Statistics Verifier

This gives you structured checklists for fact-checking statistical claims and catching common analysis errors. It covers the basics like verifying sample sizes and checking if conclusions match the data, plus deeper stuff like detecting p-hacking, choosing the right significance tests, and spotting when correlation gets passed off as causation. The red flags table is genuinely useful for quickly identifying sketchy claims. It won't replace domain expertise, but it's a solid starting framework when you need to audit someone's numbers or validate research findings. Most helpful when you're dealing with press releases, research summaries, or any situation where someone might be overselling their data.

skills.sh installs: 218
GitHub stars: 108
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add travisjneuman/.claude --skill statistics-verifier --agent claude-code

Installs into .claude/skills of the current project.

Files

Statistics Verifier

Structured frameworks for verifying statistical claims, validating research methodology, and detecting analytical errors and biases.

Statistical Claim Verification Checklist

Rapid Claim Assessment

CLAIM VERIFICATION PROTOCOL:

1. SOURCE CHECK
   - Who made the claim?
   - What is their expertise and incentive?
   - Where was it published (peer-reviewed, preprint, press release)?
   - Is the original data or study accessible?

2. METHODOLOGY CHECK
   - What type of study (RCT, observational, survey, meta-analysis)?
   - What was the sample size and population?
   - What was the measurement method?
   - Is the statistical test appropriate for the data type?

3. NUMBER SENSE CHECK
   - Does the claim pass a basic plausibility test?
   - Are units and denominators clearly stated?
   - Absolute vs relative numbers — which is being used?
   - Is the base rate provided for context?

4. REPLICATION CHECK
   - Have other studies found similar results?
   - Are the findings consistent across populations?
   - Has anyone attempted and failed to replicate?

SKILL.md on GitHub