add shwetank/metrics-design