The Clo-Author

Your Econ AI Research Assistant for Claude Code

An open-source Claude Code workflow that turns your terminal into a full-service applied econometrics research assistant — from literature review to journal submission.

Built on Pedro Sant’Anna’s claude-code-my-workflow, reoriented for applied econometrics research publication.

You describe a task in plain English. Claude plans the approach, dispatches specialized agents, reviews quality, fixes issues, and presents results. Like a contractor who manages the entire job — 16 agents, 10 commands, all running behind the scenes.

Get Started in 5 Minutes

Step 1: Fork & Clone

gh repo fork hugosantanna/clo-author --clone
cd clo-author

Step 2: Start Claude Code

claude

Using VS Code? Open the Claude Code panel instead. Everything works the same.

Step 3: Paste the Starter Prompt

Fill in the bolded placeholders with your project details:

I am starting a new applied econometrics research project on [YOUR TOPIC]. Read CLAUDE.md and help me set up the project structure. Start with /discover --lit [YOUR TOPIC].

Claude reads the configuration, fills in your project details, and enters contractor mode — planning, implementing, reviewing, and verifying autonomously.

Step 4: Start Working

Once setup is done, just describe what you need:

  • “Review my paper” — checks your identification strategy, code, writing, and LaTeX in parallel
  • /review --methods Paper/main.tex — validates your DiD/IV/RDD assumptions, clustering, and inference
  • /analyze Data/cleaned/survey.csv — cleans data, runs your specification, produces tables and figures
  • /new-project health insurance — walks you through the full pipeline from literature review to submission

What Happens Behind the Scenes

You talk, Claude orchestrates. The 16 agents work in worker-critic pairs — every creator has a paired critic who can’t edit files, only review. Two specialized referees (domain + methods) simulate real journal peer review. The orchestrator dispatches agents based on a dependency graph, enforces quality gates (80/90/95), and routes escalations when critics and creators can’t agree after 3 rounds.

For the full picture: User Guide (what you can do), Meet the Agents (who does the work), Architecture (how the system works), Customization (how to make it yours), and Command Reference (every flag and subcommand).

Day 1 Checklist

That’s it. Everything else — agents, hooks, rules — runs automatically in the background.

If you prefer to configure things yourself instead of letting Claude handle it:

Customize CLAUDE.md — Open CLAUDE.md and replace all [BRACKETED PLACEHOLDERS]:

  1. Project name and institution
  2. Folder structure (adjust to your layout)
  3. Current project state (your papers and analyses)

Fill in the domain profile — Run /discover (interactive interview) or manually edit .claude/rules/domain-profile.md:

  1. Your field and adjacent subfields
  2. Target journals ranked by tier
  3. Common data sources and identification strategies
  4. Field conventions and seminal references

Configure permissions — Review .claude/settings.json. The template includes permissions for git, LaTeX, R, and utility scripts.

Test it:

/tools compile Paper/main.tex
/review --proofread Paper/main.tex

Prerequisites

Tool Required For Install
Claude Code Everything npm install -g @anthropic-ai/claude-code
XeLaTeX Paper compilation TeX Live or MacTeX
R Analysis & figures r-project.org
gh CLI GitHub integration brew install gh (macOS)

Optional: Stata, Python, Julia (multi-language analysis), Quarto (web slides).

Origin

This project is a fork of Pedro Sant’Anna’s claude-code-my-workflow, which was built for Econ 730 at Emory University (6 lectures, 800+ slides). The Clo-Author reorients that infrastructure from lecture production to applied econometrics research publication.

The /humanizer skill is by Siqi Chen, adapted here for academic writing in economics.

Maintained by Hugo Sant’Anna. MIT License — fork it, customize it, make it yours.