AI Blocks › Make documents, sheets and slides
Data quality auditor
Give it a dataset. Get a report on gaps, duplicates, odd values and the rules that would catch them.
Data quality auditor 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 Alireza Rezvani
Made by Alireza Rezvani. See the original on GitHub; we copied it as it is, with its licence.
What it does
A health check on any dataset that tells you what is broken, how bad it is, and what to fix first. You end with a single quality score and a ranked repair plan. A full audit profiles the data, then analyses missing values to see whether gaps are random or follow a pattern. It flags outliers with IQR and z-score tests, checks duplicates and cross column logic like end dates before start dates, and scores overall quality. If one column went wrong recently, a targeted scan asks what changed upstream and compares against a good baseline. For live data it proposes five to eight key columns with limits and alerts. It runs Python scripts.
You give it
- The dataset
- What looks wrong, if anything (optional)
- Key columns to protect (optional)
You get
- Data quality score
- Missing value and outlier findings
- Ranked repair plan
- Monitoring checklist
Use it when
- A dashboard number looks wrong and you do not know why.
- You are about to use a new dataset and want to trust it first.
- You need ongoing checks on a live feed.
- Your team needs a ranked list of data fixes.
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 read your files.