From pm-analytics
Structures retention analysis, churn investigations, engagement deep-dives with cohort segmentation, inflection points, aha moments, and testable interventions for product teams.
npx claudepluginhub mohitagw15856/pm-claude-skills --plugin pm-analyticsThis skill uses the workspace's default tool permissions.
Diagnose why users leave, identify what keeps them, and recommend specific, testable interventions — not vague "improve onboarding" suggestions.
Diagnoses user churn causes, builds cohort retention curves, identifies behaviors driving long-term retention. For PMs analyzing D1/D7/D30 metrics and engagement.
Analyzes retention curves to diagnose primary drop-off points and generate specific intervention plans with expected impact. Use for churn reduction, user reactivation, or retention playbooks.
Diagnoses mobile app retention issues with industry benchmarks and provides prioritized plans for activation, habit formation, and engagement deepening.
Share bugs, ideas, or general feedback.
Diagnose why users leave, identify what keeps them, and recommend specific, testable interventions — not vague "improve onboarding" suggestions.
The retention curve has two components:
A product with PMF has a retention curve that flattens. If it trends to zero, you have a PMF problem, not an onboarding problem. Name this distinction explicitly.
| Metric | Formula | What It Tells You |
|---|---|---|
| D1 Retention | Users who return on day 2 ÷ new users day 1 | Quality of first experience |
| D7 Retention | Users active on day 8 ÷ users who joined 7 days ago | Early habit formation |
| D30 Retention | Users active on day 31 ÷ users who joined 30 days ago | Product-market fit signal |
| DAU/MAU Ratio | Daily active users ÷ monthly active users | Stickiness (>20% good, >50% excellent) |
| Churn Rate | Users lost in period ÷ users at start of period | Monthly or annual |
| Net Revenue Retention | MRR at end of period ÷ MRR at start (same cohort) | Revenue health including expansion |
Don't analyse "retention" — analyse retention for specific cohorts:
Where does the drop happen? D1? D7? Month 3?
Which early behaviour predicts long-term retention?
Interview churned users — never skip this. Survey data alone is insufficient.
Question: [Specific retention question being answered] Period Analysed: [Date range] Segment: [Which users]
Current Retention Snapshot:
| Metric | Current | Industry Benchmark | Status |
|---|---|---|---|
| D1 Retention | [X%] | 25–40% | 🔴/🟡/🟢 |
| D7 Retention | [X%] | 10–25% | 🔴/🟡/🟢 |
| D30 Retention | [X%] | 5–15% | 🔴/🟡/🟢 |
| DAU/MAU | [X%] | 10–20% typical | 🔴/🟡/🟢 |
Retention Curve Shape: [Flattening / Still declining / Trending to zero] PMF Signal: [Strong / Weak / Absent — based on curve shape]
Root Cause Hypotheses:
| Hypothesis | Evidence | Confidence | Test |
|---|---|---|---|
| [Cause] | [Data point] | H/M/L | [How to validate] |
"Aha Moment" Correlation: Users who [specific action] in first [N] days retain at [X%] vs [Y%] for those who don't.
Recommended Interventions:
| Intervention | Target Drop | Expected Lift | Effort | Priority |
|---|---|---|---|---|
| [Specific change] | D1 / D7 / D30 | [X%] | S/M/L | 1/2/3 |
Monitoring Plan: