Statistical Analysis

anthropics/knowledge-work-pluginsOfficial

Handles the statistical work that comes up in business analytics: descriptive stats with guidance on when to use mean versus median, percentile distributions that tell a richer story than averages alone, trend detection with moving averages and growth rates, and outlier identification using IQR or z-score methods. The hypothesis testing section covers common scenarios like A/B tests and segment comparisons, with a practical framework that emphasizes effect size and business impact over p-values. What I appreciate here is the clear decision tables for which statistical method to use when, and the repeated emphasis on not automatically removing outliers or mistaking statistical significance for practical importance. It assumes you're doing analysis work but aren't a statistician.

skills.sh installs: 4.8K
GitHub stars: 35.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/knowledge-work-plugins --skill statistical-analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

Statistical Analysis Skill

Descriptive statistics, trend analysis, outlier detection, hypothesis testing, and guidance on when to be cautious about statistical claims.

Descriptive Statistics Methodology

Central Tendency

Choose the right measure of center based on the data:

Situation	Use	Why
Symmetric distribution, no outliers	Mean	Most efficient estimator
Skewed distribution	Median	Robust to outliers
Categorical or ordinal data	Mode	Only option for non-numeric
Highly skewed with outliers (e.g., revenue per user)	Median + mean	Report both; the gap shows skew