pdf

Extract text and structured data from PDFs with OCR for scanned images.

25|3|Updated Jul 14, 2026
One-click install
npx skills add https://github.com/nimadorostkar/Claude-Skills-collection --skill pdf-nimadorostkar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/nimadorostkar/Claude-Skills-collection/tree/main/skills/documents/pdf
Command: npx skills add https://github.com/nimadorostkar/Claude-Skills-collection --skill pdf-nimadorostkar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pdfplumber, PyMuPDF, pytesseract, Pillow.

What problem does it solve?

This skill resolves the common frustration of dealing with inaccessible PDF content, such as scanned documents without text layers, complex multi-column layouts, or non-structured tables that break standard extraction tools.

Core Features & Use Cases

  • Intelligent Extraction: Distinguishes between native text and scanned images, automatically triggering OCR when necessary.
  • Layout Preservation: Handles complex table extraction and multi-column document structures that standard tools often mangle.
  • Document Manipulation: Provides a robust toolkit for merging, splitting, rotating, and watermarking pages, as well as filling form fields.

Quick Start

Use the pdf skill to extract all structured table data from the provided financial report and save it into a clean dataframe.

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 scanned PDF documents that have no text layer?

To extract text from scanned PDF documents, the skill automatically triggers OCR using pytesseract and Pillow. It detects missing text layers and applies optical character recognition to retrieve inaccessible content from image-only files.

What is the best way to extract complex tables and multi-column layouts from a PDF?

The best way to extract complex tables and multi-column layouts from a PDF is using pdfplumber integration. This ensures high-fidelity data retrieval and layout preservation, preventing the structural mangling that standard extraction tools often cause.

Can I merge, split, and populate form fields across different PDF architectures?

You can merge, split, rotate, and populate form fields across various PDF architectures. The skill provides a robust toolkit for complex document manipulation, including watermarking pages and filling interactive forms natively.

Does PyMuPDF work well for high-fidelity PDF data extraction?

PyMuPDF works well for high-fidelity PDF data extraction by ensuring accurate text retrieval and layout preservation. It integrates seamlessly with the skill to handle complex document structures and multi-column formatting robustly.

Why does standard PDF extraction fail on non-structured tables and scanned documents?

Standard PDF extraction fails on non-structured tables and scanned documents because they lack accessible text layers and have complex layouts. The skill overcomes this by combining intelligent extraction with OCR to process inaccessible content.