skills.rest
afel6
afel6COMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text and structured content from PDFs and scanned documents.

Updated Mar 25, 2026
Search Tags:#ocr#pdf#docx#pymupdf#text-extraction#marker-pdf#web-extract
One-click install
npx skills add https://github.com/afel6/scal-ai-pipeline --skill ocr-and-documents-afel6
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/afel6/scal-ai-pipeline/tree/main/hermes_skills_library/productivity/ocr-and-documents
Command: npx skills add https://github.com/afel6/scal-ai-pipeline --skill ocr-and-documents-afel6

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extracts text and structured content from PDFs, scanned images, and common document formats to eliminate manual transcription and make archival documents searchable and analysable.

Core Features & Use Cases

  • Web-first extraction for remote documents using URL fetch and conversion tools to avoid local dependencies.
  • Lightweight local parsing of text-based PDFs with pymupdf for fast extraction, splitting, merging, and basic table handling.
  • High-quality OCR and layout-aware extraction with marker-pdf for scanned documents, equations, forms, and complex layouts, including image export and optional LLM boosting.
  • Practical use cases include ingesting arXiv papers, digitizing scanned reports, extracting tables and images for data analysis, and converting DOCX/PPTX into structured text for reporting.

Quick Start

Extract text and metadata from the PDF at https://arxiv.org/pdf/2402.03300 and return the content in 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 scanned PDF documents?▼

This Skill extracts text from scanned PDFs by using marker-pdf for OCR and layout-aware analysis, converting complex forms and images into structured markdown while preserving tables and equations.

Can I parse remote PDFs from a URL without downloading them locally?▼

Yes, you can parse remote PDFs from a URL using the Skill's web_extract dependency, which fetches and converts remote documents directly into structured text without requiring local file downloads.

What is the best way to extract tables and equations from PDFs?▼

The best way to extract tables and equations from PDFs is using marker-pdf for layout-aware parsing, which accurately digitizes complex structures and exports them into structured markdown for research and data analysis.

Does pymupdf support lightweight local PDF text extraction?▼

Yes, pymupdf supports lightweight local PDF text extraction by providing fast parsing, splitting, and merging capabilities for text-based PDFs without requiring heavy OCR model downloads or complex layout analysis.

How do I convert DOCX and PPTX files into structured text for reporting?▼

To convert DOCX and PPTX files into structured text, this Skill applies extraction workflows that transform common document formats into searchable, editable markdown content for research and reporting.

Related Skills

Explore More Education & Research Skills→
WarrenZhu050413WarrenZhu050413
7

pdftext

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

Community
Intermediate
rangerrick337rangerrick337
10

pdf-conversion

Convert PDFs to Markdown with preserved formatting and embedded images.

Community
Intermediate
eddieluengeddielueng
1

ocr-and-documents

Extract text from PDFs and scanned documents via URL or local OCR tools.

Community
Intermediate
projectedanxprojectedanx
1

ocr-and-documents

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

Community
Intermediate