What are 'vanity metrics' in the context of this skill?

Vanity metrics are volume-based numbers like total sign-ups that don't reflect actual product quality or user retention; this skill helps you identify and avoid them.

Is this skill grounded in specific industry standards?

Yes, it is grounded in standards like SWEBOK, AIPMM, and insights from industry-leading books like 'Lean Analytics' and 'Inspired'.

Can this skill help with cohort analysis?

Yes, it includes specific instructions for tracking user groups over time to identify behavior patterns and improve long-term retention.

How does the Retention Analysis skill improve product management?

It provides standardized frameworks for measuring success, helping PMs focus on meaningful metrics rather than vanity numbers, and guides them through structured experimentation.

Product Retention Analysis

Name: Product Retention Analysis
Author: sethdford

bysethdford

•

Analytics & Monitoring

Measures product performance and customer behavior through structured measurement frameworks and experiment plans.

The retention-analysis skill empowers product managers to move beyond vanity metrics by establishing clear, data-informed measurement frameworks. It provides structured guidance on building metric hierarchies, distinguishing between leading and lagging indicators, and conducting deep-dive cohort analyses to understand user trends over time. Whether you are designing a new experiment or setting up a performance dashboard, this skill ensures your analytics are grounded in industry standards like SWEBOK and AIPMM, helping you avoid common pitfalls like over-tracking or failing to investigate the cause of metric shifts.

Key Features

015 GitHub stars

02Leading vs. Lagging Indicator Mapping

03Experimentation Velocity and Success Criteria

04Automated Anti-pattern Detection for Vanity Metrics

05Cohort Analysis and User Group Tracking

06Metric Hierarchy Construction (North Star to Diagnostic)

Use Cases

01Defining success metrics and targets for a new product feature launch

02Designing a structured experiment plan to improve user churn rates

03Establishing a baseline performance framework for a product audit

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add sethdford/claude-skills retention-analysis

For use in Claude.ai and ChatGPT

Key Features

015 GitHub stars

02Leading vs. Lagging Indicator Mapping

03Experimentation Velocity and Success Criteria

04Automated Anti-pattern Detection for Vanity Metrics

05Cohort Analysis and User Group Tracking

06Metric Hierarchy Construction (North Star to Diagnostic)

Use Cases

01Defining success metrics and targets for a new product feature launch

02Designing a structured experiment plan to improve user churn rates

03Establishing a baseline performance framework for a product audit

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add sethdford/claude-skills retention-analysis

For use in Claude.ai and ChatGPT