bahayonghang/academic-writing-skills

AI-powered post-writing toolkit for academic papers — format validation, grammar/style polishing, de-AI editing, reference checking, and reviewer-style paper audits. 5 skills for LaTeX, Typst & PDF. Focused on enhancing existing text quality, not generating from scratch.

What it solves

This project provides a suite of specialized skills for AI coding assistants (like Claude Code and Codex) to help researchers polish, validate, and audit academic manuscripts. It focuses on improving existing drafts—rather than writing papers from scratch—by automating tedious tasks like format checking, bibliography verification, and grammar analysis.

How it works

It functions as a collection of "skills" that can be installed into AI tools via npx. Each skill is a set of instructions and optional Python helper scripts that guide the LLM to perform specific academic tasks. The system supports multiple document formats including LaTeX and Typst, and integrates with external tools like latexmk, chktex, and pymupdf to ensure technical correctness and document compilation.

Who it’s for

Academic researchers and students writing conference papers, journal articles, or theses (specifically supporting both English and Chinese languages) who want to use AI to refine their technical writing without introducing hallucinations.

Highlights

  • Comprehensive Audit Tools: Includes a paper-audit skill for reviewer-style critiques and blocker triage.
  • Format-Specific Support: Dedicated workflows for LaTeX (English and Chinese) and Typst manuscripts.
  • Bibliography Management: Tools to search, filter, and export citation snippets from local BibTeX/BibLaTeX libraries.
  • Thesis-to-Presentation Pipeline: A specialized skill to build Beamer defense decks from existing XeLaTeX thesis repositories.
  • Writing Studio: Prose polishing with specific profiles for major publishers like Nature, IEEE, and Elsevier.
  • De-AI Editing: Features specifically designed to remove "AI-like" phrasing from academic text.

Related

  • Project
    claesbackman/AI-research-feedback

    A collection of Claude Code skills that provide multi-agent academic reviews for research papers, grant proposals, and pre-analysis plans, including paper-code reproducibility checks.

  • Project
    Yuan1z0825/nature-skills

    A library of 22 packaged AI-agent workflows ("skills") for academic research — paper reading, Nature-style writing, figure generation, reviewer responses, literature search, and patent drafting — installable into Claude Code, Codex, Chatbox, and other agents.

  • Project
    Noi1r/beamer-skill

    An AI coding assistant skill that automates the creation, compilation, and pedagogical review of academic Beamer LaTeX presentations from research papers.

  • Project
    BZDmathclub/bzd-math-modeling-skills

    A comprehensive suite of AI skills for Codex and Claude Code that guides users through the entire mathematical modeling competition process, from problem translation to final paper review.

  • Project
    Boom5426/Nature-Paper-Skills

    A collection of 27 AI agent skills for Codex and Claude Code to help scientists write, revise, and manage rebuttals for Nature-series life science and computational biology papers.