skills.rest
moltis-org
moltis-orgOFFICIAL
Explore all skills by this author →
WebsiteGitHub

ocr-and-documents

Extract text from PDFs and scanned documents via OCR and parsing tools.

2.8k|332|Updated Jan 29, 2026
Search Tags:#ocr#pdf#pymupdf#document-extraction#marker-pdf#web_extract
One-click install
npx skills add https://github.com/moltis-org/moltis --skill ocr-and-documents-moltis-org
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/moltis-org/moltis/tree/main/crates/skills/src/assets/productivity/ocr-and-documents
Command: npx skills add https://github.com/moltis-org/moltis --skill ocr-and-documents-moltis-org

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Text from PDFs and scanned documents is often locked in non-editable formats. This skill combines OCR and native parsers to extract readable content from PDFs, DOCX, PPTX, and other document types, enabling quick downstream processing.

Core Features & Use Cases

  • Remote URL extraction via web_extract for online documents.
  • Local text extraction using pymupdf for standard PDFs.
  • OCR-based extraction using marker-pdf for scanned pages and complex layouts.
  • Output formats favor Markdown or plain text for AI-assisted workflows.

Quick Start

Extract text from a sample PDF or scanned document and return it as Markdown.

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 using OCR?▼

Extracting text from a scanned PDF uses marker-pdf for OCR processing, recognizing complex layouts and returning the content as formatted Markdown or plain text for downstream AI workflows.

Can I extract text from a PDF hosted at a remote URL?▼

Yes, you can extract text from a PDF hosted at a remote URL by using the web_extract component, which fetches online documents and parses them into readable text without requiring local downloads.

Does this PDF extraction tool return Markdown format?▼

Yes, this PDF extraction tool returns Markdown format. It favors Markdown or plain text outputs when processing PDFs, DOCX, and PPTX files to enable quick downstream processing in AI-assisted workflows.

What is the best way to parse text from a standard PDF versus a scanned document?▼

The best way to parse text is using pymupdf for standard native PDFs, while switching to marker-pdf for scanned documents and complex layouts, ensuring accurate text extraction across different file types.

What happens when extracting text from an unsupported document format?▼

When extracting text from an unsupported document format, the skill provides clear error handling to indicate the incompatibility, ensuring your Python 3 environment processes only supported files like PDFs, DOCX, and PPTX.

Related Skills

Explore More Data & Analytics Skills→
photonics-dhlphotonics-dhl

ocr-and-documents

Extract text and structured data from PDFs and documents using OCR and parsing tools.

Community
Intermediate
malue-aimalue-ai
36

raglite

Index local PDF, Markdown, and plain text documents into structured Markdown for semantic search.

Official
Intermediate
ricardorochericardoroche
2

rag-design-patterns

Standardizes chunking, vector database integration, embedding management, and retrieval reranking for RAG pipelines.

Community
Intermediate
lenadlmlenadlm

image-ocr

Extract text from images using Tesseract and cloud OCR APIs.

Community
Intermediate