skills.rest
Embassy-of-the-Free-Mind
Embassy-of-the-Free-MindOFFICIAL
Explore all skills by this author →
GitHub

batch-translate

Crop two-page spreads, run OCR, and translate books with page context.

14|3|Updated Dec 18, 2025
Search Tags:#workflow#ocr#translation#gemini#batch-translate#book-processing#historical-texts
One-click install
npx skills add https://github.com/Embassy-of-the-Free-Mind/sourcelibrary-v2 --skill batch-translate
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: batch-translate
Source: https://github.com/Embassy-of-the-Free-Mind/sourcelibrary-v2/tree/main/.claude/skills/batch-translate
Command: npx skills add https://github.com/Embassy-of-the-Free-Mind/sourcelibrary-v2 --skill batch-translate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill batch processes books through the full pipeline: cropping two-page spreads, performing OCR on pages, and translating with page-context to maintain continuity across chapters and pages. It enables humanities digitization projects to efficiently handle large corpora with consistent results and reduced manual workload.

Core Features & Use Cases

  • Batch-driven workflow: crop, OCR, and translate with context for multiple books in a single run.
  • Context-aware translation: maintains continuity across pages for better readability and coherence.
  • Automated orchestration: coordinates cropping, OCR, translation, and optional batch endpoints to scale processing.

Quick Start

Process a set of books through the batch-translate workflow to start the full crop→OCR→translate pipeline.

Frequently Asked Questions about batch-translate

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

FAQPage Schema
How do I automate OCR and translation for a batch of historical books?▼

Automate OCR and translation by processing books through a batch workflow that crops two-page spreads, runs OCR, and translates text while maintaining page-to-page context for consistent continuity across large corpora.

Can I maintain context across pages when translating historical texts?▼

Context-aware translation maintains continuity across pages by passing page-to-page context during the translation process, ensuring better readability and coherence throughout chapters and entire historical digitization projects.

How does batch processing handle two-page spreads in book digitization?▼

Batch processing handles two-page spreads by automatically cropping them into individual pages before running OCR and translation, streamlining the end-to-end book processing pipeline for large-scale digitization tasks.

Does Gemini OCR support batch translation workflows for large corpora?▼

Gemini supports batch translation workflows by providing the underlying OCR and translation engine, enforcing deterministic steps with contextual continuity to efficiently handle large-scale historical text processing.

What is the best way to scale book processing for humanities digitization projects?▼

Scale book processing by using automated orchestration to coordinate cropping, OCR, and translation across multiple books in a single run, reducing manual workload while ensuring consistent results across large corpora.

Related Skills

Explore More Education & Research Skills→
lxh755818-botlxh755818-bot

ocr-and-documents

Extract text from PDFs and scanned documents using OCR.

Community
Advanced
muddyrainmuddyrain
1

image-text-studio

Coordinate text, highlights, styles, and templates for export-ready image-text cards.

Community
Advanced
lazyFrogLOLlazyFrogLOL
127

extract-moves-from-video

Extract typed command text from video recordings of terminal sessions.

Community
Intermediate
JDerekLomasJDerekLomas
1

daily-sourcelibrary

Automate batch OCR and translation of historical Latin texts with Gemini Batch API.

Community
Intermediate