Data Analysis

This generates Python statistical analysis code and runs it through a structured 4-round review process to catch mathematical errors, data handling issues, and missing uncertainty measures. It's built for academic research where you need proper test selection, effect sizes, confidence intervals, and p-values that reviewers won't tear apart. The workflow enforces good practices like named sections in your code, appropriate test selection based on data type, and never reporting a point estimate without uncertainty. Comes with helper scripts for statistical summaries and p-value formatting. The multi-round review is the real value here, it systematically checks things you'd otherwise catch only after running the analysis and realizing your t-test assumptions were violated.

skills.sh installs: 2K
GitHub stars: 459
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add lingzhi227/agent-research-skills --skill data-analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

Data Analysis

Generate rigorous statistical analysis code with multi-round review.

Input

$0 — Data source (CSV, JSON, pickle, or experiment logs)
$1 — Research goal or hypothesis to test

References

4-round code review prompts: ~/.claude/skills/data-analysis/references/review-prompts.md

Scripts

Statistical summary and comparison

python ~/.claude/skills/data-analysis/scripts/stat_summary.py --input results.csv --compare method --metric accuracy --output summary.json
python ~/.claude/skills/data-analysis/scripts/stat_summary.py --input results.csv --describe

Detects data types, recommends tests, runs comparisons, outputs effect sizes and significance stars. Requires numpy, scipy.

Format p-values

python ~/.claude/skills/data-analysis/scripts/format_pvalue.py --values "0.001 0.05 0.23" --format stars
python ~/.claude/skills/data-analysis/scripts/format_pvalue.py --csv results.csv --column pvalue --format latex

Formats p-values with stars, LaTeX notation, or plain text. Stdlib-only.