diagnose-retention

Analyze cohort-based retention to identify churn drivers and create actionable plans.

142|16|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/amplitude/builder-skills --skill diagnose-retention
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: diagnose-retention
Source: https://github.com/amplitude/builder-skills/tree/main/growth-skills/skills/diagnose-retention
Command: npx skills add https://github.com/amplitude/builder-skills --skill diagnose-retention

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Diagnose churn drivers by cohort, identify behaviors that predict retention, and craft a concrete plan to bend the retention curve.

Core Features & Use Cases

  • Cohort-based retention analysis to reveal how different segments churn and why.
  • Identification of 3-5 retention-predictive behaviors with quantification, causality assessment, and actionability.
  • A structured retention plan with prioritized interventions across habit formation, churn interventions, and structural retention.

Quick Start

Execute a cohort-based analysis by loading activation events and signups to surface retention curves and actionable predictors.

Frequently Asked Questions about diagnose-retention

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

FAQPage Schema
How do I diagnose churn drivers and identify behaviors that predict retention?

Identify churn drivers by applying cohort decomposition to segment retention data and isolate predictive behaviors using event-level activation signals. This approach quantifies causality to reveal why specific user groups churn over time.

What is the best way to analyze D1-D30 retention across different user cohorts?

Analyzing D1-D30 retention requires loading cohort data and activation events to surface retention curves and segment differences. This reveals how distinct user groups drop off, allowing you to target interventions based on activation status.

How do I build a structured retention plan to bend the retention curve?

Build a retention plan by prioritizing interventions across habit formation, churn interventions, and structural retention. Link predictive behaviors to measurable retention improvements to systematically bend the curve and reduce churn.

What data do I need to identify retention-predictive behaviors and activation status?

You need cohort data, event-level activation signals, and signups to identify retention-predictive behaviors. Loading these inputs allows you to segment users by activation status and quantify which specific actions predict long-term retention.

Can I use cohort decomposition to target churn interventions for specific product segments?

Yes, cohort decomposition isolates how different segments churn and why, allowing you to target churn interventions precisely. By quantifying 3-5 predictive behaviors, you can apply prioritized habit formation strategies to the highest-risk cohorts.