hanlulong/econ-writing-skill

Agent Skill that transforms AI assistants into expert economics paper writers. Synthesizes 50+ guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Kremer. Compatible with Claude Code and OpenAI Codex.

What it solves

Writing high-quality economics papers requires adhering to strict academic conventions, specific structural formulas, and a clear, jargon-free style. This project provides a structured knowledge base that transforms AI assistants into expert economics writers, helping researchers avoid common AI-generated writing patterns and follow the best practices of Nobel laureates and leading economists.

How it works

It is an "Agent Skill"—a set of structured markdown files (including SKILL.md, identification-strategies.md, and latex-tips.md) that can be integrated into AI coding assistants like Claude Code and OpenAI Codex. These files provide the AI with specific rules, section-by-section formulas (e.g., for abstracts and introductions), and style guides. The AI can then operate in four modes:

  • Drafting: Creating new text with placeholders for specific results.
  • Rewriting: Fixing passive voice and vague language while preserving meaning.
  • Reviewing: Checking text against academic rules and providing a report.
  • Auditing: Simulating three different reviewer perspectives to score the paper on a 100-point rubric.

Who it’s for

Economists, PhD students, and academic researchers who need help drafting, polishing, or reviewing economics papers, grant proposals, and policy briefs, as well as those preparing for the job market (JMP).

Highlights

  • Authoritative Synthesis: Distills advice from over 50 guides by top economists, including Nobel laureates.
  • Identification Strategy Guidance: Tailored writing advice for 13 different empirical strategies, including RCT, DiD, and RDD.
  • Anti-AI Patterns: Specifically designed to eliminate telltale AI writing markers like uniform sentence length and generic phrasing.
  • Comprehensive Academic Workflow: Includes guidance for everything from LaTeX formatting and AEA replication standards to referee responses and dissertation structure.
  • Multi-Perspective Auditing: Simulates a Methodologist, Field Expert, and Writing Critic to provide a rigorous pre-submission check.

Related

  • Project
    K-Dense-AI/scientific-agent-skills

    A collection of 163 standardized skills for AI agents to perform complex scientific research workflows across biology, chemistry, medicine, and physics.

  • Project
    labarba/sciwrite

    An AI agent skill that reviews scientific and engineering manuscripts for writing quality using a systematic five-pass editorial process based on a Stanford course.

  • Project
    joeseesun/qiaomu-meta-skill

    A meta-skill that transforms prompts and workflows into researched, evaluated, and securely published AI agent skill packages.

  • Project
    Yuan1z0825/nature-skills

    A library of reusable research skills for AI agents to automate high-impact academic workflows, from paper reading and Nature-style polishing to peer review simulation and patent drafting.

  • Project
    kangarooking/kangarooking-skills

    A collection of structured, open-source Agent Skills and workflows for AI agents to automate tasks ranging from content creation and 3D generation to complex software engineering.