data-analysis

Analyze empirical datasets with regressions and export tables and figures.

Updated Feb 26, 2026
One-click install
npx skills add https://github.com/naj2r/claude-econ-paper-template --skill data-analysis-naj2r
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-analysis
Source: https://github.com/naj2r/claude-econ-paper-template/tree/main/.claude/skills/data-analysis
Command: npx skills add https://github.com/naj2r/claude-econ-paper-template --skill data-analysis-naj2r

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill orchestrates end-to-end empirical data analysis workflows so researchers can load datasets, explore distributions and missingness, estimate regressions with appropriate fixed effects and clustered standard errors, and produce publication-ready tables and figures without manual pipeline assembly.

Core Features & Use Cases

  • Language-aware scripting: Produce Stata .do files or R scripts depending on user preference, defaulting to Stata for regressions and R for visualizations.
  • Structured workflow phases: Follow conventions for setup, exploratory analysis, main regressions (county+year fixed effects), publication-ready output, and verification.
  • Reproducible outputs: Export regression results to CSV, generate .tex tables (esttab/modelsummary), and save figures with explicit dimensions for Overleaf and Quarto workflows.
  • Use Case: Run a panel regression with clustered standard errors, export the regression table to .tex, and save diagnostic plots to the output/ directory for inclusion in the manuscript.

Quick Start

Run the data-analysis skill on a dataset path and specify Stata or R to generate scripts, run regressions, and export tables and figures.

Frequently Asked Questions about data-analysis

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

FAQPage Schema
How do I automate regression analysis and export publication-ready tables from Stata or R?

You can automate regression analysis and export publication-ready tables by generating Stata .do files or R scripts that estimate fixed-effects regressions with clustered standard errors and output .tex tables using esttab or modelsummary.

What is the best way to run panel data regressions with clustered standard errors and save diagnostic plots?

The best way to run panel data regressions with clustered standard errors and save diagnostic plots is to use a structured workflow that applies county and year fixed effects, then exports figures with explicit dimensions to the output directory.

Can I generate both .tex tables and CSV results for my empirical research dataset?

Yes, you can generate both .tex tables and CSV results for empirical research datasets. The workflow produces publication-ready regression outputs alongside raw CSV results while following repository conventions for reproducibility.

Does this data analysis workflow support cross-sectional datasets or is it limited to panel data?

The data analysis workflow supports both cross-sectional and panel datasets. It applies appropriate fixed effects and clustered standard errors depending on your dataset structure, using either Stata for regressions or R for visualizations.

How do I create reproducible .do or .R scripts for exploratory data analysis and missingness checks?

To create reproducible .do or .R scripts for exploratory data analysis and missingness checks, follow structured setup phases that load datasets, explore distributions, and generate scripts saved to the repository for transparent research pipelines.

Are the exported figures formatted correctly for Overleaf and Quarto manuscript workflows?

Yes, the exported figures are formatted for Overleaf and Quarto workflows. The output generation phase saves plots with explicit dimensions and naming conventions, ensuring seamless integration into publication-ready LaTeX or Quarto documents.