pdf

Extract text, fill forms, and manipulate PDFs using Python libraries.

1|Updated Jan 1, 2026
One-click install
npx skills add https://github.com/RussianRoulette84/agentic_project --skill pdf-russianroulette84
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/RussianRoulette84/agentic_project/tree/main/.claude/skills/pdf
Command: npx skills add https://github.com/RussianRoulette84/agentic_project --skill pdf-russianroulette84

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, Pillow, and includes scripts (resource) components.

What problem does it solve?

PDFs are ubiquitous but extracting data, editing content, and automating repetitive PDF tasks (like form filling, merging, splitting, watermarking, and encryption) can be time-consuming and error-prone. This skill provides a programmable toolkit to perform those operations reliably.

Core Features & Use Cases

  • Text extraction: read and pull textual content from PDFs, including OCR on scanned documents.
  • Form handling: fill out and save both fillable and non-fillable forms, with support for text fields, checkboxes, and radio groups.
  • PDF composition and manipulation: merge, split, rotate pages, watermark, encrypt/decrypt, and create new PDFs.
  • Automation-ready workflows: supports batch processing and scripting via Python libraries (pypdf, pdfplumber, pdf2image, Pillow).
  • Use Case: Digitize and archive hundreds of invoices by extracting line items and producing a consolidated CSV while generating a searchable PDF.

Quick Start

Process a PDF by extracting text, merging pages, or filling a form and saving the result to a new 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 from a scanned PDF using Python?

Extracting text from a scanned PDF requires rendering pages to images with pdf2image and Pillow before applying OCR. This skill automates that workflow, handling both native text extraction via pdfplumber and OCR for scanned documents.

Can I fill out both fillable and non-fillable PDF forms programmatically?

Yes, you can fill out both fillable and non-fillable PDF forms programmatically. This skill supports manipulating text fields, checkboxes, and radio groups, then saving the populated results to a new PDF file.

What is the best way to merge, split, and watermark PDF documents in Python?

The best way to merge, split, and watermark PDF documents is using pypdf to parse and modify PDF streams. This skill provides an automation-ready toolkit to perform these composition and manipulation tasks reliably in batch.

Does pypdf support PDF encryption and decryption for secure document workflows?

Yes, pypdf supports PDF encryption and decryption for secure document workflows. This skill leverages those capabilities to parse, render, and modify PDF streams while handling security constraints on sensitive files.

How do I digitize and extract line items from hundreds of invoices into a CSV?

To digitize and extract line items from hundreds of invoices into a CSV, you can use this skill for batch processing. It extracts textual content and tabular data via pdfplumber, outputting structured data while generating searchable PDFs.