skills.rest
aliceisjustplaying
aliceisjustplayingCOMMUNITY
Explore all skills by this author →
Website𝕏@__justplayingGitHub

epub

Extract metadata, table of contents, and full text from EPUB files to Markdown.

5|1|Updated Dec 18, 2025
Search Tags:#markdown#search#metadata#chapter#toc#epub#ebook
One-click install
npx skills add https://github.com/aliceisjustplaying/claude-resources-monorepo --skill epub
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: epub
Source: https://github.com/aliceisjustplaying/claude-resources-monorepo/tree/main/skills/epub
Command: npx skills add https://github.com/aliceisjustplaying/claude-resources-monorepo --skill epub

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires commander, turndown, jszip, xml2js, and includes scripts (resource) components.

What problem does it solve?

This Skill streamlines the process of working with EPUB ebooks by enabling quick access to metadata, table of contents, and full book text for analysis or conversion.

Core Features & Use Cases

  • Metadata extraction: retrieve title, author, publisher, date, language, and identifiers.
  • Table of contents navigation: view and navigate the book's structure, including chapter references.
  • Chapter reading & full extraction: read individual chapters or export the entire book to Markdown.
  • Search: find occurrences across chapters with contextual results.
  • Use Case: a researcher can quickly inspect a textbook's structure and extract relevant sections for notes.

Quick Start

To start, provide the path to an EPUB file and a command such as metadata, toc, chapter, full, or search. Examples:

  • View metadata: node ~/.claude/skills/epub/scripts/epub-reader/dist/index.js metadata "<path-to-epub>"
  • List TOC: node ~/.claude/skills/epub/scripts/epub-reader/dist/index.js toc "<path-to-epub>"
  • Read chapter 3: node ~/.claude/skills/epub/scripts/epub-reader/dist/index.js chapter "<path-to-epub>" 3
  • Full extraction: node ~/.claude/skills/epub/scripts/epub-reader/dist/index.js full "<path-to-epub>"
  • Search: node ~/.claude/skills/epub/scripts/epub-reader/dist/index.js search "<path-to-epub>" "query"

Frequently Asked Questions about epub

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

FAQPage Schema
How do I extract text and metadata from an EPUB file for analysis?▼

You can extract EPUB metadata and text by running a local CLI command that parses the file with jszip and xml2js, outputting title, author, and full chapter content rendered as Markdown.

Can I search for specific keywords across all chapters of an EPUB?▼

Yes, you can search across EPUB chapters by running the search command with a query string, which finds keyword occurrences and returns contextual results from the parsed book content.

How do I navigate the table of contents of an EPUB to read a specific chapter?▼

You can navigate an EPUB's table of contents by listing the structure with the toc command, then reading individual chapters by specifying their index number to the chapter command.

Does this EPUB reading method require any specific dependencies or environment?▼

Yes, EPUB parsing requires a Node.js environment to run the local TypeScript CLI, which relies on jszip, xml2js, turndown, and commander to unzip archives, parse XML, and convert HTML to Markdown.

What is the best way to convert a full EPUB ebook to Markdown format?▼

The best way to convert an EPUB to Markdown is using the full extraction command, which parses the ebook with jszip and uses turndown to render the entire book text into a structured Markdown format.

Related Skills

Explore More Education & Research Skills→
NS-VandanaNS-Vandana

file-converter

Convert files between CSV, JSON, YAML, XML, Markdown, EPUB, images, PDFs, and ZIP archives.

Community
Advanced
bahayonghangbahayonghang
16

memory-system

Index Markdown notes into a local SQLite vector/full-text index.

Community
Intermediate
dallenpyrahdallenpyrah

obsidian-vault

Search, create, and link notes in Obsidian vaults using wikilinks.

Community
Basic
anilcan-karaanilcan-kara

ocr-and-documents

Extract text from PDFs and scanned documents using pymupdf or marker-pdf.

Community
Intermediate