Help us improve
Share bugs, ideas, or general feedback.
From pm-copilot
Use this skill when the user asks about "cohort analysis", "retention cohorts", "how to read cohort data", "analyze my retention", "what does my cohort data say", "cohort retention curves", "D7/D30 retention", "how to improve cohort retention", or has cohort data they want to interpret and act on.
npx claudepluginhub productfculty-aipm/pm-copilot-by-product-facultyHow this skill is triggered — by the user, by Claude, or both
Slash command
/pm-copilot:cohort-analysisThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are helping the user analyze cohort retention data to understand how well the product retains users over time, identify where users drop off, and recommend actions to improve retention.
Analyzes user cohorts for retention curves, feature adoption trends, churn patterns, and engagement insights. Generates heatmaps, charts, Python scripts, and research recommendations.
Analyzes customer cohorts by acquisition date, channel, behavior, or revenue tier to track retention curves, LTV, revenue, and engagement from CRM or analytics data.
Structures retention analysis, churn investigation, or engagement deep-dives for product teams. Produces a retention snapshot with root cause hypotheses, aha-moment correlation, and prioritised interventions.
Share bugs, ideas, or general feedback.
You are helping the user analyze cohort retention data to understand how well the product retains users over time, identify where users drop off, and recommend actions to improve retention.
Framework: AARRR (Retention stage), Lenny Rachitsky's retention benchmarks, North Star framework.
Read memory/user-profile.md for product stage and business model. Read context/company/analytics-baseline.md for existing retention baselines and targets.
Ask the user to provide:
If the data is provided, identify:
Compare the user's retention to benchmarks from Lenny's data:
Mobile apps (consumer):
SaaS / B2B:
Freemium:
Calibrate recommendations to the user's stage and model from memory.
Find the point of sharpest drop:
If the drop is at D1 (first day): Activation problem — users aren't experiencing the core value in their first session
If the drop is at D7 (first week): Habit formation problem — the product isn't building a regular use pattern
If the drop is at D30 (first month): Value realization problem — initial excitement fades without ongoing value
If cohorts are getting worse over time (newer cohorts retain less): Product-market fit may be drifting — new users coming in are less well-matched to the product than early users
Ask: can the cohort be segmented to find which users retain and which don't?
Segment by:
This segmentation usually reveals: a subset of users who retain very well, and a subset who churn almost immediately. Understanding the difference drives the highest-ROI improvements.
Produce: