Install
$ agentstack add skill-jykim-claude-obsidian-skills-epub-to-markdown ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
EPUB to Markdown Skill
Convert EPUB files to well-formatted single markdown files with images extracted.
Usage
python3 epub_to_markdown.py "" -o ""
Features
- Metadata extraction: title, author, language, publisher, publication date
- TOC parsing: Extracts table of contents with hierarchy
- HTML to Markdown: Converts chapter HTML using html2text
- Heading preservation: Maintains H1-H6 hierarchy
- Image extraction: Extracts images to
_files_/folder with book prefix - Single file output: All chapters in one markdown file
Output Structure
output_dir/
├── book.epub # Original file
├── book.md # Extracted markdown
└── _files_/ # Images folder
├── BookTitle_cover.jpg
├── BookTitle_figure1.png
└── ...
Image Prefix
Images are extracted with a book prefix derived from the title:
- Title: "Die Empty: Unleash Your Best Work Every Day"
- Prefix:
DieEmptyUnleash(first 3 words, special chars removed) - Image:
_files_/DieEmptyUnleash_cover.jpg
This prevents filename collisions when extracting multiple books to the same folder.
Output Format
---
title: {from metadata}
author: {from metadata}
language: {from metadata}
source_file: original.epub
source_type: epub
extracted: YYYY-MM-DD HH:MM:SS
status: extracted
---
# {Book Title}
## Table of Contents
- Chapter 1
- Chapter 2
...
---
## Chapter 1
{content with links}
---
## Chapter 2
{content}
Dependencies
pip install ebooklib beautifulsoup4 html2text
Or use requirements.txt:
pip install -r requirements.txt
Options
| Flag | Description | |------|-------------| | -o, --output | Output markdown file path (default: same as epub with .md) | | -q, --quiet | Suppress progress messages |
Limitations
- DRM-protected EPUBs: Cannot be extracted (will fail with error)
- Complex formatting: May simplify to plain text
- Large EPUBs: May take time for books with many chapters/images
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jykim
- Source: jykim/claude-obsidian-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.