# data-analysis

A skill that walks the agent through dataset analysis: quality checks first, then the right method, then findings with caveats. Useful when you have an export and need an answer, not just code.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 598 installs · ★ 50
- Author: akillness
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/akillness/jeo-skills/tree/HEAD/.agent-skills/data-analysis/SKILL.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/akillness-data-analysis

## What it does

The skill sets an order for working with a dataset. The agent frames the question and the metric, profiles the data for nulls, duplicates and impossible values, and only then computes. Four patterns are covered: explaining a change, comparing segments, funnel and retention work, and telemetry review. Each comes with its own checklist.

Findings come back in three layers: what the data shows, what it likely means, and what could weaken the conclusion. That keeps observation apart from guesswork. Tool access is limited to `Read`, `Grep`, `Glob` and `Bash` — reading files, searching and running commands, with no code edits.

This is not the skill for anomaly hunting across a codebase or for building a dashboard; the same collection has separate skills for those. When data quality is poor, the agent says what can be trusted instead of forcing conclusions out of a messy extract.

## Install

### Claude Code (native platform)

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

2. **Platform CLI**
```bash
gemini skills install https://github.com/akillness/jeo-skills --path .agent-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 akillness/jeo-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/akillness/jeo-skills/tree/HEAD/.agent-skills/data-analysis/SKILL.md

## When to use it
- check an export for nulls and duplicates before computing
- explain why conversion dropped week over week
- compare channels by both rate and volume
- map an onboarding funnel and find the worst drop-off
- split findings into observation, interpretation and caveat

## Example prompts
- analyze `events.csv`, compute retention by cohort and tell me where it breaks
- compare conversion by channel for last month, show sample size for each
- check the `orders` table for duplicates and nulls, then explain the revenue spike

## Similar
- [data-analyst](https://affpapa.org/en/nevibecode/skills/borghei-data-analyst.md) — skill · 605 installs
- [analyze](https://affpapa.org/en/nevibecode/skills/analyze.md) — skill · 5700 installs
- [analytics-data-analysis](https://affpapa.org/en/nevibecode/skills/analytics-data-analysis.md) — skill · 1100 installs
- [validate-data](https://affpapa.org/en/nevibecode/skills/anthropics-validate-data.md) — skill · 3700 installs
- [Exploratory Data Analysis](https://affpapa.org/en/nevibecode/skills/aj-geddes-exploratory-data-analysis.md) — skill · 513 installs
- [exploratory-data-analysis](https://affpapa.org/en/nevibecode/skills/exploratory-data-analysis.md) — skill · 279 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 · lingzhi227](https://affpapa.org/en/nevibecode/skills/lingzhi227-data-analysis.md) — 2000 installs

From the same set: [akillness/jeo-skills](https://affpapa.org/en/nevibecode/by/akillness/jeo-skills.md) — 29 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