A specialized skill for extracting, parsing, and modifying EPUB files by treating them as structured ZIP archives.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install epub
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install epub using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is EPUB Processor?
The EPUB Processor is a technical workflow designed to handle electronic publication files with high reliability within an AI agent environment. Since an EPUB is essentially a ZIP archive containing a website-like structure, this skill employs an unzip-then-parse strategy that works across all versions. By utilizing these Openclaw Skills, developers can bypass complex libraries and directly interact with the underlying XML and XHTML content. This approach ensures 100% compatibility for reading, extracting, or modifying ebook data, making it an essential tool for any automated document processing pipeline.
EPUB Processor Use Cases
- Extracting the full text of a book for summarization or LLM-based analysis.
- Parsing the Table of Contents to navigate directly to specific chapters or sections.
- Retrieving detailed book metadata including author, title, publisher, and language.
- Converting ebook content into clean text or Markdown for archival and research.
- Extracting high-resolution cover images or embedded illustrations from the internal structure.
- Programmatically editing ebook content and repacking the modified archive for distribution.
How EPUB Processor Works
- Move the .epub file to the active directory and rename it to a .zip archive to enable standard extraction.
- Extract the archive into a structured folder using the unzip utility to access internal files.
- Locate the navigation file, prioritized as nav.xhtml or toc.ncx, to understand the chapter layout and hierarchy.
- Access the OPF package file to determine the correct reading order (the spine) and extract global metadata.
- Process the XHTML content files using BeautifulSoup to strip away HTML tags and extract clean, formatted text.
EPUB Processor Setup
Ensure your environment is ready by installing the required Python dependencies for HTML and XML parsing:
pip install beautifulsoup4 lxml --break-system-packages
The basic shell commands to start processing involve copying and unzipping the target file:
# Standard extraction workflow
cp input.epub book.zip
unzip -o book.zip -d book_extracted/
EPUB Processor Data Schema & Taxonomy
The skill maps the internal EPUB structure to a predictable schema to facilitate easy data extraction:
| Path | Purpose | Data Type |
|---|---|---|
META-INF/container.xml |
Points to the root package file | XML |
*.opf |
Manifest and Spine (reading order) | XML |
nav.xhtml |
Human-readable Table of Contents | XHTML |
toc.ncx |
Legacy Table of Contents (EPUB2) | XML |
images/ |
Directory for all visual assets | Binary |
Using these Openclaw Skills ensures your data extraction scripts can locate the correct content regardless of the internal naming conventions used by different ebook publishers.
EPUB Processor Advanced Features
- Multi-format TOC parsing supporting both modern EPUB3 (Nav) and legacy EPUB2 (NCX) standards.
- High-fidelity text cleaning that removes script, style, and head tags automatically to provide clean input for AI models.
- Reliable repacking logic that preserves the required mimetype uncompressed at the start of the archive for valid ebook creation.
- Namespace-safe XML processing to handle complex metadata schemas without common parsing errors.
- Seamless integration into Openclaw Skills based automation for library management and document research workflows.
SKILL.md
Loading
Related Openclaw Skills
Fund Report Processor
A zero-interaction automation skill designed to retrieve, extract, and visualize financial data from daily fund report email attachments.
Let's Send It
A trustless coordination infrastructure for AI agents and communities to launch tokens on Solana using a structured 40-seat model.
SearXNG Web Search
A privacy-respecting metasearch skill that enables AI agents to aggregate and retrieve real-time data from hundreds of search engines through SearXNG.
Cisco ASA Syslog Analysis
A comprehensive framework for parsing, interpreting, and analyzing Cisco ASA firewall syslog messages for security and network troubleshooting.
Phone Agent Skill
A mobile automation skill that enables AI agents to control Android devices via natural language for testing, data collection, and UI interaction.
Feishu Bitable Creator
A professional automation tool for creating cleaned, ready-to-use Feishu Bitable tables with intelligent data population and admin management.
Featured*
