A comprehensive document processing skill that tracks learning progress across multiple sessions while building a persistent long-term knowledge base.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install document-learning
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 document-learning 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 Document Learning System?
The Document Learning System is a sophisticated framework designed for AI agents to ingest, process, and remember complex information from large-scale documents. It transcends simple file reading by implementing a robust bookmarking system that allows users to pause and resume learning sessions across various file formats, including high-capacity PDFs and text files.
By utilizing Openclaw Skills, this system integrates directly with long-term memory structures, ensuring that every insight extracted during a reading session is permanently stored and searchable. It is specifically engineered to handle multi-document workflows, allowing developers and researchers to juggle multiple technical manuals or books without losing their place or context.
Document Learning System Use Cases
- Learning complex technical manuals or driver specifications over several days.
- Managing academic research by tracking progress across multiple whitepapers and textbooks simultaneously.
- Building a searchable corporate knowledge base from existing PDF documentation and text logs.
- Summarizing long-form content chapter-by-chapter while maintaining a permanent record in MEMORY.md.
How Document Learning System Works
- The user initiates a session by providing a document path or uploading a file, which the system extracts and indexes.
- An initial progress entry is created in the tracking store to monitor chapters or page numbers.
- Content is processed in chunks to manage memory efficiency, especially for files exceeding 100MB.
- Key concepts and summaries are automatically extracted and appended to MEMORY.md and date-stamped session notes.
- Upon request, the system references the progress store to resume learning from the exact last-read position.
Document Learning System Setup
To enable document learning capabilities within your environment, ensure you have the necessary Python dependencies for PDF processing and then use the built-in script.
# Install required PDF processing library
pip install pdfplumber
# Start learning a new document
# Use the command: Please learn this document: [filename]
Document Learning System Data Schema & Taxonomy
The skill organizes learning data through a structured taxonomy to ensure persistence and easy retrieval.
| Component | Location / Format | Purpose |
|---|---|---|
| Long-term Memory | MEMORY.md |
Permanent storage of extracted key concepts and facts. |
| Session Logs | memory/YYYY-MM-DD.md |
Detailed notes and summaries from specific learning dates. |
| Progress Store | Internal JSON/Metadata | Tracks filename, last page/chapter, and percentage complete. |
| Large Files | PDF, TXT, MD, LOG | Source material supported for chunked ingestion. |
Document Learning System Advanced Features
- Multi-document parallel tracking: Switch between different manuals without losing the bookmark for any individual file.
- Automatic encoding detection: High-resilience processing for text files with varying character sets.
- Visual progress reporting: Generate status summaries showing completion percentages across your entire library.
- Integrated memory search: Use the memory_search tool to query learned facts across all previously processed documents.
- Manual navigation: Ability to jump to specific chapters or sections, overriding the automatic bookmarking.
SKILL.md
Loading
Related Openclaw Skills
Atomic RAG Knowledge Base
An advanced knowledge base builder that deconstructs PDF documents into atomic, logically complete units for high-precision Retrieval-Augmented Generation.
Academic Deep Research
A methodical research framework for AI agents that conducts exhaustive investigations through mandated research cycles and formal academic standards.
Academic Writing
A specialized AI agent skill designed to streamline scholarly writing, literature reviews, and thesis development with strict academic integrity.
A-Share Stock Trading Assistant
A professional AI trading assistant providing real-time data and technical analysis for the Chinese A-share stock market.
AI-Resume-Judge
An AI-driven resume evaluation system that provides quantitative scoring, cross-industry equivalence mapping, and actionable improvement suggestions.
AgentID MCP
Connect Claude Code to AgentID for persistent shared memory, live activity reporting, and seamless multi-agent mission coordination.
Featured*
