academic-paper-writer

This Skill addresses the issues of messy formatting, cumbersome reference management, and difficulties in multi-format conversion during the academic paper writing and typesetting process. In practical research, scholars and students often need to convert PDF scans, Word drafts, or Markdown documents into properly formatted documents that meet journal or conference requirements. Manual formatting adjustments are time-consuming and error-prone.

Usage is straightforward: simply place the source file (PDF, DOC, DOCX, or MD) in the project root directory, and optionally provide a format template (e.g., an IEEE template) and a BibTeX reference file. The system automatically detects the file type and selects the appropriate processing pipeline (OCR pipeline, re-typesetting pipeline, or MD direct-conversion pipeline) to generate a standardized DOCX document and a BibTeX file. You can then use natural language instructions to control typesetting details, crop images, perform incremental generation, or resume from a breakpoint.

It is particularly suitable for researchers, graduate students, and university faculty who frequently write academic papers, especially those needing to unify drafts in various formats into a fixed template. It is also ideal for document engineers handling batch conversion and typesetting of multi-format documents.

It is recommended to clean up old intermediate files before starting a new task to avoid content confusion. Note that it primarily relies on Node.js and Python helper scripts; using the OCR pipeline for the first time may require installing additional dependencies (such as Tesseract). For processing large PDF files, it is advisable to handle them in sections by chapter to improve performance.