Build comprehensive metrics frameworks using the AARRR pirate metrics or input/output methodology.
4-6 hrs → 45 min
Compared to doing it manually
/metric-framework-builderType this in Claude to run the skill
Every team tracks different metrics. Nobody agrees on what success looks like. Dashboards multiply while clarity decreases.
.claude/skills/ folder in your project/metric-framework-builder in Claude to run the skillDiagnose conversion funnel problems and generate data-backed improvement hypotheses.
Design A/B tests with proper methodology, sample sizes, and success criteria.
Interpret experiment results with statistical rigor and clear ship/no-ship recommendations.
Design statistically sound experiments with clear hypotheses and sample size calculations.
Focus on outcomes, not outputs. Track a north star metric (overall value), plus supporting metrics for acquisition, activation, engagement, retention, and revenue. Avoid vanity metrics that don't drive decisions.
Lagging indicators measure past results (revenue, churn). Leading indicators predict future results (activation rate, feature adoption). PMs need both, but leading indicators help you course-correct faster.
One north star, 3-5 supporting metrics. Too many metrics dilute focus. If everything is important, nothing is. Choose metrics that actually change your decisions.
Download this skill and drop it in your .claude/skills/ folder.
This skill + 70+ more, context files, and agent workflows — $499