ocr-and-documents

Extract text, Markdown, and tables from PDFs and scanned documents.

87|20|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/openaeon/OpenAEON --skill ocr-and-documents-openaeon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/openaeon/OpenAEON/tree/main/skills/ocr-and-documents
Command: npx skills add https://github.com/openaeon/OpenAEON --skill ocr-and-documents-openaeon

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill removes the hassle of manually reading or copying text from PDFs, scanned documents, and other file types by converting them into usable text (and optionally structured data).

Core Features & Use Cases

  • Remote-first extraction: Uses web_fetch to convert remote PDFs (including arXiv) into text without local setup.
  • Local text-based PDF parsing (pymupdf): Extracts fast plaintext, Markdown, tables, images, and basic document metadata.
  • High-quality OCR for scanned docs (marker-pdf): Runs OCR with layout-aware parsing for scanned PDFs and document types that need deep extraction.
  • Supported examples: Extract full text or Markdown from a research paper PDF, OCR a scanned receipt, and pull tables from a text-based report.

Quick Start

Use the skill to extract text from a local file named document.pdf.

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 and tables from a scanned PDF document?

For text-based PDFs, this skill uses pymupdf, a lightweight parser, to quickly extract plaintext, Markdown, tables, and images without needing OCR. Scanned documents require the marker-pdf engine instead.

Can I extract text from remote arXiv PDFs without downloading them first?

Yes, this skill uses web_fetch to ingest and extract text from remote PDFs, including arXiv links, directly without local setup. It processes the URL and returns the extracted text or Markdown.

What's the best way to convert a research paper PDF into Markdown?

The best way to convert a research paper PDF into Markdown is using the marker-pdf engine within this skill. It performs layout-aware parsing to accurately extract structured Markdown, equations, and tables from academic papers.

Do I need OCR to extract text from a text-based PDF file?

No, you do not need OCR for text-based PDFs. This skill uses pymupdf as a lightweight parser to directly extract fast plaintext, Markdown, and tables from native text-based PDF documents.

Does this document parsing tool support extracting images and metadata from local PDFs?

Yes, this document parsing tool supports local batch workflows. When using the pymupdf parser, it optionally extracts images, tables, and basic document metadata from local PDF files.

Why does my PDF text extraction return garbled characters for scanned reports?

PDF text extraction returns garbled characters for scanned reports because the file lacks an embedded text layer. You must switch from pymupdf to the marker-pdf OCR engine to process scanned document layouts accurately.