Csv data cleaning

---
name: csv-data-cleaning
description: "Inspects a messy CSV and proposes cleaning steps: types, missing values, duplicates and inconsistent labels. Use before analysing a dataset."
---

# Csv data cleaning

Clean data is data whose problems you have written down.

## How to work

1. Load the file and report rows, columns, types and sample values.
2. Find missing values, duplicates, outliers, mixed formats and inconsistent spellings.
3. Propose a fix for each problem and say what it changes.
4. Apply the fixes to a copy, never the original.
5. Report before and after counts.

## Rules

- Do not drop rows silently.
- Keep a log of every change.

## Output

A problem list, the cleaning script, and a before-and-after summary.

How to use it

1. Download the skill.
2. Put its folder (with SKILL.md inside) in .claude/skills/csv-data-cleaning/ for just this project, or in ~/.claude/skills/ for every project.
3. Restart your tool and ask for what the skill does. It loads on its own when it fits.

Try it

Clean this customers.csv and tell me what you changed.

Copy prompt