Data Cleaning Pipeline

This handles the standard data cleaning workflow: dealing with missing values, spotting outliers, removing duplicates, and standardizing formats. You'd reach for it when you're staring at messy raw data that needs to be analysis-ready. It's designed for building automated preprocessing pipelines, which is honestly where most data work time goes. The repo has 245 stars and sits in a collection of AI prompts, so it's likely a prompt template rather than executable code. Worth noting that the actual implementation details are light in the source, so you'll want to check the full SKILL.md to see exactly what techniques and approaches it covers before adding it to your workflow.

GitHub stars: 317
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add aj-geddes/useful-ai-prompts --skill 'Data Cleaning Pipeline' --agent claude-code

Installs into .claude/skills of the current project.

Files

Data Cleaning Pipeline

Overview

Data cleaning pipelines transform raw, messy data into clean, standardized formats suitable for analysis and modeling through systematic handling of missing values, outliers, and data quality issues.