Interpret experiment results with statistical rigor and clear ship/no-ship recommendations.
/ab-test-analyzer2-3 hrs → 20 min
Compared to doing it manually
/ab-test-analyzerType this in Claude to run the skill
A/B test results sit in dashboards, but interpreting them requires statistical knowledge most PMs don't have. Bad interpretation leads to shipping losers or killing winners.
/welcome/ab-test-analyzer in Claude to run the skill/metric-framework-builderBuild comprehensive metrics frameworks using the AARRR pirate metrics or input/output methodology.
/funnel-analyzerDiagnose conversion funnel problems and generate data-backed improvement hypotheses.
/experiment-designerDesign A/B tests with proper methodology, sample sizes, and success criteria.
/ab-test-designerDesign statistically sound experiments with clear hypotheses and sample size calculations.
Check statistical significance first (usually 95% confidence). Look at the primary metric, but also secondary metrics for unintended effects. Segment results by user type — averages can hide important patterns.
Inconclusive results are still results. Options: run longer for more data, test a bigger change, or accept that this variable doesn't matter much. Document learnings either way.
Don't peek at results early, ensure adequate sample size before starting, test one variable at a time, and account for novelty effects. Run for full business cycles to capture weekly patterns.
Get all 70 skills running in a system that knows your company, product, and customers.
All 70 skills + your company context in one system.