# exploratory-data-analysis

A Claude skill that identifies a scientific file's format and writes a markdown report on its structure, quality and next analysis steps.

- skill · `type=skill` · Claude Code · 279 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/scientific/exploratory-data-analysis
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/exploratory-data-analysis

## What it does

Point the skill at a file path and it reads the extension, then looks it up across six reference categories: chemistry and molecular formats, bioinformatics and genomics, microscopy and imaging, spectroscopy, proteomics and metabolomics, and general scientific data. Over 200 extensions are covered, from `.pdb` and `.fastq` to `.hdf5` and `.ome.tiff`. Each entry describes what data the format usually holds, which Python libraries read it, and what analysis fits.

You can run the bundled `scripts/eda_analyzer.py`, which detects the type, loads the reference entry and produces a markdown report. Or work in the conversation: check dimensions and missing values for tables, length distributions and quality scores for sequences, channel and calibration metadata for images. The report layout lives in `assets/report_template.md`.

Expect to install the Python library for whichever format you open — the skill names it in the reference, it does not install anything for you. A file whose extension is not in the references will not be detected automatically, so you fall back to manual inspection.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --skill scientific/exploratory-data-analysis
```

2. **Skills CLI (Vercel)**
```bash
npx skills add davila7/claude-code-templates --skill exploratory-data-analysis -a claude-code
```

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

### Codex

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

### Cursor

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install davila7/claude-code-templates exploratory-data-analysis
```

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

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/scientific/exploratory-data-analysis
```

### Windsurf (Devin Desktop)

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

### 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/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/scientific/exploratory-data-analysis

## When to use it
- figure out what is inside an unfamiliar scientific file
- assess data quality and completeness before analysis
- pick the right Python library for a given format
- produce a markdown dataset report for documentation
- decide which analysis suits this data type

## Example prompts
- analyze data.fastq and show me the report
- explore this .hdf5 file: shapes, dtypes, missing values
- run EDA on results.mzML and suggest preprocessing steps

## Similar
- [Exploratory Data Analysis](https://affpapa.org/en/nevibecode/skills/aj-geddes-exploratory-data-analysis.md) — skill · 513 installs
- [analytics-data-analysis](https://affpapa.org/en/nevibecode/skills/analytics-data-analysis.md) — skill · 1100 installs
- [tooluniverse-sdk](https://affpapa.org/en/nevibecode/skills/tooluniverse-sdk.md) — skill · 397 installs
- [statistical-analysis](https://affpapa.org/en/nevibecode/skills/anthropics-statistical-analysis.md) — skill · 4600 installs
- [data-analysis](https://affpapa.org/en/nevibecode/skills/akillness-data-analysis.md) — skill · 598 installs
- [Time Series Analysis](https://affpapa.org/en/nevibecode/skills/time-series-analysis.md) — skill · 605 installs

## Other versions with the same name
- [exploratory-data-analysis · k-dense-ai](https://affpapa.org/en/nevibecode/skills/k-dense-ai-exploratory-data-analysis.md) — 2100 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 224 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