Pdf Toolkit

What it does

The PDF Toolkit skill enables AI agents to perform a variety of manipulations on PDF documents. It allows for merging multiple PDFs into one, splitting PDFs into smaller chunks or extracting specific pages, rotating pages, adding watermarks, compressing file sizes, encrypting with passwords, and editing metadata. This tool is designed for users needing to modify and manage PDF files programmatically.

When to use it

• Combining several reports or documents into a single PDF.
• Extracting key sections from a large PDF document.
• Adding a confidentiality watermark to sensitive PDFs.
• Reducing the file size of a PDF for easier sharing.
• Protecting a PDF with a password before distribution.

Key capabilities

• Merge: Combines multiple PDF files into one.
• Split: Extracts pages or splits a PDF into smaller chunks.
• Rotate: Rotates individual pages by 90, 180, or 270 degrees.
• Extract: Allows extraction of specific pages or page ranges.
• Watermark: Adds text or image watermarks to PDFs.
• Compress: Reduces the overall file size of a PDF.
• Encrypt: Applies password protection to PDFs.
• Metadata Editing: Modifies PDF metadata information.
• Page Numbering: Adds page numbers to a PDF document.
• Bookmark Management: Adds or removes bookmarks within a PDF.

Example prompts

• "Combine 'report_part1.pdf' and 'report_part2.pdf' into a single file named 'final_report.pdf'."
• "Extract pages 3, 5, and 7 from 'document.pdf' and save them as 'selected_pages.pdf'."
• "Rotate the first five pages of 'presentation.pdf' by 90 degrees and save it as 'rotated_presentation.pdf'."

Tips & gotchas

• Requires dependencies: PyPDF2, PyMuPDF, Pillow, and Reportlab to be installed in the agent’s environment.
• The skill operates directly on PDF files; it does not offer content summarization or translation capabilities.
• Familiarity with basic Python syntax may be helpful for more complex operations.