pdf-design

What it does

This skill enables AI agents to generate, edit, and format PDF documents directly within a workflow. It handles layout adjustments, text insertion, and file assembly without requiring external software.

When to use it

• Creating standardized reports or invoices from raw data templates.
• Assembling multi-page documents by merging separate text files into one cohesive PDF.
• Adjusting margins, fonts, or headers on existing document drafts before final distribution.
• Generating legal forms or certificates with dynamic variable insertion.

Key capabilities

• Document Creation: Builds new PDFs from scratch based on provided content and structure.
• Text Manipulation: Inserts, deletes, or reorders text blocks within the document.
• Layout Control: Modifies page dimensions, margins, and column structures.
• File Assembly: Combines multiple source files into a single output document.

Example prompts

• "Create a 3-page invoice PDF for Client X with line items for services A, B, and C."
• "Merge these three separate text files into one formatted PDF report with a table of contents."
• "Update the header and footer of this existing PDF template to include our new company logo and address."

Tips & gotchas

Ensure your source text or data is clean and structured before asking the agent to format it, as layout errors can compound quickly. Verify the final output visually if precise graphical alignment (like images or complex tables) is critical, as basic text-based PDF generation may lack fine-grained control over vector graphics.