Claude Code Skills for Empirical Research

A collection of custom Claude Code skills designed for empirical research in economics and finance. These skills provide structured workflows for common academic research tasks.

Installation

To use these skills, copy the .md files to your Claude Code commands directory:

# Copy all skills to your Claude commands folder
cp *.md ~/.claude/commands/

After installation, you can invoke any skill in Claude Code using /skill-name (e.g., /robustness).

The skills/ directory holds a second set in the newer agent skill format (a folder per skill, each with a SKILL.md and YAML frontmatter). Those install to a different location:

# Copy the agent skills to your Claude skills folder
cp -R skills/* ~/.claude/skills/

Claude invokes these automatically when a task matches the skill’s description; you can also call one by name. See Agent Skills below.

Available Skills

1. Robustness (/robustness)

Purpose: Comprehensive checklist of empirical robustness tests for finance/economics papers.

Features:

• Core robustness categories: alternative samples, specifications, measures
• Identification tests: placebo, pre-trends, IV diagnostics
• DiD-specific tests (parallel trends, Bacon decomposition, Callaway-Sant’Anna)
• IV-specific tests (first-stage F, weak instrument inference)
• Referee-proof minimum requirements
• Reporting templates for robustness tables

Usage:

/robustness
> "robustness checklist"     # Full checklist for current paper
> "DiD robustness"           # DiD-specific tests only
> "referee-proof"            # Most commonly requested tests

---

2. Literature Review (/lit-review)

Purpose: Systematically summarize academic papers, extract key findings, and identify research gaps.

Features:

• Structured paper summary template
• Data & methodology extraction
• Comparison tables across multiple papers
• Literature gap analysis framework
• BibTeX generation

Usage:

/lit-review
> "summarize this paper"     # Full template
> "quick summary"            # Citation, question, finding, relevance
> "compare papers"           # Comparison table
> "find gaps"                # Identify research gaps

---

3. Coding Guidelines (/coding-guidelines)

Purpose: Standardized Python & Stata coding practices for empirical research projects.

Features:

• Project directory organization
• Python script templates with path management
• Stata script templates with global macros
• Data loading, merging, and validation patterns
• Visualization standards (matplotlib/seaborn)
• Output table conventions (outreg2/esttab)