skills.rest
openakita
openakitaCOMMUNITY
Explore all skills by this author →
GitHub

openakita/skills@translate-pdf

Translate PDF documents page-by-page while preserving layout, tables, and images.

2.0k|267|Updated Jan 30, 2026
Search Tags:#technical documentation#layout preservation#pdf translation#document localization#ocr translation#multilingual pdf
One-click install
npx skills add https://github.com/openakita/openakita --skill openakita-skills-translate-pdf
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openakita/skills@translate-pdf
Source: https://github.com/openakita/openakita/tree/main/skills/translate-pdf
Command: npx skills add https://github.com/openakita/openakita --skill openakita-skills-translate-pdf

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyMuPDF, httpx, pdf2image, pytesseract, pdfplumber, reportlab, deep-translator, openai, 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 original formatting, layout, tables, and images are preserved, making multilingual document handling seamless.

Core Features & Use Cases

  • Preserves Layout: Translates text while maintaining original styling, fonts, sizes, and positioning.
  • Handles Complex Elements: Accurately translates text within tables, headers, footers, and footnotes, while leaving images, formulas, and code blocks untouched.
  • Supports OCR: Can process scanned PDFs by first performing Optical Character Recognition (OCR) to extract text before translation.
  • Batch Processing: Capable of translating multiple PDF files efficiently.
  • Use Case: Translate a technical manual or academic paper from English to Chinese, ensuring all diagrams, tables, and formatting remain intact for clear understanding.

Quick Start

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

Frequently Asked Questions about openakita/skills@translate-pdf

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

FAQPage Schema
How do I translate a PDF while preserving the original layout and tables?▼

This Skill translates PDF documents page-by-page, preserving original layout, styling, tables, and images by extracting text, translating via LLMs or other engines, and reconstructing the PDF.

Can I translate scanned PDF documents to another language?▼

Yes, you can translate scanned PDF documents by first performing Optical Character Recognition (OCR) to extract text before translation and PDF reconstruction, supporting multiple languages including Simplified Chinese, English, and Japanese.

Does PDF translation work for batch processing multiple technical manuals?▼

Yes, batch processing is supported for translating multiple PDF files efficiently, ensuring all diagrams, tables, and formatting remain intact for clear understanding across multilingual documents.

What is the best way to generate a bilingual PDF from an English technical document?▼

The best way to generate a bilingual PDF is using this Skill's dedicated workflow, which translates text via LLMs or other engines and reconstructs the file to display both original and translated text while preserving complex elements like formulas and code blocks.

Are images and code blocks left untouched during multilingual PDF localization?▼

During multilingual PDF localization, images, formulas, and code blocks are left untouched, while text within tables, headers, and footers is accurately translated to ensure document formatting remains intact.

Related Skills

Explore More Content & Communication Skills→
superfhpsuperfhp

ocr-and-documents

Extract text, tables, metadata, and images from PDFs and scanned documents.

Community
Intermediate
iflytekiflytek
217

ifly-pdf&image-ocr

Extract text from images and PDFs and convert PDFs to JSON, Markdown, or Word.

Official
Intermediate
koolamusickoolamusic
9

pdf

Extracts text and tables from PDF documents.

Community
Advanced
kunwl123456kunwl123456
26

pymupdf-pdf

Parse PDFs with PyMuPDF for text and basic data extraction.

Community
Intermediate