ocr-and-documents

Extract text, tables, and OCR content from PDFs and documents.

14|2|Updated Mar 29, 2026

Search Tags:#ocr #pdf #pymupdf #document-processing #text-extraction #marker-pdf #web_extract

Ready to run

npx skills add https://github.com/gquthier/CLAWG --skill ocr-and-documents-gquthier

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/gquthier/CLAWG/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/gquthier/CLAWG --skill ocr-and-documents-gquthier

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, pymupdf4llm, marker, and includes scripts (resource) components.

What problem does it solve?

Extract text from PDFs and documents, including scanned files, to produce searchable, machine-readable content.

Core Features & Use Cases

Remote URL extraction via web_extract for online documents
Local extraction using pymupdf for text-based PDFs and marker-pdf for OCR/scanned documents
DOCX and PPTX handling guidance (via respective tools) and Markdown output for easy integration
Use cases include converting research papers, reports, and manuals into searchable text and structured data

Quick Start

Provide a document URL or a local PDF and ask me to extract text.

Frequently Asked Questions about ocr-and-documents

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

FAQPage Schema

How do I extract text from a scanned PDF?▼

To extract text from a scanned PDF, this Skill uses marker-pdf for OCR processing, converting non-text content into machine-readable, searchable text. It handles tables and text from local files and remote URLs.

Can I extract text from a PDF via a remote URL?▼

Yes, you can extract text from a PDF via a remote URL using the web_extract functionality. This allows online documents to be processed directly without needing a local copy.

What is the best way to convert a PDF to Markdown?▼

The best way to convert a PDF to Markdown is by using pymupdf4llm for text-based PDFs and marker-pdf for scanned documents, producing structured Markdown output for easy integration.

Does this OCR tool work with DOCX and PPTX files?▼

Yes, this OCR tool works with DOCX and PPTX files by providing handling guidance and utilizing optional python-docx support to extract text and output Markdown.

Why does marker-pdf need to be used instead of pymupdf?▼

Marker-pdf is used instead of pymupdf when processing scanned documents or images that require OCR, whereas pymupdf is sufficient for extracting text directly from text-based PDFs.

What document formats are supported for local text extraction?▼

Local text extraction supports PDF, DOCX, PPTX, and EPUB files, converting text, tables, and non-text content into searchable, machine-readable Markdown.