statistical-analysis · davila7 — Claude Code skill: what it does, how to install
Automates hypothesis testing, assumption verification, and APA-formatted summary drafting. Helpful for researchers processing scientific experimental datasets.
npx claude-code-templates@latest --skill scientific/statistical-analysisWhat statistical-analysis does
This skill guides the selection and execution of statistical evaluations tailored to sample properties. It handles comparisons like independent t-tests, one-way ANOVA, chi-square evaluations, and non-parametric substitutes such as Mann-Whitney U. Beyond classical inference, it covers correlation metrics, regression models, and Bayesian estimations using Bayes Factors.
Prior to generating final metrics, the embedded diagnostics evaluate distribution normality, variance homogeneity, and potential outliers. If validation fails, the assistant indicates corrective paths, advising Welch adjustments or non-parametric alternatives.
Calculation routines rely directly on packages like pingouin, scipy.stats, and statsmodels, meaning execution halts without an existing Python runtime. Results arrive structured with effect estimates such as Cohen's d, confidence bands, and publication-ready APA phrasing.
What it helps with
- select the proper statistical test based on dataset distribution
- verify normality and variance homogeneity assumptions
- compute statistical power and estimate target sample size
- draft academic findings according to APA publication guidelines
Example prompts for the agent
- Inspect
experiment.csvfor normality and run an independent t-test across both groups - Estimate the required sample size for a planned study with power set to 0.8 and d = 0.5
- Perform a one-way ANOVA on
dfand format the findings following APA guidelines
How to install statistical-analysis
1claude-code-templates
npx claude-code-templates@latest --skill scientific/statistical-analysis2Skills CLI (Vercel)
npx skills add davila7/claude-code-templates --skill statistical-analysis -a claude-code3Manually: put the files in place
~/.claude/skills/statistical-analysis/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/statistical-analysis/
Manually: put the files in place
.agents/skills/statistical-analysis/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/statistical-analysis/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install davila7/claude-code-templates statistical-analysis2Manually: put the files in place
.github/skills/statistical-analysis/SKILL.mdPlatform CLI
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/scientific/statistical-analysisManually: put the files in place
.devin/skills/statistical-analysis/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.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 statistical-analysis
How do I install statistical-analysis in Claude Code?
Run npx claude-code-templates@latest --skill scientific/statistical-analysis in your terminal. Alternatively, place the file directly at ~/.claude/skills/statistical-analysis/SKILL.md.
What does statistical-analysis do?
It provides a workflow for scientific data analysis, spanning power calculations, diagnostic checks, hypothesis testing, and Bayesian modeling. Output tables and text conform to APA standards.
Which Python packages are required?
Core evaluations depend on scipy, statsmodels, and pingouin. Bayesian analyses require pymc and arviz installed in your environment.
Similar skills
All skills for Science and research →statistical-analysis by other authors comes first.
