skills.rest
markwang2658
markwang2658COMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text from PDFs and scanned documents using pymupdf and marker-pdf.

31|3|Updated May 7, 2026
Search Tags:#documents#ocr#pdf#pymupdf#extract#marker-pdf
One-click install
npx skills add https://github.com/markwang2658/hermes-windows-native --skill ocr-and-documents-markwang2658
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/markwang2658/hermes-windows-native/tree/main/hermes-agent/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/markwang2658/hermes-windows-native --skill ocr-and-documents-markwang2658

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill eliminates manual transcription by converting content from PDFs and scanned documents into searchable, editable text using fast, local extraction (pymupdf) and high-quality OCR via marker-pdf.

Core Features & Use Cases

  • Fast text extraction from PDFs with pymupdf
  • OCR-based processing for scanned documents and complex layouts using marker-pdf
  • Optional image extraction and metadata retrieval from documents

Quick Start

Run the extraction on a sample PDF to see plain text output.

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?▼

To extract text from scanned PDFs, this skill uses marker-pdf for high-quality OCR processing, converting image-based content into searchable and editable text automatically.

What is the best way to convert native text PDFs into editable text?▼

For native text PDFs, fast local extraction is handled by pymupdf, which quickly retrieves the embedded text without needing OCR, providing immediate editable output.

Does this PDF extraction approach work for administrative and archival workflows?▼

Yes, this text extraction supports research, administration, and archival workflows, handling both native text PDFs and scanned documents to eliminate manual transcription tasks.

Can I extract images and metadata from PDFs along with the text?▼

Yes, the extraction process includes optional image extraction and metadata retrieval from documents, allowing you to capture visual content and document properties alongside the text.

Do I need pymupdf and marker-pdf to extract text from complex layouts?▼

Yes, marker-pdf is specifically used for OCR-based extraction of scanned documents and complex layouts, while pymupdf handles fast native text extraction from standard PDFs.

Related Skills

Explore More Data & Analytics Skills→
MarbleSodasMarbleSodas

ocr-and-documents

Extract searchable text from PDFs and scanned documents via web or local parsing.

Community
Intermediate
profmikegreeneprofmikegreene
1

plan-ingestion

Parses pilot plans and hypotheses into structured JSON or tabular data for downstream analysis.

Community
Intermediate
GitnappGitnapp

ocr-and-documents

Extract text and structured information from PDFs and scanned documents.

Community
Advanced
whichguywhichguy

ocr-and-documents

Extract and edit text from PDFs and scanned documents using OCR.

Community
Intermediate