skills.rest
AlvaroBiano
AlvaroBianoCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown or structured data.

Updated May 2, 2026
Search Tags:#ocr#pdf#pymupdf#document-processing#text-extraction#marker-pdf
One-click install
npx skills add https://github.com/AlvaroBiano/hermes-agent --skill ocr-and-documents-alvarobiano
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/AlvaroBiano/hermes-agent/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/AlvaroBiano/hermes-agent --skill ocr-and-documents-alvarobiano

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extract text from PDFs and documents that contain both text and images by applying OCR and parsing techniques to produce searchable, editable output.

Core Features & Use Cases

  • OCR-based extraction for scanned PDFs, with multi-language support and layout-aware processing.
  • Remote URL extraction is attempted first (web_extract) and local extractors (pymupdf or marker-pdf) are used as fallbacks.
  • Supports EPUB, DOCX, PPTX outputs and Markdown or structured data suitable for further analysis or archival.

Quick Start

Provide a document path or URL to start extracting text using the OCR-and-documents 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 PDFs using OCR?▼

You can extract text from scanned PDFs using OCR by providing a local file path or URL. The tool applies layout-aware processing to parse text and images, outputting searchable Markdown or structured data for downstream analysis.

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

The best way to convert a PDF document to Markdown is using parsing backends like pymupdf or marker-pdf. These tools analyze document layouts and extract text directly into Markdown format suitable for further analysis or archival.

Can I extract text from a document provided via a URL?▼

Yes, you can extract text from a document provided via a URL. Remote URL extraction is attempted first via web_extract, with local extractors like pymupdf or marker-pdf used as fallbacks to ensure successful text retrieval.

Does this text extraction tool support formats other than PDF?▼

Yes, the text extraction tool supports formats beyond PDF. It can process and output EPUB, DOCX, and PPTX files, converting them into Markdown or structured data suitable for further analysis or archival.

Do I need to install pymupdf and marker-pdf to extract document text?▼

Yes, you need to install external dependencies such as pymupdf, pymupdf4llm, marker, and marker-pdf to extract document text. These libraries provide the necessary OCR and parsing backends for local file processing.

Why does my PDF text extraction fail on complex layouts?▼

PDF text extraction may fail on complex layouts if the primary backend struggles with the structure. The tool attempts web extraction first, then falls back to layout-aware backends like marker-pdf to better handle intricate document formatting.

Related Skills

Explore More Education & Research Skills→
webdevtodayjasonwebdevtodayjason

ocr-and-documents

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

Community
Advanced
teradata-labsteradata-labs
7

td-vector-distance

Calculate vector distances with TD_VectorDistance in Teradata Vantage.

Official
Advanced
Sake-TeamSake-Team

regex-vs-llm-structured-text

Routes structured text parsing decisions between regex and LLM validation.

Official
Advanced
afel6afel6

ocr-and-documents

Extract text and structured content from PDFs and scanned documents.

Community
Intermediate