Does it support SQL for data analysis?

Yes, the skill includes optimized SQL patterns for common analytical tasks such as Day-N cohort retention and funnel stage mapping.

What is the 'Ship/Extend/Kill' framework?

It is a decision-making matrix provided by the skill that uses statistical signals to recommend whether to fully roll out a feature, extend the experiment runtime, or revert the changes.

What is the Product Analytics skill for Claude Code?

It is a specialized capability that provides Claude with frameworks, rules, and best practices for analyzing product data, evaluating experiments, and making data-informed development decisions.

How does this skill handle A/B test evaluation?

It uses a structured framework that considers hypothesis, sample size, p-values, and confidence intervals to determine if a result is statistically significant and safe to ship.

Product Analytics

Name: Product Analytics
Author: yonatangross

byyonatangross

•

140

•

Analíticas y Monitorización

Analyzes product experiments, retention cohorts, and conversion funnels to drive evidence-based ship or kill decisions.

The Product Analytics skill provides a rigorous framework for transforming raw product data into actionable business intelligence within Claude Code. It empowers teams to evaluate A/B test results with statistical confidence, perform cohort-based retention analysis to identify product-market fit, and diagnose conversion drop-offs within complex user funnels. By integrating statistical foundations like p-values, confidence intervals, and Minimum Detectable Effect (MDE) directly into the development workflow, it ensures that feature rollouts are guided by mathematical evidence rather than intuition, helping developers avoid common pitfalls like peeking bias and sample ratio mismatches.

Características Principales

01Standardized A/B test evaluation templates with built-in statistical significance checks.

02140 GitHub stars

03Statistical foundations guide covering p-values, confidence intervals, and power analysis.

04Multi-stage funnel analysis patterns to identify and prioritize conversion bottlenecks.

05Data-driven Ship/Extend/Kill decision matrix for objective product management.

06Cohort retention analysis frameworks for measuring long-term user engagement and adoption.

Casos de Uso

01Evaluating the statistical significance and business impact of a new feature experiment.

02Generating SQL queries for Day-N retention analysis to measure product-market fit.

03Diagnosing specific drop-off points in a user registration or checkout funnel.

Características Principales

01Standardized A/B test evaluation templates with built-in statistical significance checks.

02140 GitHub stars

03Statistical foundations guide covering p-values, confidence intervals, and power analysis.

04Multi-stage funnel analysis patterns to identify and prioritize conversion bottlenecks.

05Data-driven Ship/Extend/Kill decision matrix for objective product management.

06Cohort retention analysis frameworks for measuring long-term user engagement and adoption.

Casos de Uso

01Evaluating the statistical significance and business impact of a new feature experiment.

02Generating SQL queries for Day-N retention analysis to measure product-market fit.

03Diagnosing specific drop-off points in a user registration or checkout funnel.