Data Cleaning Log

Clean a messy dataset and produce a documented log of every change and why. Use for raw exports, CRM dumps, survey files, duplicates, or preparing a file for analysis.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add eshmith7/claude-skills-library --skill data-cleaning-log
Manual install
git clone --depth 1 https://github.com/eshmith7/claude-skills-library.git /tmp/claude-skills-library
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills-library/data-skills/data-cleaning-log ~/.claude/skills/data-cleaning-log

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Data Cleaning and Prep Log

Cleaning a file is easy. Defending it three weeks later is not. When somebody asks why this month's number does not match last month's, the answer is almost always an undocumented cleaning decision that nobody wrote down. This skill cleans the file and writes the log that survives the question.

## When to use this

Trigger on: clean this data, fix this file, remove duplicates, standardise these values, prepare this for analysis, "this export is a mess", "why are there two versions of the same customer".

Also run this first whenever another analysis is requested on an obviously raw file. Analysis on dirty data produces a confident wrong answer, which is worse than no answer.

## Before you start

Required: the file.

Ask, briefly, only what you cannot infer:
1. What one row is supposed to represent. This is the single most useful question, and getting it wrong makes everything downstream wrong.
2. What the file will be used for. Cleaning for a headline count is different from cleaning for a customer-level join.
3. Whether any column is a key that must stay unique.

## Check for personal data before anything else

Scan the columns for anything that identifies a person: names, email addresses, phone numbers, addresses, PIN codes, customer IDs tied to individuals, government identifiers, dates of birth.
Read the full skill on GitHub

Details

Skill name
data-cleaning-log
Path
data-skills/data-cleaning-log/SKILL.md
Repo updated
9 September 2026

FAQ

What does the Data Cleaning Log skill do?

Clean a messy dataset and produce a documented log of every change and why. Use for raw exports, CRM dumps, survey files, duplicates, or preparing a file for analysis.

How do I install the Data Cleaning Log skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add eshmith7/claude-skills-library --skill data-cleaning-log. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Data Cleaning Log popular?

It lives in eshmith7/claude-skills-library, which has 5 GitHub stars and 1 forks.

Related skills

Browse the most popular Claude skills, all marketing, sales & business skills, or write your own with the skills generator.