Data cleaner

Give it a messy dataset. Get missing values, duplicates, wrong types and outliers fixed.

Data cleaner is a free AI skill for the job "Make documents, sheets and slides". Give the instructions to an AI assistant that supports the required files and tools, then review its output.

Free · No account · MIT licence · Made by Burhan Sebin · Level: beginner · Thinking: low

Made by Burhan Sebin. See the original on GitHub; we copied it as it is, with its licence.

What it does

A messy file becomes analysis ready, with a log of every change made. You see exactly what was fixed and can undo or adjust it. First it profiles the data: nulls per column, duplicate rows and mixed types. Then it fills gaps by column, using medians for light numeric gaps and an Unknown label for categories. It removes exact duplicates and checks near duplicates, such as rows that differ only by spacing or capital letters. It converts dates and numbers to proper types and standardises formats. Outliers are found with the 1.5 times IQR rule or z-scores, and you choose between capping, blanking or keeping them. A final validation reports anything still wrong. It uses Python.

You give it

The raw data file
Expected column types and ranges (optional)
How to treat outliers (optional)

You get

Cleaned dataset file
Log of every transformation
Data quality report
List of remaining issues

Use it when

A CSV from a supplier has blank cells, duplicates and dates in three formats.
You need clean data before building a report.
Your customer list has the same person twice with different spelling.
Numbers are stored as text and break your formulas.

How to use it

Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
Ask for the job in your own words. Your AI opens the skill when it fits.
It works best when your AI can run code and open spreadsheets.