statistics-math — Claude Code skill: stats and math for data
A coding-agent skill with Python recipes for statistics, probability, linear algebra and regression. Useful when you need to compute metrics or test a hypothesis.
npx skills add pluginagentmarketplace/custom-plugin-data-engineer --skill statistics-math -a claude-codeWhat statistics-math does
The skill covers the math side of data work. It ships runnable Python examples: descriptive stats with NumPy, distributions and hypothesis tests with SciPy, matrix operations and SVD, regression through statsmodels and scikit-learn. The agent copies a working pattern instead of inventing one.
A/B testing gets its own section. There is a class with a two-sample t-test, a chi-square test and a two-proportion z-test that returns the p-value, effect size and a significance flag. The regression part compares OLS, Ridge and Lasso and prints R² and RMSE for each.
The skill is marked foundational, and that label holds up: without basic Python and NumPy the examples will not run. The tool table lists NumPy 1.26+, SciPy 1.12+, pandas 2.2+, statsmodels 0.14+ and scikit-learn 1.4+. Older pins in your project will break some calls, so check the environment before letting the agent edit code.
What it helps with
- compute descriptive stats for a data array
- test whether two samples differ
- evaluate an A/B test from conversion counts
- reduce dimensionality with SVD
- compare OLS, Ridge and Lasso on the same data
Example prompts for the agent
- compute mean, median and IQR for this array
- run a t-test on the two samples and report the effect size
- evaluate this A/B test: 120 conversions out of 1000 vs 150 out of 1000
How to install statistics-math
1Skills CLI (Vercel)
npx skills add pluginagentmarketplace/custom-plugin-data-engineer --skill statistics-math -a claude-code2Manually: put the files in place
~/.claude/skills/statistics-math/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/statistics-math/
1Skills CLI (Vercel)
npx skills add pluginagentmarketplace/custom-plugin-data-engineer --skill statistics-math -a codex2Manually: put the files in place
.agents/skills/statistics-math/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add pluginagentmarketplace/custom-plugin-data-engineer --skill statistics-math -a cursor2Manually: put the files in place
.cursor/skills/statistics-math/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install pluginagentmarketplace/custom-plugin-data-engineer statistics-math2Manually: put the files in place
.github/skills/statistics-math/SKILL.md1Skills CLI (Vercel)
npx skills add pluginagentmarketplace/custom-plugin-data-engineer --skill statistics-math -a gemini-cli2Platform CLI
gemini skills install https://github.com/pluginagentmarketplace/custom-plugin-data-engineer --path skills/statistics-mathManually: put the files in place
.devin/skills/statistics-math/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add pluginagentmarketplace/custom-plugin-data-engineer --skill statistics-math -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about statistics-math
How do I install statistics-math in Claude?
Run npx skills add pluginagentmarketplace/custom-plugin-data-engineer --skill statistics-math -a claude-code. The skill file lands at ~/.claude/skills/statistics-math/SKILL.md.
What does statistics-math do?
It gives the agent Python patterns for statistics, probability, linear algebra and regression, built on NumPy, SciPy, statsmodels and scikit-learn.
Which library versions does it need?
The tool table lists NumPy 1.26+, SciPy 1.12+, pandas 2.2+, statsmodels 0.14+ and scikit-learn 1.4+. Some examples fail on older versions.
