Product metrics review
Skill yigityildiz0/universal-ai-skill-library/skills/common/product-metrics-review
531 searchable AI Agent Skills for Claude Code, OpenAI Codex, and OpenCode — EN/TR catalog, platform and risk notes, direct ZIPs, and curated bundles.
npx -y skills add yigityildiz0/universal-ai-skill-library --skill product-metrics-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
3 things to look at
- 19 days oldThe repository was created 19 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Review product metrics, KPI movement, metric definitions, segmentation, anomalies, and decision implications. Use for metrics review, KPI review, product performance, why a metric changed, north-star metric, funnel review, or product health check.
SKILL.md
0.9 KB, 128 tokens by cl100k_base, as published. Nobody here has run it
Product Metrics Review
Interpret change only after validating the metric.
- State the product decision, metric contract, source, time period, owner, and freshness.
- Check denominator, cohort, time zone, missing data, tracking changes, releases, and definition changes before explaining movement.
- Segment the change by the few dimensions that can reveal meaningful differences; avoid fishing.
- Separate observation, hypothesis, evidence, and next test.
- Recommend an owner, decision date, and stop condition for follow-up.
Do not confuse correlation with causal proof or publish a metric interpretation without the caveats that materially change it.