Analyze funnel retention cohorts
Skill alexe-ev/product-plugins/data-analytics/skills/analyze-funnel-retention-cohorts
Skill library for AI agents — 15 product domains, 121 skills. Tells the agent what to ask, how to reason, and what to output.
npx -y skills add alexe-ev/product-plugins --skill analyze-funnel-retention-cohortsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 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
Analyze funnel drop-off, retention curves, and cohort behavior to identify problems and opportunities. Use this skill when a team has data and needs to understand user behavior patterns.
SKILL.md
2.4 KB, as published. Nobody here has run it
Analyze Funnel, Retention & Cohorts
Purpose
Turn funnel, retention, and cohort data into product insights that identify where users drop off, churn, or get stuck.
Skill type
Conceptual skill with calculation-aware components
Use this skill when
- A funnel has unexplained drop-off at specific steps
- Retention is declining or unexpectedly flat
- Cohort analysis is needed to understand behavioral differences across user groups
- A product change may have affected retention and needs investigation
Do not use this skill when
- No data is available (collect data first)
- The goal is experiment result analysis (use analyze-experiment-results)
Required inputs
- Funnel data, retention data, or cohort data (at least one)
- Product context (what flow or user group is being analyzed)
Optional inputs
- Baseline benchmarks
- Cohort definitions
- Time range
- Segment breakdowns
Upstream context
Works best when:
- Metrics framework is defined
- Data instrumentation is in place
If upstream context is missing
If data is absent, produce a data collection plan and flag that analysis cannot proceed without it.
Downstream handoff
Output can feed:
- detect-performance-signals
- formulate-experiment-hypothesis (data insights become experiment inputs)
- identify-problem-opportunity
Instructions
- Map the funnel or retention structure being analyzed.
- Identify drop-off points or retention cliff events.
- Compare cohorts if relevant (by acquisition source, segment, time period).
- Identify patterns and anomalies.
- Generate hypotheses for the observed behavior.
- Recommend next steps: further analysis, qualitative research, or experiment.
Output
Provide:
- Funnel analysis with drop-off rates per step
- Retention curve interpretation
- Cohort comparison summary (if applicable)
- Key patterns and anomalies
- Hypotheses for observed behavior
- Recommended next steps
- Data quality caveats
Risks / caveats
- Correlation in cohort data is not causation — use it for hypothesis generation, not conclusions
- Segment data before drawing conclusions — average retention often hides meaningful variation
- Small cohorts produce noisy results — flag when sample sizes are thin