How does this skill help with product metrics?

It provides a structured framework to move from raw numbers to actionable insights by answering what changed, why it changed, the business impact, and the recommended next steps.

Does it support funnel and cohort analysis?

Absolutely. It includes specific templates for tracking stage-by-stage drop-offs and defining cohort retention metrics across various windows like D1, D7, and D30.

Can I use this for stakeholder reporting?

Yes, it includes a dedicated Stakeholder Analysis Output Format designed to provide clear, plain-English summaries, key charts, and specific recommended actions with owners and timelines.

How does it handle data uncertainty?

The skill requires a confidence level (High/Medium/Low) for every finding and forces the identification of what the data cannot tell you to ensure honest and accurate reporting.

Product Data Analysis Standard

Name: Product Data Analysis Standard
Author: mohitagw15856

bymohitagw15856

•

295

•

Data Science & ML

Transforms raw product metrics into actionable business decisions using structured frameworks for funnel, cohort, and root-cause analysis.

This skill equips Claude with a rigorous product management framework to analyze data movements and communicate findings effectively to stakeholders. It moves beyond simple data reporting by enforcing the '4-Question Method'—identifying what changed, the root cause, the business impact, and recommended next steps. Whether you are investigating a conversion drop, conducting a cohort study, or performing a funnel deep-dive, this skill ensures every analysis includes confidence levels, evidence-based hypotheses, and clear action items while explicitly calling out data limitations and potential correlations.

Key Features

014-Question Method for structured decision-making (What, Why, So what, Now what)

02295 GitHub stars

03Automated metric triage with multi-dimensional segmentation checks by platform, cohort, and channel

04Comprehensive funnel analysis templates for identifying and investigating specific drop-off points

05Cohort analysis guidelines for tracking long-term retention trends and performance anomalies

06Stakeholder-ready output formats including confidence levels and explicit data caveats

Use Cases

01Analyzing user retention through cohort tables to identify high-performing acquisition channels

02Creating executive-level data summaries for monthly product performance reviews

03Investigating an unexpected drop in conversion rates or sign-up flows

Key Features

014-Question Method for structured decision-making (What, Why, So what, Now what)

02295 GitHub stars

03Automated metric triage with multi-dimensional segmentation checks by platform, cohort, and channel

04Comprehensive funnel analysis templates for identifying and investigating specific drop-off points

05Cohort analysis guidelines for tracking long-term retention trends and performance anomalies

06Stakeholder-ready output formats including confidence levels and explicit data caveats

Use Cases

01Analyzing user retention through cohort tables to identify high-performing acquisition channels

02Creating executive-level data summaries for monthly product performance reviews

03Investigating an unexpected drop in conversion rates or sign-up flows