skills.rest
projectedanx
projectedanxCOMMUNITY
Explore all skills by this author →
𝕏@ALifeInArtifyAIGitHub

ocr-and-documents

Extract text, tables, and images from PDFs and office files.

1|Updated May 12, 2026
Search Tags:#documents#ocr#pdf#research#extraction#text-extraction
One-click install
npx skills add https://github.com/projectedanx/hermes-agent --skill ocr-and-documents-projectedanx
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/projectedanx/hermes-agent/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/projectedanx/hermes-agent --skill ocr-and-documents-projectedanx

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill solves the challenge of extracting information from diverse document formats, including scanned PDFs, images, and complex layouts, which are otherwise inaccessible to standard text parsers.

Core Features & Use Cases

  • Intelligent Extraction: Choose between lightweight text parsing or high-quality OCR with layout analysis.
  • Versatile Format Support: Handles PDFs, DOCX, PPTX, XLSX, HTML, and EPUB files.
  • Use Case: Use this skill to convert a stack of scanned paper invoices into structured Markdown or JSON data for your database, or to extract specific tables from a research paper.

Quick Start

Use the ocr-and-documents skill to extract text from the local file report.pdf using the lightweight pymupdf engine.

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 PDFs and complex document layouts?▼

To extract text from scanned PDFs, this skill uses high-quality OCR with layout analysis via marker-pdf. It handles complex documents by converting them into structured Markdown or JSON data.

What is the best way to convert scanned invoices into structured data?▼

The best way to convert scanned invoices into structured data is using OCR and document extraction tools that support layout analysis. This skill parses diverse formats and outputs structured Markdown or JSON for database integration.

Does this document extraction approach support DOCX, PPTX, and EPUB files?▼

Yes, this document extraction approach supports versatile formats including DOCX, PPTX, XLSX, HTML, and EPUB files. It handles both scanned PDFs and office files using pymupdf and marker-pdf engines.

How do I extract tables from a research paper PDF?▼

To extract tables from a research paper PDF, use the high-quality OCR extraction mode with layout analysis. This skill identifies and extracts tables alongside text and images, outputting structured data formats like Markdown.

Do I need PyMuPDF and Torch to run OCR document extraction?▼

Yes, you need PyMuPDF, pymupdf4llm, marker-pdf, Torch, and Pandas installed to run OCR document extraction. These dependencies enable both lightweight text parsing and advanced layout analysis for complex files.

When should I use lightweight text extraction instead of high-quality OCR?▼

Use lightweight text extraction instead of high-quality OCR when processing standard digital PDFs without scanned images or complex layouts. Lightweight parsing via PyMuPDF is faster, while OCR with layout analysis is needed for scanned documents.

Related Skills

Explore More Data & Analytics Skills→
CyapstayeCyapstaye
9

ocr-and-documents

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

Community
Intermediate
legoutlegout
3

table-extractor

Extract structured tabular data from PDF documents using camelot.

Community
Intermediate
hkjanghkjang

batch

Orchestrate parallel file operations with discovery, chunking, and execution.

Community
Advanced
cxnaivecxnaive

ocr-and-documents

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

Community
Intermediate