skills.rest
zangjeicy
zangjeicyCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text and structured data from PDFs and scanned documents using OCR.

Updated Jul 13, 2026
Search Tags:#automation#ocr#pdf#research#text-extraction#document-parsing
One-click install
npx skills add https://github.com/zangjeicy/Hermes --skill ocr-and-documents-zangjeicy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/zangjeicy/Hermes/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/zangjeicy/Hermes --skill ocr-and-documents-zangjeicy

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill solves the challenge of extracting text, tables, and structured data from diverse document formats, including scanned PDFs, images, and complex layouts that standard parsers fail to read.

Core Features & Use Cases

  • Intelligent Extraction: Choose between lightweight text parsing or high-quality OCR for scanned documents and complex equations.
  • Versatile Format Support: Handles PDFs, DOCX, PPTX, XLSX, HTML, and EPUB files seamlessly.
  • Use Case: Use this skill to convert a stack of scanned research papers or handwritten notes into clean, searchable Markdown files for your knowledge base.

Quick Start

Use the ocr-and-documents skill to extract all text and tables from the document named research_paper.pdf.

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 for research?▼

To extract text from scanned PDFs, this skill uses marker-pdf for high-accuracy OCR and layout analysis. It handles complex layouts and equations, converting scanned research papers and notes into clean, searchable Markdown files.

Can I parse tables and structured data from PDFs and other file formats?▼

Yes, you can parse tables and structured data from PDFs, DOCX, PPTX, XLSX, HTML, and EPUB files. The skill utilizes pymupdf and pandas to extract structured content, supporting batch processing for data entry and archival tasks.

What's the best way to convert a batch of documents to Markdown?▼

The best way to convert documents to Markdown is using this skill's batch processing capability. It intelligently selects between lightweight pymupdf text parsing and marker-pdf OCR to transform diverse file formats into searchable Markdown files.

Does this text extraction tool work with complex layouts and equations?▼

Yes, this text extraction tool works with complex layouts and equations by utilizing marker-pdf for layout-intensive document parsing. It switches to high-quality OCR when standard lightweight parsing fails to read intricate document structures.

When should I use lightweight text extraction instead of OCR for PDF parsing?▼

You should use lightweight text extraction via pymupdf for standard digital PDFs to save processing time. Switch to marker-pdf OCR for scanned documents, images, or files containing complex equations and layout-intensive structures.

Related Skills

Explore More Education & Research Skills→
rysweetrysweet
72

pdf

Extracts text and tables from PDFs, creates, merges, and handles OCR for scanned documents.

Community
Advanced
treasure-datatreasure-data
21

pytd

Query Treasure Data via Presto or Hive and load pandas DataFrames.

Official
Intermediate
zeronx798zeronx798

chroma

Manage vector collections and perform similarity searches with metadata filtering.

Community
Intermediate
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