pdf-tools

Manipulate PDF files with PyMuPDF for searching, highlighting, merging, and extracting.

Updated Aug 6, 2025

Search Tags:#pdf #text extraction #pymupdf #merging #manipulation #highlighting

Ready to run

npx skills add https://github.com/flosrn/.claude --skill pdf-tools-flosrn

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf-tools
Source: https://github.com/flosrn/.claude/tree/main/agents-global/pdf-tools
Command: npx skills add https://github.com/flosrn/.claude --skill pdf-tools-flosrn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, and includes scripts (resource) components.

What problem does it solve?

This Skill provides a robust set of tools for manipulating PDF files, addressing common needs like searching, highlighting, merging, and extracting content.

Core Features & Use Cases

Search and Highlight Text: Find specific text within a PDF and visually mark it.
Merge PDFs: Combine multiple PDF documents into a single file.
Extract Pages: Isolate and save specific pages from a PDF.
Extract Text: Retrieve all textual content from a PDF.
Add Text Annotation: Insert text boxes onto PDF pages.

Quick Start

Use the pdf-tools skill to merge the files 'doc1.pdf' and 'doc2.pdf' into 'merged.pdf'.

Frequently Asked Questions about pdf-tools

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract text from a PDF using Python?▼

To extract text from a PDF, this Skill uses the PyMuPDF library to programmatically retrieve all textual content from the document. It supports data retrieval from PDF files for downstream processing.

Can I merge multiple PDF files into a single document?▼

Yes, you can merge multiple PDF files into a single document. This Skill leverages PyMuPDF to combine multiple PDF documents into one unified file output.

How do I search for specific text in a PDF and highlight it?▼

You can search for specific text in a PDF and highlight it using this Skill. It utilizes PyMuPDF to find specific text within the document and visually mark it with highlights.

Do I need PyMuPDF installed to extract pages from a PDF?▼

Yes, PyMuPDF (fitz) is required for all PDF manipulation operations, including extracting pages. You must install this dependency to isolate and save specific pages from a PDF document.

What is the best way to add text annotations to existing PDF pages?▼

The best way to add text annotations is using this Skill's PyMuPDF integration to insert text boxes onto PDF pages. It supports programmatic modification to insert text annotations directly into the document.