skills.rest
AissenLiu
AissenLiuCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text from PDFs and scanned documents via web_extract, pymupdf, or marker-pdf.

Updated Apr 27, 2026
Search Tags:#ocr#pdf#pymupdf#document-processing#text-extraction#marker#scanned-docs
One-click install
npx skills add https://github.com/AissenLiu/EasyHermes --skill ocr-and-documents-aissenliu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/AissenLiu/EasyHermes/tree/main/hermes-agent/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/AissenLiu/EasyHermes --skill ocr-and-documents-aissenliu

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PDFs and scanned documents often contain valuable text that is locked behind images or complex layouts. This skill extracts and makes the content searchable for analysis, archiving, or data integration.

Core Features & Use Cases

  • Remote URL extraction via web_extract for PDFs on the web.
  • Local extraction options using pymupdf for text-based PDFs and marker-pdf for OCR-heavy documents.
  • Exports include Markdown, tables, images, and metadata, with helpful disk-space checks and format guidance.

Quick Start

Extract text from a sample PDF or scanned document and output 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 PDFs for downstream processing?▼

To extract text from scanned PDFs, apply remote extraction via web_extract first, then fallback to local extractors like pymupdf for text-based PDFs and marker-pdf for OCR. This workflow outputs searchable text, Markdown, tables, images, and metadata for analysis.

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

The best way to convert scanned documents to Markdown is using marker-pdf for OCR-heavy files or pymupdf for text-based PDFs. These local extractors fallback on remote web_extract to provide structured Markdown exports alongside tables, images, and metadata.

Does marker-pdf work for extracting tables and images from PDFs?▼

Yes, marker-pdf works for extracting tables and images from OCR-heavy PDFs. Together with pymupdf for text-based PDFs, the skill provides CLI exports for Markdown, tables, images, and metadata, including disk-space checks and format guidance.

Can I use pymupdf to extract text from remote PDF URLs?▼

Yes, you can extract text from remote PDF URLs by applying web_extract first for remote extraction. If remote extraction fails, pymupdf handles text-based PDFs locally while marker-pdf processes scanned documents via OCR as a fallback.

What are the limitations of using OCR for document text extraction?▼

Limitations of OCR document text extraction include disk-space constraints, which the skill actively checks, and format compatibility. The skill provides guidance for supported formats and applies pymupdf or marker-pdf locally only when remote web_extract extraction is unavailable.

Do I need pandas to extract metadata from PDF documents?▼

Pandas is included as a dependency to support exporting extracted PDF content like tables and metadata. The skill uses pymupdf and marker-pdf to parse documents, then leverages pandas for structured data outputs required for downstream analysis.

Related Skills

Explore More Data & Analytics Skills→
DaddyElonMusk69DaddyElonMusk69

ocr-and-documents

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

Community
Intermediate
smilebank7smilebank7
2

Extract Materials

Extract text, tables, and equations from PDFs, PPTX, DOCX, and images into Markdown.

Community
Intermediate
WarrenZhu050413WarrenZhu050413
7

pdftext

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

Community
Intermediate
gqf2008gqf2008

ocr-and-documents

Extract text from PDFs, DOCX, and PPTX using web_extract, pymupdf, or marker-pdf.

Community
Intermediate