skills.rest
JamesFincher
JamesFincherCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text and structured content from PDFs via OCR or pymupdf.

Updated May 4, 2026
Search Tags:#ocr#pdf#table extraction#document parsing#scanned documents#markdown extraction
One-click install
npx skills add https://github.com/JamesFincher/gengar --skill ocr-and-documents-jamesfincher
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/JamesFincher/gengar/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/JamesFincher/gengar --skill ocr-and-documents-jamesfincher

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Extracting usable text from PDFs, scanned documents, and image-based files is slow and often requires manual copying, especially when documents contain complex layouts or OCR-needed content.

Core Features & Use Cases

  • URL-first extraction for PDFs: Uses web extraction for documents that have a URL to convert PDF-to-markdown without local dependencies.
  • Lightweight text extraction: Supports fast extraction for text-based PDFs (and other supported formats) using pymupdf with optional markdown output, tables, images, pages selection, and basic metadata.
  • High-quality OCR for scans: Uses marker-pdf when OCR is required (scans, equations/LaTeX, forms, and advanced layout), including optional JSON output and saving extracted images.
  • Use Cases: Turn arXiv PDFs into markdown for research workflows, convert scanned receipts into searchable text, or extract tables and key sections from multi-page reports.

Quick Start

Ask the agent to extract OCR-ready text from a scanned PDF by using the marker-pdf path when local OCR is needed, otherwise falling back to the lightweight pymupdf workflow.

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 scanned PDF documents that require OCR?▼

To extract text from scanned PDFs requiring OCR, this Skill uses marker-pdf for high-quality layout analysis and OCR processing, supporting complex layouts, equations, and forms with optional JSON output and image extraction.

What's the best way to convert a multi-page PDF report into markdown?▼

Converting multi-page PDF reports into markdown is handled through the pymupdf lightweight extraction path for text-based PDFs, or via URL-first web extraction to convert PDF-to-markdown without local dependencies.

Does this PDF extraction tool work with arXiv papers for research workflows?▼

Yes, this PDF extraction tool works with arXiv papers by turning them into markdown for research workflows, supporting both URL-based extraction and local processing pipelines for document ingestion.

Can I extract tables and structured content from PDF files?▼

Yes, you can extract tables and structured content from PDF files using pymupdf for fast text-based extraction with optional markdown output, or marker-pdf for advanced layout analysis when OCR is needed.

Do I need pymupdf or marker-pdf installed to extract text from local PDFs?▼

You need pymupdf for fast non-OCR extraction of text-based PDFs, or marker-pdf when high-quality OCR and layout analysis are required for scanned documents, equations, and forms.

When should I use URL-first extraction instead of local PDF processing?▼

URL-first extraction should be used when you have a document URL and want to convert PDF-to-markdown without local dependencies, with automatic fallback to local processing using pymupdf or marker-pdf when needed.

Related Skills

Explore More Education & Research Skills→
huidgehuidge
2

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown.

Community
Advanced
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
raja21068raja21068
2

arxiv

Search arXiv by topic or ID and download PDFs into a local library.

Community
Intermediate
projectedanxprojectedanx
1

ocr-and-documents

Extract text, tables, and images from PDFs and office files.

Community
Intermediate