pm-metrics

Review product metrics to identify root causes and actionable insights.

215|26|Updated Dec 15, 2025
One-click install
npx skills add https://github.com/serejaris/personal-corp-skills --skill pm-metrics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pm-metrics
Source: https://github.com/serejaris/personal-corp-skills/tree/main/skills/pm-metrics
Command: npx skills add https://github.com/serejaris/personal-corp-skills --skill pm-metrics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

Product teams struggle to turn raw metrics into clear, actionable insights and root-cause diagnoses.

Core Features & Use Cases

  • North Star decomposition (L1/L2) to diagnose growth and engagement drivers
  • Retention diagnostics (D1/D7/D30) and cohort analysis to identify churn patterns
  • Funnel and activation analysis with actionable recommendations
  • A/B experiment readouts and alignment to OKRs

Quick Start

Provide context and numeric data to the agent and ask for a prioritized review.

Frequently Asked Questions about pm-metrics

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

FAQPage Schema
How do I turn raw product metrics into actionable insights and root-cause diagnoses?

To turn product metrics into actionable insights, provide your raw numeric data and context to the agent for a prioritized review. It identifies trends, anomalies, and root causes to generate clear recommendations for your team.

What is North Star metric decomposition and how does it diagnose growth drivers?

North Star metric decomposition breaks down your primary growth metric into L1 and L2 components. This diagnostic process isolates specific engagement and growth drivers, helping you pinpoint exactly which underlying factors impact your product's core value.

How do I analyze D1, D7, and D30 retention cohorts to identify churn patterns?

Retention diagnostics analyze D1, D7, and D30 cohorts to map churn patterns across user lifecycles. By evaluating these cohorts, you can identify exactly when and why users drop off, enabling targeted activation efforts to improve long-term retention.

Can I use this for A/B experiment readouts and OKR pacing alignment?

Yes, the agent supports A/B experiment readouts and OKR pacing alignment. You can apply it after tests or during weekly reviews to surface trends, evaluate experiment impacts, and ensure your metrics align with your OKR targets.

What is the best way to conduct funnel and activation analysis for product drop-off points?

Funnel and activation analysis evaluates user progression through key stages to locate drop-off points. Providing your funnel data to the agent yields actionable recommendations to optimize activation rates and smooth the user journey.