# data-analysis

Writes statistical analysis code for a paper: picks a test that fits the data and reports p-values, effect sizes and confidence intervals.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2000 installs · ★ 433
- Author: lingzhi227
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/lingzhi227/agent-research-skills/tree/HEAD/skills/data-analysis/SKILL.md
- Updated: 2026-02-27
- HTML: https://affpapa.org/en/nevibecode/skills/lingzhi227-data-analysis

## What it does

The skill takes a data source (CSV, JSON, pickle or experiment logs) plus the hypothesis you want to check. It then lays out an analysis script in sections: imports, loading the data, dataset preparation, descriptive statistics, preprocessing, the tests themselves, and saving extra results to pickle.

That code goes through four review rounds. The first hunts for mistakes in the maths and statistics. The second looks at data handling: missing values, units, exclusion criteria. Rounds three and four check tables for plausible values, uncertainty measures, and consistency across the whole report. A test-selection table ships inside the skill: t-test and Mann-Whitney for two groups, ANOVA and Kruskal-Wallis for several, chi-square and Fisher's exact for categorical data, plus correlation and regression.

Two helper scripts come along. `stat_summary.py` detects data types, suggests a test, runs comparisons and returns effect sizes with significance stars; it needs `numpy` and `scipy`. The other, `format_pvalue.py`, renders p-values as stars, LaTeX or plain text and uses only the standard library. Analysis is limited to `pandas`, `numpy`, `scipy`, `statsmodels`, `sklearn` and `pickle`, so a different stack is out of scope.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill data-analysis -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/data-analysis/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/data-analysis/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill data-analysis -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/data-analysis/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill data-analysis -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/data-analysis/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lingzhi227/agent-research-skills data-analysis
```

2. **Manually: put the files in place**
- File: `.github/skills/data-analysis/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill data-analysis -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/lingzhi227/agent-research-skills --path skills/data-analysis
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/data-analysis/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lingzhi227/agent-research-skills --skill data-analysis -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/lingzhi227/agent-research-skills/tree/HEAD/skills/data-analysis/SKILL.md

## When to use it
- pick a statistical test that matches the data type and group count
- attach a confidence interval or p-value to every reported estimate
- handle missing values, units and exclusion rules before tests run
- check that values and uncertainty measures agree across tables
- convert p-values into stars or LaTeX for typesetting

## Example prompts
- Analyse `results.csv`, compare methods on accuracy and report effect sizes
- Test the group difference in `experiment.json` and write up a report with confidence intervals
- Format the pvalue column of `results.csv` as LaTeX

## Similar
- [anysearch](https://affpapa.org/en/nevibecode/skills/anysearch.md) — skill · 38500 installs
- [academic-paper](https://affpapa.org/en/nevibecode/skills/academic-paper.md) — skill · 10800 installs
- [nature-figure](https://affpapa.org/en/nevibecode/skills/nature-figure.md) — skill · 18800 installs
- [academic-paper-reviewer](https://affpapa.org/en/nevibecode/skills/academic-paper-reviewer.md) — skill · 9800 installs
- [nature-polishing](https://affpapa.org/en/nevibecode/skills/nature-polishing.md) — skill · 17500 installs
- [nature-citation](https://affpapa.org/en/nevibecode/skills/nature-citation.md) — skill · 15600 installs

## Other versions with the same name
- [data-analysis · bytedance](https://affpapa.org/en/nevibecode/skills/bytedance-data-analysis.md) — 3600 installs
- [data-analysis · claude-office-skills](https://affpapa.org/en/nevibecode/skills/data-analysis.md) — 7900 installs
- [data-analysis · akillness](https://affpapa.org/en/nevibecode/skills/akillness-data-analysis.md) — 598 installs

From the same set: [lingzhi227/agent-research-skills](https://affpapa.org/en/nevibecode/by/lingzhi227/agent-research-skills.md) — 31 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md