# csv-data-summarizer

The skill loads a CSV with pandas and returns a full report: column types, missing values, statistics and the charts that fit the dataset. Useful when a dump lands in the chat.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2100 installs · ★ 478
- Author: coffeefuelbump
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/coffeefuelbump/csv-data-summarizer-claude-skill/tree/HEAD/SKILL.md
- Updated: 2025-10-16
- HTML: https://affpapa.org/en/nevibecode/skills/csv-data-summarizer

## What it does

It inspects the file first, then picks the analyses that match the columns it finds. A date column in the name triggers a time-series plot. Two or more numeric columns bring a correlation heatmap. Categorical fields get value distributions and histograms where they make sense.

The behaviour is deliberately pushy: the agent should not stop to ask what you want or hand you a list of options. It runs the analysis, renders every relevant chart and presents the whole thing in one reply. The repo ships `analyze.py` for the logic, `requirements.txt` and a sample dataset at `resources/sample.csv` to test against. Missing values are handled along the way.

You need Python 3.8+ plus pandas 2.0, matplotlib 3.7 and seaborn 0.12 — the script fails on import without them, so set up the environment before calling the agent. Date detection keys off the word date in a column name, which means a column called `dt` or `period` will not be picked up.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add coffeefuelbump/csv-data-summarizer-claude-skill --skill csv-data-summarizer -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add coffeefuelbump/csv-data-summarizer-claude-skill --skill csv-data-summarizer -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add coffeefuelbump/csv-data-summarizer-claude-skill --skill csv-data-summarizer -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install coffeefuelbump/csv-data-summarizer-claude-skill csv-data-summarizer
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add coffeefuelbump/csv-data-summarizer-claude-skill --skill csv-data-summarizer -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/coffeefuelbump/csv-data-summarizer-claude-skill
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add coffeefuelbump/csv-data-summarizer-claude-skill --skill csv-data-summarizer -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/coffeefuelbump/csv-data-summarizer-claude-skill/tree/HEAD/SKILL.md

## When to use it
- get the shape of an unfamiliar export in one pass
- count missing cells and column types in a CSV
- plot a trend from a dated column
- spot correlations between numeric fields
- show how categories are distributed

## Example prompts
- Take `sales_data.csv`, analyze the whole thing and draw the charts
- Look at `orders.csv` and tell me what stands out
- Analyze this customer table and plot the distributions

## Similar
- [xlsx](https://affpapa.org/en/nevibecode/skills/xlsx.md) — skill · 187223 installs
- [google-agents-cli-observability](https://affpapa.org/en/nevibecode/skills/google-agents-cli-observability.md) — skill · 511300 installs
- [caveman-evidence-review](https://affpapa.org/en/nevibecode/skills/caveman-evidence-review.md) — skill · 104500 installs
- [migration](https://affpapa.org/en/nevibecode/skills/migration.md) — skill · 103900 installs
- [performance-optimization](https://affpapa.org/en/nevibecode/skills/performance-optimization.md) — skill · 65200 installs
- [supabase](https://affpapa.org/en/nevibecode/skills/supabase.md) — skill · 8 installs

---
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