data-dictionary

Generate Markdown codebooks documenting Stata .dta dataset variables and statistics.

1|1|Updated Apr 20, 2026
One-click install
npx skills add https://github.com/eabeam/econ-skills --skill data-dictionary-eabeam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-dictionary
Source: https://github.com/eabeam/econ-skills/tree/main/data-dictionary
Command: npx skills add https://github.com/eabeam/econ-skills --skill data-dictionary-eabeam

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Auto-generate comprehensive data dictionaries for Stata .dta files, capturing variable names, labels, value labels, missingness, and basic statistics to improve reproducibility and understanding.

Core Features & Use Cases

  • Read Stata .dta files to extract variable metadata (names, labels, value labels, types)
  • Produce a Markdown codebook with sections for variables, value labels, and missingness statistics
  • Generate summary statistics for numeric variables and basic metadata in one ready-to-share document
  • Use in research workflows to document datasets before analysis or share with collaborators

Quick Start

Run the data-dictionary skill on a .dta file or directory to generate a Markdown codebook.

Frequently Asked Questions about data-dictionary

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a codebook from a Stata .dta file?

Generate a Stata .dta codebook by running the skill on a single file or directory. It outputs a structured Markdown document with sections for variable names, labels, value labels, missingness, and summary statistics.

What is a data dictionary for Stata datasets?

A Stata data dictionary documents dataset metadata, capturing variable names, labels, value labels, and missingness. It improves reproducibility and understanding by providing a ready-to-share Markdown summary of basic statistics.

Can I document multiple Stata datasets at once?

Yes, apply the tool to a directory containing multiple .dta files to ensure consistent documentation across datasets. It extracts variable metadata and generates a structured Markdown codebook for each file.

Does the codebook include missingness and summary statistics?

Yes, the codebook includes missingness statistics and generates summary statistics for numeric variables. It details variable names, labels, and value labels alongside this metadata in one Markdown document.

What's the best way to document Stata data for reproducible research?

Auto-generate a Markdown codebook detailing variable names, labels, value labels, missingness, and basic statistics. This structured document is suitable for reproducible research workflows and sharing with collaborators.