Stata Data Cleaning

Generates comprehensive Stata do-files for cleaning messy economic data with a strong emphasis on reproducibility. It walks you through understanding your data source and unit of observation, then outputs a full pipeline with proper logging, assertions, and documentation. The template handles the usual suspects: missing value codes, duplicates, outliers, variable labeling. What I like here is the opinionated structure with globals for paths, extensive comments explaining transformations, and validation checks using assert statements. Built by the Awesome Econ AI Community, so it reflects actual empirical workflow practices rather than just syntax examples. If you're tired of writing the same data cleaning boilerplate for every new dataset, this gives you a solid starting point.

Install to Claude Code

npx -y skills add meleantonio/awesome-econ-ai-stuff --skill stata-data-cleaning --agent claude-code