pdf_to_epub

Name: pdf_to_epub
Availability: InStock
Author: koreyba

Convert PDF books into EPUB files with chapter detection and image optimization.

30|3|Updated Jan 2, 2026

One-click install

npx skills add https://github.com/koreyba/Claude-Skill-pdf-to-epub --skill pdf-to-epub

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: pdf_to_epub
Source: https://github.com/koreyba/Claude-Skill-pdf-to-epub/tree/main/pdf_to_epub
Command: npx skills add https://github.com/koreyba/Claude-Skill-pdf-to-epub --skill pdf-to-epub

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, pdfplumber, lxml, beautifulsoup4, Pillow, ebooklib, and includes scripts (resource) and reference (resource) components.

What problem does it solve?

This Claude Skill automates the conversion of PDF books into high-quality EPUB files, preserving structure, images, and footnotes while optimizing for reading on e-readers.

Core Features & Use Cases

Chapter detection: Automatically identifies chapters and headings to produce a navigable EPUB.
Image extraction & optimization: Extracts images and optimizes them for size and compatibility.
Footnote/Endnote hyperlinking: Converts references into clickable links within the e-book.
Reading order handling for multi-column layouts: Detects layout and preserves reading order across complex PDFs.
Quality validation: Ensures text integrity and correct reading order after conversion.

Quick Start

From the skill directory, run:

python -m scripts.convert input.pdf output.epub
python -m scripts.validate input.pdf output.epub