Overview
The PDF skill lets your Agent treat PDFs like plain text — read, extract tables, merge, split, rotate, watermark, fill forms, encrypt/decrypt. Scanned documents are OCR'd automatically so the Agent can read them like source files.
Features
- Extract text, tables, and images
- Merge, split, rotate, and watermark
- Fill and read PDF form fields
- Encrypt and decrypt while preserving metadata
- Automatic OCR for scanned documents
Try prompts like
Say these in XClaw — the skill activates automatically
- ›OCR the scanned contract in Downloads and extract the parties and amount
- ›Merge these 3 PDFs by date and add page numbers
- ›Export every table in this earnings report to CSV
