pdf

Extract text, tables, and images from PDFs with OCR.

Updated Mar 5, 2026
One-click install
npx skills add https://github.com/zivtech/joyus-desktop --skill pdf-zivtech
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/zivtech/joyus-desktop/tree/main/.claude/skills/pdf
Command: npx skills add https://github.com/zivtech/joyus-desktop --skill pdf-zivtech

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, reportlab, pytesseract, pdf2image, pypdfium2, pandas, pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the friction of interacting with PDF documents, whether you need to extract specific data points, merge multiple files, or programmatically fill out complex forms that lack digital fields.

Core Features & Use Cases

  • Advanced PDF Manipulation: Merge, split, rotate, and encrypt documents with ease.
  • Intelligent Data Extraction: Extract text, tables, and images from both native and scanned PDFs using OCR.
  • Form Automation: Fill out static or dynamic PDF forms using coordinate-based annotation or field-mapping.

Quick Start

Ask the assistant to extract all text from the provided document using the pdf skill.

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 a scanned PDF using OCR?

To extract text and tables from a scanned PDF, OCR processing converts document images into machine-readable text. This approach uses pytesseract and pdf2image to analyze visual layouts and parse structured table data accurately.

What is the best way to automate filling out PDF forms that lack digital fields?

Automated form filling for PDFs without digital fields relies on coordinate-based annotation. This method maps data directly onto specific page coordinates to populate static documents programmatically without interactive form fields.

Can I batch process multiple PDF documents to merge, split, and rotate files?

Yes, you can batch manipulate multiple PDF documents to merge, split, and rotate files. This workflow leverages pypdf and pypdfium2 to handle document structure modifications across large file sets efficiently.

Does this approach support extracting both text and images from native PDFs?

Yes, this approach supports extracting text, tables, and images from native PDFs. It uses pdfplumber and pillow to analyze document structure, parse visual layouts, and retrieve embedded media accurately.

When do I need OCR versus native text extraction for PDF data extraction?

You need OCR for scanned documents where text is embedded as images, while native text extraction works for standard digital PDFs. Using OCR ensures accurate data extraction from image-heavy or non-selectable document formats.

How do I parse complex table structures from PDF files for data analysis?

Parsing complex table structures from PDF files involves analyzing visual layout and document metadata. Using pdfplumber and pandas, the process extracts structured table data and prepares it for downstream analysis workflows.