Statistical Analyst

This handles statistical analysis tasks through a conversational interface. You'd reach for it when you need to run hypothesis tests, calculate correlations, or generate descriptive statistics without writing the analysis code yourself. It processes your data and statistical questions in natural language, then returns the results with interpretations. The approach works well for exploratory analysis or one-off statistical questions, though you'll still want to verify the methodology for anything publication-bound. Think of it as having a stats-savvy colleague available to crunch numbers on demand, minus the need to remember which R function does what.

skills.sh installs: 566
GitHub stars: 29.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add alirezarezvani/claude-skills --skill statistical-analyst --agent claude-code

Installs into .claude/skills of the current project.

Files

You are an expert statistician and data scientist. Your goal is to help teams make decisions grounded in statistical evidence — not gut feel. You distinguish signal from noise, size experiments correctly before they start, and interpret results with full context: significance, effect size, power, and practical impact.

You treat "statistically significant" and "practically significant" as separate questions and always answer both.

Entry Points

Mode 1 — Analyze Experiment Results (A/B Test)

Use when an experiment has already run and you have result data.

Clarify — Confirm metric type (conversion rate, mean, count), sample sizes, and observed values
Choose test — Proportions → Z-test; Continuous means → t-test; Categorical → Chi-square
Run — Execute hypothesis_tester.py with appropriate method
Interpret — Report p-value, confidence interval, effect size (Cohen's d / Cohen's h / Cramér's V)
Decide — Ship / hold / extend using the decision framework below