An intelligent orchestration agent that automates the transition from raw digital books to structured Obsidian notes and Neo4j knowledge graphs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install reading-book
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 reading-book 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 Learning Coordinator?
The Book Learning Coordinator is a powerful master controller designed for Openclaw Skills that orchestrates a multi-step learning pipeline. It manages the sequential execution of specialized modules including book extraction, note generation, and graph database importation. By acting as a central hub, it transforms long-form text documents into organized, actionable knowledge assets without manual intervention.
This skill is essential for researchers, students, and lifelong learners who want to build a second brain. It ensures that every chapter of a book is systematically processed, summarized into Markdown for Obsidian, and mapped into a Neo4j database to visualize relationships between complex concepts. With built-in progress tracking and error handling, it provides a robust framework for high-volume information processing.
Book Learning Coordinator Use Cases
- Automatically converting academic textbooks into structured Obsidian study vaults.
- Building complex Neo4j knowledge graphs from technical documentation or financial reports like Security Analysis.
- Managing long-term learning projects with automated progress tracking and session resumption.
- Creating comprehensive summary reports and statistical overviews of completed reading materials.
How Book Learning Coordinator Works
- The skill initializes the learning environment by validating the source file path and creating dedicated storage directories.
- It triggers the book-extractor to parse the document structure and identify all individual chapters.
- A sequential processing loop is initiated for each chapter, calling the note-generator to create detailed summaries and concept lists.
- Extracted concepts are passed to the neo4j-cypher-generator to create graph database queries.
- The neo4j-importer executes the queries to update the local or cloud knowledge graph.
- A progress tracking file is updated in real-time, recording successful imports and any errors encountered during the lifecycle.
Book Learning Coordinator Setup
To integrate this coordinator into your environment, ensure you have the required sub-modules installed and run the master script via CLI:
# Basic execution
python book-learning-coordinator-script.py --book_path "F:\book\YourBook.docx"
# Resume from a previous interrupted session
python book-learning-coordinator-script.py --resume --book_path "F:\book\YourBook.docx"
# Start from a specific chapter
python book-learning-coordinator-script.py --start_chapter 15 --book_path "F:\book\YourBook.docx"
Book Learning Coordinator Data Schema & Taxonomy
The skill manages a structured output hierarchy to ensure data integrity across various Openclaw Skills:
| File/Data Type | Description | Location |
|---|---|---|
| Progress Tracker | Markdown file tracking chapter status and timestamps | Obsidian/<Book>/Learning_Progress.md |
| Chapter Notes | Markdown files containing summaries and extracted concepts | Obsidian/<Book>/ChXX-Title.md |
| Final Report | A comprehensive summary of the entire book learning journey | Obsidian/<Book>/Full_Report.md |
| Graph Data | Nodes and Relationships imported via Cypher batches | Neo4j Database |
Book Learning Coordinator Advanced Features
- Breakpoint Resumption: Automatically detects completed chapters and resumes from where the last session ended.
- Batch Processing: Capability to queue and process multiple books in a single execution run.
- Granular Error Isolation: Failures in a single chapter or sub-module do not halt the entire pipeline; errors are logged for later review.
- Real-time Learning Statistics: Generates detailed analytics including concept count, relationship density, and total processing time.
SKILL.md
Loading
Related Openclaw Skills
Monet Works Content QA Pipeline
A high-performance QA remediation pipeline that automatically detects and repairs content issues to ensure brand consistency.
Airslate Integration for AI Agents
A powerful document workflow automation skill that enables AI agents to manage e-signatures, templates, and organizational data through Membrane.
MOVA Invoice OCR & Approval
A professional-grade OCR and human-in-the-loop workflow for processing invoices, receipts, and financial documents with cryptographic audit trails.
News Scenario Analysis
A sophisticated dual-agent skill that analyzes news headlines to generate comprehensive 18-month market impact reports and investment strategies.
Python SMTP Email Skill
A zero-dependency Python skill for sending automated emails via SMTP_SSL using the standard library.
Insites Integration for AI Agents
A powerful sales intelligence and CRM integration that enables AI agents to manage organizations, pipelines, and activities directly within the Insites platform.
Featured*
