pdf

Parse, extract, and transform PDF content with Python tools.

Updated Mar 14, 2026

Search Tags:#automation #pdf #cli #forms #extraction #batch-processing #manipulation

Ready to run

npx skills add https://github.com/CaptainPhantasy/floyd-v5 --skill pdf-captainphantasy

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/CaptainPhantasy/floyd-v5/tree/main/extensibility/skills/data/pdf
Command: npx skills add https://github.com/CaptainPhantasy/floyd-v5 --skill pdf-captainphantasy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, Pillow.

What problem does it solve?

The PDF toolkit tackles the time-consuming tasks of extracting text and tables, creating and merging PDFs, and filling forms, enabling automated workflows instead of manual document handling.

Core Features & Use Cases

Automated PDF content extraction (text and tables), merging, splitting, and rotation.
Form processing and annotation-based filling, with CLI and Python library support.
Use cases include batch invoice processing, archiving documents, and generating filled reports from PDFs.

Quick Start

Run a sample script to extract text from a PDF and save it to a text file.

Frequently Asked Questions about pdf

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

FAQPage Schema

How do I extract text and tables from PDF documents in batch?▼

You can batch extract text and tables from PDFs using pdfplumber and pypdf, automating the parsing of multiple documents to transform content into usable text files for archiving or downstream processing.

Can I merge, split, and rotate PDFs using a command-line workflow?▼

Yes, the toolkit supports merging, splitting, and rotating PDFs via command-line workflows powered by pypdf, enabling automated batch manipulation of document properties across large sets of files.

Does this PDF processing approach support filling existing forms?▼

Yes, PDF form filling is supported through annotation-based methods, allowing you to generate filled reports and process batch invoices by programmatically applying data to existing PDF documents.

What is the best way to process scanned PDFs that need OCR fallbacks?▼

For scanned PDFs requiring OCR fallbacks, the toolkit leverages pdf2image and Pillow to convert document pages into images, enabling text extraction workflows when standard parsing fails on image-based content.

What Python libraries are required to automate PDF creation and modification?▼

Automating PDF creation and modification requires Python-based tooling including pypdf, pdfplumber, pdf2image, and Pillow, which collectively handle parsing, extraction, transformation, and image-based rendering tasks.