Econ Writing Skill is an open-source Agent Skill designed to transform AI assistants into expert economics paper writers. It synthesizes best practices from over 50 authoritative guides by leading economists, Nobel laureates, and Clark Medal winners, providing actionable advice tailored for various economics paper types. The skill benefits researchers, academics, and students aiming to improve the quality, structure, and clarity of their economic writing, offering compatibility with Claude Code and OpenAI Codex.

How It Works

This skill operates by distilling complex writing and structural guidance from numerous expert sources into a structured format usable by AI coding assistants. It employs specific formulas for key sections (e.g., Abstract, Introduction), provides detailed strategies for empirical identification methods, and incorporates style rules derived from prominent economists like McCloskey and Cochrane. A core differentiator is its focus on eliminating AI-generated writing patterns and promoting clarity, conciseness, and economic significance, ensuring outputs resemble those of experienced human economists.

Quick Start & Requirements

Installation is straightforward via a single bash command: curl -fsSL https://raw.githubusercontent.com/hanlulong/econ-writing-skill/main/install.sh | bash This installs the skill globally for Claude Code and OpenAI Codex. Alternatively, installation can be done via npx or by cloning the repository. No specific hardware or software prerequisites beyond the compatible AI assistants are mentioned.

Highlighted Details

• Comprehensive Guidance: Covers writing and structure for all paper types (applied, theory, mixed), with dedicated formulas for sections like Abstract (4-part), Introduction (Head's), Model (Glaeser/Varian), and Conclusion (3-part).
• Identification Strategy Support: Offers specific writing advice for 13 common econometric identification strategies (RCT, DiD, IV, RDD, Synthetic Control, etc.).
• Style and Quality Focus: Implements style rules from Cochrane and McCloskey, actively combats AI-generated writing patterns, and includes a title evaluation framework.
• Review and Audit Modes: Features simulated 3-reviewer feedback (Methodologist, Field Expert, Writing Critic) with a 100-point scoring rubric and a 24-item pre-submission checklist.
• Academic Workflow Integration: Provides tailored guidance for job market papers, grant proposals, referee responses, policy briefs, replication packages, and dissertation structuring.

Maintenance & Community

Contributions are welcomed via GitHub issues and pull requests for new sources, examples, or rule refinements. The project is authored by Lu Han. Further community interaction details (e.g., Discord/Slack) are not specified in the README.

Licensing & Compatibility

This project is licensed under the MIT License, permitting broad use, modification, and distribution, including for commercial purposes, with minimal restrictions.

Limitations & Caveats

The skill is specifically tailored for economics papers and does not extend to other academic disciplines or general writing tasks. While it synthesizes a vast array of expert advice, its effectiveness relies on the underlying AI assistant's capabilities and the user's ability to provide necessary context and data placeholders.