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.
npx -y skills add anthropics/knowledge-work-plugins --skill statistical-analysis --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
shadcn/improve
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills