pm-cohort

Analyze cohort retention and feature adoption data to detect abnormal user groups.

1|Updated Apr 30, 2026
One-click install
npx skills add https://github.com/Wcof/PMSkill --skill pm-cohort
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pm-cohort
Source: https://github.com/Wcof/PMSkill/tree/main/skills/delivery/pm-cohort
Command: npx skills add https://github.com/Wcof/PMSkill --skill pm-cohort

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps product teams make sense of cohort and retention data by turning raw user behavior metrics into actionable product insights. Instead of stopping at a heatmap or a table of percentages, it identifies which user cohorts are underperforming, how retention and feature adoption differ over time, and what follow-up research should happen next.

Core Features & Use Cases

  • PMContext-grounded cohort analysis: Derives retention metrics, cohort dimensions, and adoption thresholds directly from PMContext so the analysis stays aligned with product goals and definitions.
  • Retention and adoption pattern detection: Builds cohort retention views, compares feature adoption curves, flags underperforming or unusual cohorts, and marks insufficient data when pattern detection is unreliable.
  • Research-ready output: For every abnormal cohort, it adds a hypothesis, a validation path, and traceability back to the PMContext metric source.
  • Use Case: When monthly signup cohorts show declining D7 and D30 retention, this Skill can pinpoint which month dropped most, connect the drop to onboarding or feature discovery changes, and recommend targeted interviews or experiments.

Quick Start

Ask the agent to use pm-cohort to analyze your signup or activation cohorts against PMContext retention thresholds and identify anomalous cohorts with likely causes and validation steps.

Frequently Asked Questions about pm-cohort

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I identify abnormal user cohorts from retention heatmaps?

Cohort analysis identifies abnormal user groups by comparing retention curves and feature adoption data against PMContext thresholds, flagging underperforming cohorts with traceable conclusions and validation paths.

What is the best way to analyze churn patterns in signup cohorts?

Analyzing churn patterns in signup cohorts involves tracking D7 and D30 retention changes over time, pinpointing specific months with declining retention, and connecting those anomalies to onboarding or feature discovery changes.

How do I find out why feature adoption dropped for a specific user cohort?

Feature adoption drops are investigated by comparing adoption curves across cohort dimensions, detecting anomalies against defined thresholds, and generating targeted interview or experiment recommendations to validate the underlying hypothesis.

Do I need PMContext definitions to run cohort retention analysis?

Yes, cohort retention analysis requires PMContext-derived retention metrics and user-scenario-based cohort dimensions to ensure threshold-based validation and anomaly detection remain aligned with product goals.

What should I do when cohort pattern detection shows insufficient data?

When pattern detection shows insufficient data, cohort analysis marks the anomaly as unreliable, requiring you to wait for more retention data or adjust cohort dimensions before drawing churn conclusions.