skills.rest
cabezno
cabeznoCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text and markdown from PDFs and scanned files via OCR.

Updated May 15, 2026
Search Tags:#ocr#pdf#research#document parsing#scanned documents#markdown extraction
One-click install
npx skills add https://github.com/cabezno/bmb-encover-agent --skill ocr-and-documents-cabezno
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/cabezno/bmb-encover-agent/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/cabezno/bmb-encover-agent --skill ocr-and-documents-cabezno

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill removes the friction of manually copying content out of PDFs and scanned documents by extracting readable text (and optionally tables and images) into formats you can work with.

Core Features & Use Cases

  • Remote-first extraction: Converts URL-based PDFs (e.g., arXiv PDFs) via web_extract to markdown before attempting local processing.
  • Lightweight text extraction: Uses pymupdf for fast, local extraction of text and markdown from text-based PDFs.
  • High-quality OCR extraction: Uses marker-pdf for scanned PDFs needing OCR, equations/layout recovery, and richer document parsing.
  • Practical use cases: Turn research papers into searchable notes, extract study/reference text from scanned articles, and prepare document content for downstream summarization or indexing.

Quick Start

Use the ocr-and-documents skill to extract and convert the attached file 'paper.pdf' into markdown for easy reading and search.

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 for research?▼

To extract text from a scanned PDF, this Skill uses marker-pdf to perform OCR, recovering readable text, equations, and layout information, and converts the document content into markdown.

Can I convert an arXiv PDF to markdown from a URL?▼

Yes, you can convert an arXiv PDF to markdown from a URL by using the web_extract path, which fetches remote documents before attempting local file processing.

What is the best way to parse text from a local PDF without OCR?▼

For parsing text from local, text-based PDFs without OCR, the Skill uses pymupdf to perform fast, lightweight extraction of text and markdown directly from the document.

Does this PDF extraction method support tables and images?▼

Yes, the PDF extraction process supports optional table extraction and image artifact handling, allowing you to capture complex document layouts alongside the readable text output.

Can I batch process scanned articles for searchable text?▼

Yes, you can batch process scanned articles and document archives to generate searchable text, applying OCR and markdown extraction across multiple files for research workflows.

Related Skills

Explore More Education & Research Skills→
gztcodegztcode

ocr-and-documents

Extract text from PDFs, scanned documents, and images using OCR.

Community
Advanced
QuantumBFSQuantumBFS
60

download-ref

Fetch academic paper metadata and PDFs from arXiv or DOI sources.

Official
Advanced
guccangguccang
3

ocr-and-documents

Extract text, tables, metadata, and images from PDFs and scanned documents.

Community
Advanced
dawsonblockdawsonblock

create-a-tool-named

Converts PDFs to Markdown text and preserves formatting for easy reuse.

Community
Basic