data-analysis

Runs end-to-end R data analysis producing regression results and publication-ready tables and figures.

4|Updated Aug 22, 2025
One-click install
npx skills add https://github.com/stevejbickley/arcbita-geek-seminars --skill data-analysis-stevejbickley
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-analysis
Source: https://github.com/stevejbickley/arcbita-geek-seminars/tree/main/sessions/2026-07-29-ClaudeCodeforAppliedSocialScience/starter/.claude/skills/data-analysis
Command: npx skills add https://github.com/stevejbickley/arcbita-geek-seminars --skill data-analysis-stevejbickley

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It automates the full empirical research workflow in R — from loading a dataset through exploration, regression analysis, and publication-ready output — so researchers avoid writing boilerplate analysis scripts and manually formatting tables and figures. ## Core Features & Use Cases - Phased Analysis Pipeline: Structured workflow covering pre-flight data inspection, exploratory analysis, regression modeling, and output generation. - Publication-Ready Output: Generates regression tables with modelsummary and figures with ggplot2, exported as .tex, .html, .pdf, and .png. - Convention Enforcement: Follows project R code conventions, saves all objects with saveRDS(), and runs an automated code review before presenting results. - Use Case: A researcher points the skill at a county panel CSV and asks for a regression of wages on education with state fixed effects; it produces numbered R scripts, clustered-standard-error estimates via fixest, and formatted tables and figures. ## Quick Start Ask the assistant to analyze the dataset at data/county_panel.csv and run a regression of wages on education with state fixed effects.

Frequently Asked Questions about data-analysis

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

FAQPage Schema
How do I run a full regression analysis on a CSV file in R?▼

Provide the dataset path and describe the analysis goal, such as regressing wages on education with fixed effects. The workflow loads the data, runs exploratory diagnostics, estimates the regression with fixest or lm, and exports tables and figures.

What R packages does this analysis workflow use?▼

The workflow uses tidyverse for data manipulation, fixest for panel regressions, modelsummary for regression tables, and ggplot2 for figures. Scripts load packages with library() at the top and set a seed in YYYYMMDD format.

Does it support panel data and clustered standard errors?▼

Yes, panel regressions use the fixest package, and standard errors are clustered at the appropriate level with the reasoning documented. Cross-sectional data uses lm or glm instead.

What output formats are generated for tables and figures?▼

Regression tables are exported as .tex for LaTeX and .html for quick viewing. Figures are saved as both .pdf and .png with explicit dimensions, and all computed objects are persisted with saveRDS().

How are long-running regressions or simulations handled?▼

Long-running fits are launched in the background with Rscript and monitored via the Monitor tool, which streams R stdout in real time. This avoids polling loops and lets the workflow react to milestones as they occur.