converting-content

Convert image-based EPUBs to text with OCR and translate English to Japanese via LM Studio.

1|Updated Jan 7, 2026
One-click install
npx skills add https://github.com/sumik5/sumik-llm-plugin --skill converting-content
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: converting-content
Source: https://github.com/sumik5/sumik-llm-plugin/tree/main/plugins/studio/skills/converting-content
Command: npx skills add https://github.com/sumik5/sumik-llm-plugin --skill converting-content

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandoc, recognize-image.py, lmstudio-translate.py, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides efficient conversion of image-based EPUBs to text and facilitates accurate translation of content using LM Studio.

Core Features & Use Cases

  • EPUB to Text Conversion: Extracts text from image-based EPUBs using OCR technology.
  • LM Studio Translation: Utilizes LM Studio's local LLM to translate English text into natural Japanese.
  • Use Case: Ideal for converting EPUBs with images into editable text or translating technical documents.

Quick Start

Convert an image-based EPUB to text using the converting-content skill with the command: /converting-content <epub-file-path>.

Frequently Asked Questions about converting-content

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

FAQPage Schema
How do I extract text from an image-based EPUB?

To extract text from an image-based EPUB, you need optical character recognition (OCR) to process the embedded images. This Skill uses OCR technology to convert visual content within EPUBs into editable text.

Can I translate English text to Japanese using LM Studio?

Yes, you can translate English text to Japanese using LM Studio. This Skill leverages LM Studio's local LLM to process extracted text and generate accurate Japanese translations.

Do I need pandoc to convert image-based EPUBs to text?

Yes, pandoc is a required dependency to convert image-based EPUBs to text. You also need the recognize-image.py and lmstudio-translate.py scripts for the OCR and translation workflow.

What is the best way to translate an EPUB document locally?

The best way to translate an EPUB locally is using a local LLM via LM Studio. This Skill extracts text with OCR and translates it, ensuring your document conversion and translation workflows remain private.

How does OCR handle EPUB conversion for technical documents?

OCR handles EPUB conversion for technical documents by scanning image-based pages and extracting editable text. This process is ideal for transforming scanned technical EPUBs into translatable text formats.

Are there limitations to translating EPUBs with a local LLM?

Translating EPUBs with a local LLM requires specific dependencies including pandoc and Python scripts. Users must have LM Studio configured locally to execute the English to Japanese translation workflow successfully.