A comprehensive tool enabling AI agents to search, download, and read books from multiple sources with intelligent progress tracking.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install book-reader
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 book-reader 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 book-reader?
The book-reader skill is designed to bridge the gap between AI agents and long-form literature. It allows agents to consume full-length books in EPUB, PDF, and TXT formats for tasks like deep learning, summarization, and automated knowledge extraction. By integrating this into your set of Openclaw Skills, you enable your agent to interact with global libraries like Project Gutenberg and Anna's Archive, or process your own local collection.
This skill goes beyond simple text extraction by implementing smart chunking and persistent state management. It ensures that large volumes of data are fed to the AI in digestible sections while maintaining a record of reading progress, bookmarks, and notes in a structured format.
book-reader Use Cases
- Automating the summarization of technical manuals or academic textbooks.
- Conducting deep research across multiple public domain books for content creation.
- Building a persistent learning routine for an AI agent with automated daily page reading.
- Extracting specific insights and data points from large PDF or EPUB libraries.
How book-reader Works
- Search for titles using the integrated API connectors for Project Gutenberg or Anna's Archive.
- Download the desired book file directly to the local workspace for processing.
- Convert and parse the document content into clean text using Pandoc or specialized Python libraries.
- Process the book in sections to stay within LLM context windows while maintaining narrative flow.
- Persist the reading state, including the last page read and custom notes, to a local JSON memory file.
book-reader Setup
To integrate this into your environment for Openclaw Skills, follow these steps:
# Install system-level dependencies
sudo apt-get install poppler-utils pandoc # Linux
# brew install poppler pandoc # macOS
# Install required Python packages
pip3 install ebooklib beautifulsoup4 lxml
# Set permissions
chmod +x book-reader.sh
book-reader Data Schema & Taxonomy
The skill manages reading metadata within ~/.openclaw/workspace/memory/reading-state.json to ensure continuity across sessions.
| Property | Type | Description |
|---|---|---|
| currentBook | string | The title of the active book |
| file | string | Path to the source EPUB, PDF, or TXT file |
| totalPages | number | Total length of the document |
| pagesRead | number | The current progress index |
| lastRead | timestamp | Unix timestamp of the last session |
| bookmarks | array | Indices of important pages saved for reference |
| notes | string | Extracted insights or annotations |
book-reader Advanced Features
- Support for multiple high-volume sources including shadow libraries and public domain repositories.
- Intelligent fallback mechanisms using Pandoc or native Python parsers for format conversion.
- Persistent session management allowing agents to resume long-form reading across multiple days.
- Customizable chunking sizes to optimize for different LLM context window requirements.
- Local file support for private EPUB and PDF collections within the Openclaw Skills ecosystem.
SKILL.md
Loading
Related Openclaw Skills
Emperor Claw OS
An advanced operating doctrine for Openclaw Skills that enables a centralized manager agent to orchestrate a distributed AI workforce through the Emperor Claw SaaS control plane.
ScholarGraph-FusionGenes
A professional-grade workflow for systematic cancer fusion gene research, automated data extraction, and structured Excel reporting.
Product Comparison Analysis
A comprehensive tool for deep product research and comparative analysis to drive informed purchasing and competitive intelligence.
Knowledge Splitter
An optimization utility for AI agents to handle large-scale knowledge documents through thematic chunking and indexed retrieval.
Agent Browser
A high-performance browser automation CLI built on Playwright for seamless web interaction and data extraction.
PR + Commit Workflow
A specialized skill designed to enforce high-signal, human-verified commit and pull request workflows within AI-driven development environments.
Featured*
