metric-diagnosis

Analyze unexpected metric changes with structured root-cause analysis across 4D segments.

1|2|Updated Dec 3, 2025
One-click install
npx skills add https://github.com/jayhjenkins/ProductOSv0.2 --skill metric-diagnosis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: metric-diagnosis
Source: https://github.com/jayhjenkins/ProductOSv0.2/tree/main/.claude/skills/workflows/metric-diagnosis
Command: npx skills add https://github.com/jayhjenkins/ProductOSv0.2 --skill metric-diagnosis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps analysts systematically investigate unexpected metric changes by applying structured root-cause analysis across defined data dimensions and factors to identify true causes rather than quick conclusions.

Core Features & Use Cases

  • 4D segmentation: People, Geography, Technology, and Time to isolate affected segments.
  • Intrinsic vs Extrinsic analysis: Distinguish internal changes (code, experiments) from external events (market, campaigns).
  • Hypothesis testing: Generate and test hypotheses with a structured table and data-driven validation.
  • North Star alignment: Assess impact on top-line metrics and strategic goals.

Quick Start

  1. Provide the metric name, timeframe, and context (e.g., WAU dropped 12% in the last 7 days).
  2. Include any data-quality concerns and available data segments (segments by user type, geography, platform, time).
  3. Request a phased diagnosis covering Phase 1: data quality, Phase 2: hypotheses, Phase 3: hypothesis testing, Phase 4: North Star impact, and Phase 5: recommended actions.

Frequently Asked Questions about metric-diagnosis

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

FAQPage Schema
How do I diagnose unexpected metric changes and find the root cause?

Diagnose metric changes by applying structured root-cause analysis using 4D segmentation across People, Geography, Technology, and Time to isolate affected segments and identify true causes rather than relying on quick conclusions.

What is the best way to investigate a sudden drop in a product metric?

Investigate metric drops through a phased workflow covering data-quality checks, hypothesis generation, hypothesis testing, North Star impact assessment, and recommended actions to produce narrowed scope and validated conclusions.

How do I distinguish intrinsic vs extrinsic factors during root-cause analysis?

Distinguish intrinsic vs extrinsic factors by evaluating internal changes like code or experiments against external events like market shifts or campaigns, applying structured hypothesis testing to validate the true cause.

Can I assess North Star metric impact when diagnosing unexpected product metric shifts?

Assess North Star metric impact by evaluating how the unexpected metric shift affects top-line metrics and strategic goals, incorporating this assessment into the final phased diagnosis and recommended actions.

What data do I need to provide for a structured metric diagnosis?

Provide the metric name, timeframe, context of the change, data-quality concerns, and available data segments by user type, geography, platform, or time to enable a comprehensive phased diagnosis.

How do I test hypotheses when analyzing unexpected metric movements?

Test hypotheses using a structured hypothesis-table method that pairs generated assumptions with data-driven validation across the 4D segmentation dimensions to produce tested, narrowed-scope conclusions.