skills.rest
CUexter
CUexterCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text and metadata from PDFs, DOCX, and PPTX into Markdown.

2|Updated Mar 26, 2026
Search Tags:#ocr#pdf#markdown#document-processing#text-extraction#web-extract
One-click install
npx skills add https://github.com/CUexter/hermes-agent --skill ocr-and-documents-cuexter
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/CUexter/hermes-agent/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/CUexter/hermes-agent --skill ocr-and-documents-cuexter

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extracts text from PDFs, scanned documents, images, and other file formats using OCR and document parsing, enabling quick digital access and archival search.

Core Features & Use Cases

  • Remote URL extraction via web_extract for PDFs and documents; Always try web_extract first to convert PDFs to Markdown via Firecrawl.
  • Local extraction using pymupdf for text-based PDFs with fast, lightweight processing.
  • OCR-based extraction with marker-pdf for scanned documents, multi-language support, and complex layouts.
  • DOCX and PPTX handling guidance; outputs Markdown suitable for integration with other tools.

Quick Start

Provide a document path or URL and I will extract its text and metadata, using pymupdf by default and marker-pdf if OCR is required.

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 PDF URL or local file into Markdown?▼

To extract text from a PDF URL or local file into Markdown, provide the document path or link. The system defaults to web_extract for remote URLs and pymupdf for local text-based PDFs, outputting Markdown with optional metadata.

What is the best way to perform OCR on scanned documents for multi-language support?▼

The best way to perform OCR on scanned documents with multi-language support is using the marker-pdf extractor. It handles complex layouts and converts scanned document images into searchable Markdown text.

Does this PDF text extraction approach support DOCX and PPTX files?▼

Yes, this PDF text extraction approach supports DOCX and PPTX files. It provides specific handling guidance for these formats alongside its core PDF parsing, ultimately converting their content into Markdown output.

When do I need to use marker-pdf versus pymupdf for document processing?▼

You need marker-pdf for OCR-based extraction of scanned documents or complex layouts, whereas pymupdf is suited for fast, lightweight text extraction from text-based PDFs without OCR requirements.

Why does the extraction tool try web_extract first for PDFs?▼

The extraction tool tries web_extract first for PDFs to efficiently convert remote URLs to Markdown via Firecrawl before falling back to local processing methods like pymupdf or marker-pdf.

Related Skills

Explore More Data & Analytics Skills→
huidgehuidge
2

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown.

Community
Advanced
Hollis36Hollis36
1

pdf

Extract text and tables from PDFs using Python libraries.

Community
Intermediate
zzafergokzzafergok
1

documents

Automate document processing across DOCX, PDF, PPTX, and XLSX formats.

Community
Advanced
paxlabs-incpaxlabs-inc
7

ocr-and-documents

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

Community
Intermediate