skills.rest
lc0rp
lc0rpCOMMUNITY
Explore all skills by this author →
Website𝕏@lukekyohereGitHub

babel-copy

Translate and rebuild PDFs into a target language while preserving layout and assets.

Updated Aug 27, 2026
Search Tags:#workflow#pdf#translation#layout-preservation#document-rebuild#signature-preservation
One-click install
npx skills add https://github.com/lc0rp/luke-agent-scripts --skill babel-copy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: babel-copy
Source: https://github.com/lc0rp/luke-agent-scripts/tree/main/skills/babel-copy
Command: npx skills add https://github.com/lc0rp/luke-agent-scripts --skill babel-copy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Pillow, PyMuPDF, pytesseract, numpy, syntok, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Translate and rebuild PDFs end-to-end, preserving non-text artifacts (signatures, logos, tables) while translating the visible text to a target language, enabling professional-looking translations of formal documents.

Core Features & Use Cases

  • End-to-end pipeline: extraction, translation, layout rebuild, asset placement, and final PDF export.
  • Supports digital, mixed, and scanned PDFs with layout-aware strategies to preserve structure.
  • Use cases include contracts, policies, forms, and other form-heavy or print-forward documents where preserving layout is crucial.

Quick Start

Translate a document by running the Babel Copy workflow to extract, translate, rebuild, and export a final PDF.

Frequently Asked Questions about babel-copy

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

FAQPage Schema
How do I translate a PDF while preserving its original layout and signatures?▼

PDF translation with layout preservation extracts source text, translates it, and visually rebuilds the document while keeping non-text assets like signatures, logos, and tables intact. This ensures professional-looking translated contracts and formal documents.

What's the best way to rebuild translated PDFs from form-heavy contracts?▼

Rebuilding translated PDFs from form-heavy contracts requires an end-to-end pipeline that handles extraction, translation, layout rebuild, asset placement, and final export. It maintains per-page fingerprints and caches translations to support resumable work and auditing.

Does the PDF translation workflow support resumable work and auditing?▼

The PDF translation workflow supports resumable work and auditing by maintaining per-page fingerprints, caching translations, and recording run-manifest metadata. This allows you to resume interrupted translation jobs and audit the processing history of rebuilt documents.

Why does my translated PDF lose non-text assets like logos and tables?▼

Translated PDFs lose non-text assets like logos and tables when the workflow lacks dedicated asset placement and layout rebuild stages. Preserving typography cues and non-text artifacts requires layout-aware strategies that reposition original assets into the rebuilt document.

Related Skills

Explore More Legal & Compliance Skills→
taracodlabstaracodlabs
779

ocr-and-documents

Extract readable text from PDFs, scanned images, and Word documents using Python libraries.

Official
Intermediate
freekmurzefreekmurze
997

pdf

Extract text and tables from PDFs using pypdf and pdfplumber.

Community
Advanced
robit-manrobit-man

pdf-extractor

Extract text, tables, and images from PDFs with OCR support.

Community
Advanced
dull-birddull-bird
6

do.translate-pdf

Translate PDF documents into a target language while preserving layout, styling, colors, and positions.

Community
Intermediate