What it does

This skill helps agents calculate and interpret statistical significance for experiments and datasets. It provides step-by-step guidance for selecting appropriate tests (t-test, chi-square, ANOVA), computing p-values, confidence intervals, and power analyses, and generating production-ready code and configurations for common data stacks.

When to use it

Use this skill when you need to:

Determine whether observed differences are statistically significant
Choose and run the right hypothesis test for your data (continuous vs categorical)
Generate reproducible code (Python/R/SQL) to compute p-values, effect sizes, and confidence intervals
Validate analytics pipelines and check assumptions (normality, variance homogeneity, sample size/power)

What's included

Scripts: none detected in the repo entry, but the skill provides example code patterns and validation steps in the instructions.
References: none bundled, but the skill points to standard statistical best practices and industry guides.
Instructions: clear procedural guidance for selecting tests, running calculations, and handling errors or missing data; example requests and expected outputs are included in the skill body.