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 set of specialized skills for AI agents (specifically Claude Code and Codex) to assist in the post-writing phase of academic paper preparation. It focuses on polishing, validating, and auditing existing drafts rather than generating content from scratch, helping researchers ensure their manuscripts meet professional standards for formatting, logic, and submission requirements.

How it works

The repository acts as a collection of "skills" that can be installed into an AI agent's environment. Each skill contains specific instructions, scripts, and templates that guide the AI on how to handle different academic tasks. It supports multiple formats including LaTeX (English and Chinese) and Typst, and utilizes external tools like latexmk, chktex, and pdfplumber to perform technical checks and audits.

Who it’s for

Academic researchers and students writing conference papers, journal articles, or dissertations who use LaTeX or Typst and want AI-assisted review and polishing.

Highlights

  • Multi-format Support: Dedicated workflows for English LaTeX, Chinese LaTeX (including GB/T 7714 references), and Typst manuscripts.
  • Paper Auditing: A reviewer-style critique system that identifies blockers, logic gaps, and "AI-like" phrasing without rewriting the source.
  • Bibliography Management: Tools to search, filter, and export citation snippets from local BibTeX/BibLaTeX libraries.
  • Submission Assistance: Specialized skills for generating and aligning cover letters with the manuscript content.
  • Technical Validation: Integration with compilation tools to diagnose blocking errors in LaTeX and Typst documents.

Related

  • Project
    Boom5426/Nature-Paper-Skills

    A repository of agent skills for Claude Code and Codex designed to guide researchers through the high-standard drafting, auditing, and submission process for Nature-series journals.

  • Project
    claesbackman/AI-research-feedback

    A collection of Claude Code skills that automate academic peer review, grant proposal evaluation, and paper-code reproducibility checks for researchers.

  • Project
    pedrohcgs/claude-code-my-workflow

    A ready-to-fork foundation for AI-assisted academic work that uses specialized agents and quality gates to automate the creation and review of papers, slides, and data analysis.

  • Project
    jamditis/claude-skills-journalism

    A genuine open‑source repo that bundles reusable “Agent Skills” for Claude Code (and Codex) to help journalists and newsroom teams automate tasks such as fact‑checking, source verification, FOIA filing, data‑journalism, PDF design, and multi‑agent workflows. Install via Claude’s plugin commands or copy individual `SKILL.md` folders; the repo includes a catalog, docs site, and up‑to‑date skill set.

  • 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.