Back to Skills

pdf

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

9stars3forksUpdated 2/21/2026

Security Assessment

Low Risk(70/100)

Detected risks:

Secret Exposure([SKILL.md] password=, [reference.md] password=)
Security Score70/100

About pdf

The 'pdf' skill provides a comprehensive toolkit for handling PDF documents in various ways, enabling users to extract text and tables, create new PDFs, and perform actions such as merging and splitting documents. It offers functionalities for extracting metadata, rotating pages, and handling forms, making it a powerful solution for programmatically processing PDF files at scale. With Python libraries such as PyPDF, pdfplumber, and reportlab, users can easily manipulate PDF files for different needs in both simple and advanced scenarios.

Main features include text extraction, table extraction, PDF merging and splitting, and PDF creation. The toolkit supports both basic and advanced use cases, such as extracting structured data from tables and handling complex forms. It also integrates seamlessly with Python code to automate repetitive tasks related to PDF processing. Target users include developers, data analysts, and anyone who needs to automate the handling of PDF documents, whether for data extraction, document generation, or batch processing of multiple PDFs.

FAQ

How do I merge multiple PDF documents using this skill?

You can merge PDFs using the 'pypdf' library. Simply read each PDF file and add their pages to a writer instance, then save the result to a new file.

Can I extract tables from PDFs with complex layouts?

Yes, the 'pdfplumber' library allows you to extract tables with advanced layout handling. You can also refine the extraction with Pandas to combine tables from multiple pages.

Is this skill compatible with both Python 2 and Python 3?

The libraries used, such as PyPDF, pdfplumber, and reportlab, are compatible with Python 3. It is recommended to use Python 3 for best compatibility and performance.

What types of PDFs can be processed with this skill?

This skill supports a wide range of PDFs, including those with text, images, and tables. However, the success of text extraction may vary based on the quality of the PDF encoding.

Can I fill in a PDF form using this skill?

Yes, you can programmatically fill in forms by following the instructions in the forms.md document. This skill allows handling form fields and automating data input.

All Files

4 files
LICENSE.txt1.4 KB
View
SKILL.md6.9 KB
View
forms.md9.1 KB
View
reference.md16.3 KB
View

Install pdf

Download and extract the skill files to your .claude/skills/ directory.

Quick Setup:

  1. Copy the skill folder to .claude/skills/
  2. Claude will automatically detect and use the skill