pdf-translator

Translate PDF documents into other languages while preserving original layout using LaTeX.

6|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/Overdue-Lin/pdf-translate-skill --skill pdf-translator-overdue-lin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf-translator
Source: https://github.com/Overdue-Lin/pdf-translate-skill/tree/main
Command: npx skills add https://github.com/Overdue-Lin/pdf-translate-skill --skill pdf-translator-overdue-lin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, pillow, texlive-xetex, ctex, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the translation of PDF documents, ensuring that the original layout, formatting, and visual structure are preserved in the translated output.

Core Features & Use Cases

  • Multilingual PDF Translation: Translate documents between languages while maintaining fidelity to the original design.
  • Layout Preservation: Converts PDFs to images for analysis, extracts text and images, and reconstructs the document using LaTeX to match the original layout.
  • arXiv Paper Support: Specializes in translating academic papers from arXiv by downloading and translating their source TeX files for superior formatting.
  • Use Case: Translate a research paper from English to Chinese, ensuring all figures, tables, and complex formatting remain intact.

Quick Start

Translate the PDF document located at '/path/to/your/document.pdf' into French.

Frequently Asked Questions about pdf-translator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I translate a PDF document while preserving its original layout?

To translate a PDF while preserving layout, this Skill converts pages to images for analysis, extracts text and images, and recomposes the document using LaTeX to match the original formatting.

Can I translate arXiv papers by processing their source TeX files directly?

Yes, you can translate arXiv papers by downloading and processing their source TeX files directly, which ensures superior formatting and accurate multilingual translation compared to standard PDF extraction.

Do I need a LaTeX distribution like XeLaTeX to reconstruct translated PDFs?

Yes, you need a LaTeX distribution like XeLaTeX to reconstruct translated PDFs, as it is required to recompose the extracted text and images into a document that matches the original layout.

How does converting PDF pages to images help with document localization?

Converting PDF pages to images helps with document localization by providing a visual reference for layout analysis, allowing the system to extract text and accurately recompose the translated document using LaTeX.

What is the best way to translate an English research paper to Chinese while keeping figures and tables intact?

The best way to translate a research paper while keeping figures and tables intact is to process the source TeX files or use image-based layout analysis to recompose the document with LaTeX, ensuring formatting fidelity.