Diagnose conversion funnel problems and generate data-backed improvement hypotheses.
/funnel-analyzer3-4 hrs → 30 min
Compared to doing it manually
/funnel-analyzerType this in Claude to run the skill
Everyone knows the funnel is leaky, but nobody knows exactly where or why. Conversion discussions turn into guessing games without proper drop-off analysis.
Agent workflows chain multiple skills into one command.
.claude/skills/ folder in your project/funnel-analyzer in Claude to run the skill/metric-framework-builderBuild comprehensive metrics frameworks using the AARRR pirate metrics or input/output methodology.
/experiment-designerDesign A/B tests with proper methodology, sample sizes, and success criteria.
/ab-test-analyzerInterpret experiment results with statistical rigor and clear ship/no-ship recommendations.
/ab-test-designerDesign statistically sound experiments with clear hypotheses and sample size calculations.
Funnel analysis tracks how users progress through a series of steps (e.g., visit → signup → activation → purchase). It reveals where users drop off and helps prioritize optimization efforts.
Look for steps with higher-than-expected abandonment. Compare to benchmarks, segment by user type, and use session recordings to understand why users leave. The biggest drop-off is your biggest opportunity.
It depends heavily on industry and funnel stage. B2B SaaS: 2-5% visitor-to-trial, 10-25% trial-to-paid. Focus less on absolute numbers and more on improving your own baseline over time.
Run this skill inside your PM Operating System, or download it on its own.
Use all 70 skills, workflows, and sub-agents in a system that knows your company, product, and customers.