investigate-metric
Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries. Use when the user reports an anomaly, asks "why did X change?", or needs root-cause analysis for a trend, funnel, retention, stickiness, or lifecycle metric.
Pinned to revision 4e8964e24a5a, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/investigate-metric/SKILL.md
- skills/investigate-metric/references/box-plot-playbook.md
- skills/investigate-metric/references/common-causes.md
- skills/investigate-metric/references/funnel-playbook.md
- skills/investigate-metric/references/lifecycle-playbook.md
- skills/investigate-metric/references/paths-playbook.md
- skills/investigate-metric/references/retention-playbook.md
- skills/investigate-metric/references/shared-patterns.md
- skills/investigate-metric/references/stickiness-playbook.md
- skills/investigate-metric/references/trend-playbook.md
- skills/investigate-metric/scripts/breakdown_attribution.py
- skills/investigate-metric/scripts/compare_to_prior_periods.py
Every link opens the file at its source, pinned to the revision this page describes.