skills.rest
magnus919
magnus919COMMUNITY
Explore all skills by this author →
WebsiteGitHub

epub

Convert EPUB2 files to EPUB3 and extract knowledge from ebook documents.

40|6|Updated Jul 11, 2026
Search Tags:#automation#publishing#epub#ebook#knowledge-extraction#document-processing
One-click install
npx skills add https://github.com/magnus919/agent-skills --skill epub-magnus919
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: epub
Source: https://github.com/magnus919/agent-skills/tree/main/epub
Command: npx skills add https://github.com/magnus919/agent-skills --skill epub-magnus919

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires EbookLib, epublib, beautifulsoup4, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the complexity of managing ebook formats by providing a unified, programmatic interface to read, write, edit, and extract knowledge from EPUB2 and EPUB3 files, eliminating the need for manual file manipulation.

Core Features & Use Cases

  • Format Conversion & Repair: Effortlessly convert legacy EPUB2 files to modern EPUB3 standards and auto-repair structural issues.
  • Knowledge Extraction: Automatically pull facts, definitions, and arguments from ebooks using either heuristic pattern matching or LLM-powered pipelines.
  • Surgical Editing: Perform non-intrusive edits to metadata, chapters, and CSS, or scaffold new, valid EPUBs from scratch.

Quick Start

Load the epub skill and ask it to extract all text from the provided ebook file into a clean markdown document.

Frequently Asked Questions about epub

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

FAQPage Schema
How do I extract text from an EPUB ebook into a clean document?▼

You can extract text from EPUB files by loading the ebook and requesting a conversion into a clean markdown document. The skill uses EbookLib and BeautifulSoup4 to parse ebook chapters and pull content for automated knowledge extraction.

What is the best way to convert legacy EPUB2 files to the EPUB3 standard?▼

Converting legacy EPUB2 files to the EPUB3 standard is handled through programmatic format conversion workflows. This approach upgrades the ebook format and auto-repairs structural issues without requiring manual file manipulation.

Do I need BeautifulSoup4 to edit metadata in EPUB files?▼

Yes, BeautifulSoup4 is required along with EbookLib and epublib to edit EPUB metadata. These dependencies enable the robust document processing and structural validation needed for surgical edits to ebook files.

Can I scaffold a new valid EPUB from scratch using EbookLib?▼

Yes, you can scaffold new, valid EPUB files from scratch using EbookLib. The skill provides a programmatic interface to construct the ebook structure, apply CSS, and manage metadata without manual file manipulation.

How does automated knowledge extraction from ebooks work?▼

Automated knowledge extraction from ebooks works by pulling facts, definitions, and arguments from the document content. This skill uses heuristic pattern matching or LLM-powered pipelines to analyze extracted text for agentic memory systems.

Related Skills

Explore More Content & Communication Skills→
AbilityaiAbilityai
103

epub-chapter-extractor

Extract EPUB chapters into separate markdown documents.

Official
Intermediate
mschuerigmschuerig

bmad-distillator

Compress source documents into lossless token-efficient distillates for LLM pipelines.

Community
Advanced
fanguyunfanguyun

book-to-skill

Convert technical books into structured Claude Code skills.

Community
Advanced
zocomputerzocomputer
45

epub-to-markdown

Convert EPUB ebook files to Markdown using pandoc with gfm-raw_html output.

Official
Basic