Skills epub-chapter-extractor
📚

epub-chapter-extractor

Low Risk 📁 Filesystem access⚙️ External commands

Extract EPUB chapters to markdown

Converting ebooks to separate chapter files takes time and requires specialized tools. This skill automatically extracts each chapter from an EPUB into its own markdown file with proper formatting and numbering.

Supports: Claude Codex Code(CC)
📊 69 Adequate
1

Download the skill ZIP

2

Upload in Claude

Go to Settings → Capabilities → Skills → Upload skill

3

Toggle on and start using

Test it

Using "epub-chapter-extractor". Extract chapters from /path/to/novel.epub

Expected outcome:

  • Created output folder: /path/to/novel/
  • Extracted 15/15 chapters:
  • [01/15] 01_introduction.md
  • [02/15] 02_chapter_one.md
  • ...
  • [15/15] 15_conclusion.md
  • All chapters saved to /path/to/novel/

Using "epub-chapter-extractor". Extract chapters from programming-book.epub to my-code-folder

Expected outcome:

  • Created output folder: my-code-folder/
  • Extracted 12/12 chapters:
  • [01/12] 01_introduction_to_programming.md
  • [02/12] 02_variables_and_data_types.md
  • ...
  • All chapters saved to my-code-folder/

Security Audit

Low Risk
v5 • 1/16/2026

All 29 static findings are FALSE_POSITIVES. The skill is a legitimate document conversion tool that reads EPUB files and writes markdown to user-specified locations. No network activity, no data exfiltration, no malicious patterns. Static findings stem from markdown code blocks being misidentified as shell execution, standard Claude skills paths flagged as hidden file access, and text patterns incorrectly matching crypto/ransomware keywords.

3
Files scanned
526
Lines analyzed
2
findings
5
Total audits

Risk Factors

📁 Filesystem access (1)
⚙️ External commands (1)
Audited by: claude View Audit History →

Quality Score

38
Architecture
100
Maintainability
85
Content
31
Community
90
Security
91
Spec Compliance

What You Can Build

Extract research book chapters

Convert academic ebooks into individual chapter files for easier reference and citation management

Organize long-form content

Break down multi-author anthologies or textbooks into separate documents for focused reading

Prepare ebook content for blogs

Convert ebook chapters into markdown for republishing as blog posts or articles

Try These Prompts

Basic extraction
Extract all chapters from mybook.epub
Custom output location
Extract chapters from book.epub to my-output-folder
Process existing file
Extract chapters from /Users/name/Documents/book.epub
Convert for analysis
Extract all chapters from the textbook.epub in my downloads folder so I can analyze each chapter separately

Best Practices

  • Place EPUB files in a dedicated folder before extraction for organized output
  • Use descriptive EPUB filenames to create meaningful output folder names
  • Verify extracted markdown files retain chapter headings for navigation

Avoid

  • Do not use on DRM-protected ebooks as extraction may violate terms of service
  • Do not expect complex formatting like tables to transfer perfectly
  • Do not assume all EPUB files have properly structured table of contents

Frequently Asked Questions

What ebook formats are supported?
Only EPUB format is supported. PDF, MOBI, AZW, and other formats require different tools.
Can I extract protected or DRM files?
DRM-protected files cannot be extracted and may violate copyright or license terms.
How are output files named?
Files are numbered sequentially like 01_chapter_title.md for proper filesystem sorting.
Where are extracted files saved?
By default, files are saved to a folder named after the EPUB in the same directory as the source file.
What dependencies are required?
The skill uses ebooklib, beautifulsoup4, html2text, and lxml which are installed via uv run.
How does this compare to Calibre?
This is a focused command-line tool for markdown extraction. Calibre offers more format support but requires GUI.

Developer Details

File structure