skills/14-luischanci-claude-code-research-starter/dot-claude/skills/data-analysis/SKILL.md
End-to-end R data analysis workflow from exploration through regression to publication-ready tables and figures.
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research data-analysisInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Run an end-to-end data analysis in R through 5 phases.
.claude/rules/r-code-conventions.mdlibrary() (never require())set.seed() if stochastic elements are involvedoutput/diagnostics/fixest for panel data with fixed effects (see /econometrics-r for detailed patterns)lm/glm for cross-section/causal-inference-r for diagnostics and modern estimators/econometrics-r for spdep/spatialreg patternsmodelsummary (preferred) or stargazer, export as .tex and .htmlggplot2 with project theme, explicit dimensions, white background, 300 DPI.pdf and .pngsaveRDS() for all computed objects# ==============================================================================
# Title: [Analysis Name]
# Author: [Name]
# Date: [YYYY-MM-DD]
# Purpose: [What this script does]
# Inputs: [Data files]
# Outputs: [Tables, figures, RDS files]
# ==============================================================================
# 0. Setup ----
library(tidyverse)
library(fixest)
library(modelsummary)
# 1. Data Loading ----
# 2. Exploratory Analysis ----
# 3. Main Analysis ----
# 4. Tables and Figures ----
# 5. Export ----
All scripts saved to scripts/R/, all outputs to output/.
tools
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
tools
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
tools
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
tools
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".