A professional AI-driven reading assistant that mandates chapter-by-chapter processing to generate high-fidelity structured notes and cross-textual knowledge graphs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install deep-reading
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 deep-reading 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 Deep Reading Assistant?
The Deep Reading assistant is a specialized tool within the Openclaw Skills ecosystem designed for scholars, researchers, and lifelong learners. Unlike standard AI summarizers that provide superficial overviews, this skill enforces a slow is fast philosophy, requiring the agent to engage deeply with the source text. It is specifically engineered to prevent AI hallucinations or over-simplification by mandating direct citations and word-by-word analysis.
By incorporating this into your Openclaw Skills library, you transform your AI agent into a meticulous librarian and analyst. It supports various formats including classical texts, modern philosophy, academic papers, and literature, automatically adjusting its reading pace based on the density and complexity of the material.
Deep Reading Assistant Use Cases
- Mastering classical and foundational texts where every word carries significant weight.
- Building a professional knowledge base using the Zettelkasten method via double-link cross-referencing.
- Analyzing dense academic papers or technical documentation chapter by chapter.
- Generating actionable modern insights from historical or philosophical works.
- Organizing multi-book research projects within the Openclaw Skills framework.
How Deep Reading Assistant Works
- Initialization: The agent checks for an existing reading plan in the reading/plan.md file.
- Book Configuration: If no plan exists, the agent guides the user through book selection and format identification (EPUB, URL, or raw text).
- Automatic Inference: The skill calculates the optimal reading volume per session based on the book type (e.g., 1 chapter for classics, 3 chapters for narratives).
- Structured Output (SOP): For every session, the agent generates six mandatory sections: Original Citations, Word-by-Word Analysis, Meaning Interpretation, Cross-Text Correlation, Modern Enlightenment, and Difficulty Annotation.
- Quality Self-Check: The agent executes a self-check protocol to ensure the output meets minimum quality standards before saving.
- Progress Sync: The reading plan is updated, and core insights are pushed to the daily memory log for long-term retention.
Deep Reading Assistant Setup
To begin using this skill within your Openclaw Skills setup, simply trigger the agent with the keywords reading or deep reading.
For automated daily reading sessions, add the following prompt to your Openclaw Gateway Dashboard:
# Example Cron Prompt
Read reading/plan.md and execute the next chapter of deep reading.
Follow the Deep Reading SOP strictly and update the progress plan.
Sync core insights to the daily memory file.
Ensure your workspace has a reading/ directory initialized for the agent to store its structured Markdown files.
Deep Reading Assistant Data Schema & Taxonomy
The Deep Reading skill organizes data into a clean, hierarchical structure optimized for Openclaw Skills integration:
| File/Folder | Description |
|---|---|
reading/plan.md |
Central registry for book configurations, reading volumes, and current progress. |
reading/[book-slug]/ |
Dedicated directory for each book containing individual chapter notes. |
reading/[book-slug]/chapter-XX.md |
Structured Markdown file containing the 6-step SOP analysis. |
reading/connections.md |
An optional index for cross-book intellectual correlations using double-link formatting. |
Deep Reading Assistant Advanced Features
- Automatic Reading Volume Inference: Dynamically adjusts output based on text complexity metrics.
- Hebbian Cross-Text Linking: Uses [[Book/Chapter]] syntax to build a relational knowledge graph across your entire library.
- Quality Assurance Scripting: Optional Python integration for automated word count and citation density verification.
- Multi-Layer Memory Pipeline: Integrates with agent-sleep and memory-sync-enhanced Openclaw Skills to move insights from short-term to long-term memory.
- Isolated Session Support: Configurable session targets to prevent context degradation during marathon reading projects.
SKILL.md
Loading
Related Openclaw Skills
OpenRA-RL: AI RTS Commander
An advanced MCP-compatible skill that enables AI agents to play Command & Conquer: Red Alert through strategic real-time command and control.
Skill Store
An intelligent advisor that searches, audits, and recommends the highest quality Openclaw Skills for your specific development needs.
Skill Shield
A professional-grade security auditing tool designed to scan, rate, and verify the safety of Openclaw Skills before deployment.
Quest Board
Quest Board is a visual project management skill that generates a professional HTML dashboard to track project status, progress, and infrastructure.
Receipt Assistant
An AI-powered tool for automatically identifying, extracting data from, and organizing expense receipts into structured reports.
High-Repeat Small Goods E-commerce Ops Skill
An automated e-commerce operations manager designed to optimize growth, conversion, and repurchase rates for high-frequency small-ticket items.
Featured*
