How do I extract tables from a PDF?

This skill provides optimized code using pdfplumber to detect and extract tables, which can then be converted into pandas DataFrames for export to Excel.

Which Python libraries are supported for PDF creation?

The skill primarily utilizes ReportLab for professional document generation, including support for headers, footers, and XML-based styling for subscripts and superscripts.

Does it support command-line PDF tools?

Yes, it provides quick-reference commands for popular CLI tools like qpdf, pdftk, and poppler-utils for fast terminal-based operations.

Can I add passwords to my PDF files?

Absolutely. The skill includes implementation patterns for encrypting PDFs with user and owner passwords using the pypdf library.

Can this skill handle scanned PDFs?

Yes, it includes specialized guidance for using pytesseract and pdf2image to perform Optical Character Recognition (OCR) on scanned documents.

PDF Processing & Extraction - Claude Code Skill

The PDF Processing Toolkit is a comprehensive skill designed to handle every aspect of PDF management within Claude Code. It provides standardized patterns for extracting text and structured tables, merging or splitting documents, and generating professional-grade PDFs from scratch using ReportLab. With built-in support for OCR on scanned documents, page rotation, watermarking, and security features like encryption, this skill transforms Claude into a powerful document automation agent capable of handling high-volume office tasks and data extraction workflows.

Características Principales

01Document security features for password protection, encryption, and watermarking

02Bulk document operations including merging, splitting, and page rotation

03Programmatic PDF generation with support for complex layouts and formatting

04OCR capabilities to convert scanned images into searchable, machine-readable text

05High-accuracy table and text extraction using pdfplumber and pandas

06707 GitHub stars

Casos de Uso

01Generating dynamic invoices or reports with custom branding and multi-page layouts

02Automating the assembly of large document packages from multiple individual PDF sources

03Extracting financial data from bank statements into structured Excel or CSV files

Tieline — product intent grounded in code

PDF Processing Toolkit

Características Principales

Casos de Uso

Background Coding Agent

Openfoam Cfd Copilot

Agent Skill Creator

Características Principales

Casos de Uso