How to use PDF Tools in your AI agent

What you'll get

This skill lets you do everything with PDF files through simple requests. Extract text or tables from existing PDFs, combine multiple files into one, split documents into separate pages, rotate pages, add watermarks, fill out forms, and even create brand-new PDFs from scratch. It can also handle scanned PDFs by converting them into searchable text. Perfect for anyone who regularly deals with documents but doesn't want to juggle multiple PDF apps.

Step 1 — Get the skill source URL

The PDF Tools skill lives at:

Step 2 — Add it to your AI agent

Copy one of these prompts and paste it into your AI tool. The agent will fetch and install the skill for you.

Add the agent skill from https://github.com/anthropics/skills/tree/main/skills/pdf to my project.

Install this agent skill: https://github.com/anthropics/skills/tree/main/skills/pdf

Add this skill to .codex/skills/: https://github.com/anthropics/skills/tree/main/skills/pdf

Add the skill at https://github.com/anthropics/skills/tree/main/skills/pdf to my .gemini/skills/ directory.

Install this agent skill from https://github.com/anthropics/skills/tree/main/skills/pdf

Add this skill: https://github.com/anthropics/skills/tree/main/skills/pdf

Step 3 — Try these prompts

Once the skill is installed, ask your AI things like:

• Pull data from a PDF invoice or report into a spreadsheet
• Combining multiple documents into one file for a client or team
• Create a simple PDF report without opening design software
• You have a scanned PDF and need the text to be searchable or editable

What this skill does

• Extracts text and tables from any PDF, including scanned documents
• Merges multiple PDFs into one file or splits a PDF into separate pages
• Creates new PDFs with custom text, layouts, and multiple pages
• Rotates pages, adds watermarks, and fills out PDF forms
• Encrypts PDFs with passwords or removes existing passwords