skills.rest
dawsonblock
dawsonblockCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown or plain text.

Updated Apr 26, 2026
Search Tags:#documents#ocr#pdf#pymupdf#text-extraction#marker-pdf#web_extract
One-click install
npx skills add https://github.com/dawsonblock/HERMY --skill ocr-and-documents-dawsonblock
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/dawsonblock/HERMY/tree/main/hermes-agent-2026.4.23/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/dawsonblock/HERMY --skill ocr-and-documents-dawsonblock

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extract text from PDFs and scanned documents for downstream processing and analysis.

Core Features & Use Cases

  • Remote URL extraction using web_extract for online documents.
  • Local text-based PDF extraction using pymupdf for fast results.
  • OCR-enabled processing with marker-pdf for scanned documents and multi-language support.
  • DOCX and PPTX handling guidance (docx parsing and links to powerpoint skill) for broader document types.
  • Use case: convert a batch of PDFs into searchable text for indexing and research notes.

Quick Start

Provide a PDF or document URL and I will extract the text using the best available method (web_extract for URLs, pymupdf for text PDFs, or marker-pdf for OCR).

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?▼

This tool uses marker-pdf for OCR-based extraction from scanned documents, converting them into searchable Markdown or plain text while preserving document structure and metadata.

What is the best way to extract text from a local text-based PDF?▼

For local text-based PDFs, the skill uses pymupdf to provide fast text extraction, outputting readable Markdown or plain text along with optional metadata and images.

Can I extract text directly from a remote document URL?▼

Yes, you can extract text from remote document URLs using the web_extract method, which fetches online documents and outputs extracted text for downstream processing.

Does marker-pdf work with DOCX and PPTX files?▼

marker-pdf focuses on PDF and scanned documents; however, the skill provides docx parsing guidance and links to a powerpoint skill for handling broader document types like DOCX and PPTX.

How do I convert a batch of PDFs into searchable text for indexing?▼

You can convert a batch of PDFs into searchable text by running them through the skill's extraction pipeline, which outputs Markdown or plain text suitable for indexing and research notes.

What formats are supported for PDF text extraction?▼

The skill supports local text-based PDFs via pymupdf, scanned documents via marker-pdf, and remote URLs via web_extract, outputting Markdown or plain text with optional metadata and images.

Related Skills

Explore More Data & Analytics Skills→
Simon-Copilot-StudioSimon-Copilot-Studio

ocr-and-documents

Extracts text from PDFs and scanned images using OCR tools like marker-pdf and pymupdf.

Community
Intermediate
bdambrosiobdambrosio
10

fetch-text

Fetch and extract text from URLs, base64 PDFs, and Note or Collection IDs.

Community
Intermediate
WarrenZhu050413WarrenZhu050413
7

pdftext

Extract text from PDFs with Docling or PyMuPDF into Markdown or plain text.

Community
Intermediate
photonics-dhlphotonics-dhl

ocr-and-documents

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

Community
Intermediate