PDF Reader
Documents Search & ProductivityInstall Command
npx clawhub@latest install pdf
Installation Guide
Make sure Node.js 22+ and OpenClaw are installed. Run openclaw --version in your terminal to verify.
Run the install command above in your terminal. ClawHub will automatically download and install PDF Reader to the ~/.openclaw/skills/ directory.
Run openclaw skills list to check your installed skills and confirm PDF Reader appears in the list.
Follow the configuration instructions in the description below to add skill settings to ~/.config/openclaw/openclaw.json5.
~/.openclaw/skills/ or the skills/ directory in your project root. Make sure the folder contains a SKILL.md file.
Detailed Description
The PDF Reader skill enables OpenClaw to directly read and understand PDF file contents, transforming PDFs from static, non-interactive documents into knowledge sources you can have a conversation with.
Core Features
- Full Text Extraction: Extracts the complete text from PDFs while preserving basic formatting structure
- Table Recognition: Intelligently recognizes tables in PDFs and converts them to structured data
- Paginated Reading: Supports reading by page range for large PDFs, avoiding loading too much content at once
- Image OCR: For scanned PDFs, supports OCR to recognize text within images
- Conversational Q&A: After reading a PDF, you can ask questions based on the document content
Configuration
{
skills: {
pdf: {
ocrEnabled: true, // Enable OCR
maxPages: 50, // Max pages per processing
tableExtraction: true // Table extraction
}
}
}
Use Cases
- Analyzing academic papers and technical white papers
- Reading and extracting key information from contracts, invoices, and other business documents
- Q&A on product manuals
- Batch extracting data from multiple PDFs for aggregation
How to Use
Send a PDF file to OpenClaw (via the chat platform's file sending feature), then ask your question directly. You can also reference a local PDF by file path.