skills.rest
JKhyro
JKhyroCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text, tables, and markdown from PDFs, scans, and office files.

Updated Apr 2, 2026
Search Tags:#ocr#pdf#markdown#tables#document parsing#arxiv
One-click install
npx skills add https://github.com/JKhyro/HERMES-AGENT --skill ocr-and-documents-jkhyro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/JKhyro/HERMES-AGENT/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/JKhyro/HERMES-AGENT --skill ocr-and-documents-jkhyro

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of converting PDFs, scans, and office documents into usable text, markdown, and structured data so you can search, summarize, and reuse information without manual copy-paste.

Core Features & Use Cases

  • Remote-first extraction: For document URLs, it tries web_extract before any local processing, making it ideal for arXiv papers, reports, and publicly hosted PDFs.
  • Local PDF and OCR workflows: It uses pymupdf for fast text-based PDFs and marker-pdf for scanned documents, equations, tables, forms, reading order, and layout-heavy files.
  • Office and research documents: It supports DOCX parsing with python-docx and points PowerPoint work to the dedicated powerpoint skill.
  • Practical examples: Use it to pull text from a scanned invoice, convert a research paper into markdown, extract tables from a report, or save images embedded in a PDF.

Quick Start

Ask the AI to extract the text, tables, or markdown from your document, using web_extract for a URL or the local pymupdf and marker-pdf helpers when OCR is needed.

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 and tables from a PDF URL?▼

To extract text and tables from a document URL, the system uses web_extract first to fetch remote content, then falls back to pymupdf or marker-pdf for structured markdown and table extraction.

What is the best way to convert scanned documents to markdown?▼

Converting scanned documents to markdown uses marker-pdf to perform OCR and reconstruct reading order, accurately capturing equations, forms, and tables into clean, searchable text.

Can I use this to extract tables and equations from arXiv papers?▼

Yes, you can extract tables and equations from arXiv papers by using web_extract for the remote URL, followed by pymupdf or marker-pdf to parse complex layouts into structured markdown.

Does document parsing work with DOCX and PowerPoint files?▼

Document parsing supports DOCX files using python-docx for text extraction, while PowerPoint parsing is handled by a dedicated powerpoint skill for presentation files.

Why does my PDF text extraction fail on scanned images?▼

PDF text extraction fails on scanned images because standard text parsing cannot read embedded images; it requires OCR via marker-pdf to recognize and extract the text from scans.

How do I extract images embedded in a local PDF?▼

To extract embedded images from a local PDF, the system uses pymupdf to process the document pages, isolating and saving image assets alongside the extracted text and metadata.

Related Skills

Explore More Education & Research Skills→
fikriaffikriaf

ocr-and-documents

Extract text from PDFs and scanned documents using OCR and parsing tools.

Community
Intermediate
Dq666dingerDq666dinger
1

ocr-and-documents

Extract text and structured data from PDFs using pymupdf and marker-pdf.

Community
Intermediate
MaxServDevMaxServDev

leitura-arquivos

Extract structured text, tables, and insights from PDF, DOCX, XLSX, CSV, TXT, and Markdown files.

Community
Intermediate
langbyyilangbyyi
96

pdf

Extract text, merge documents, fill forms, and OCR scanned PDFs.

Community
Intermediate