mofa-paddleocr

Extract structured Markdown and JSON text from PDFs and images using PaddleOCR.

11|12|Updated Feb 28, 2026
One-click install
npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-paddleocr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mofa-paddleocr
Source: https://github.com/mofa-org/mofa-skills/tree/main/_unpublished/mofa-paddleocr
Command: npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-paddleocr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the tedious manual work of converting complex documents into structured Markdown and JSON by preserving layout and text content during OCR-based extraction from PDFs and images.

Core Features & Use Cases

  • OCR-based extraction for PDFs and images using PaddleOCR to preserve layout and text blocks.
  • Outputs Markdown and JSON formats for easy ingestion into knowledge bases, data pipelines, or archival systems.
  • Use Case: Digitize scanned invoices or reports to enable search, analysis, and automated data extraction.

Quick Start

Run the PaddleOCR workflow on a document PDF or image to generate Markdown and JSON outputs.

Frequently Asked Questions about mofa-paddleocr

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert scanned PDFs and images to structured Markdown and JSON?

To convert scanned PDFs and images to structured Markdown and JSON, you run a PaddleOCR and PyMuPDF workflow that renders document pages, extracts text blocks, and preserves layout. This generates per-page Markdown and JSON outputs suitable for data pipelines.

Does PaddleOCR preserve document layout when extracting text from invoices and forms?

PaddleOCR does preserve document layout when extracting text from invoices and forms. It identifies text blocks during the OCR process to maintain the structural integrity of scanned reports and contracts, outputting both Markdown and JSON formats.

What is the best way to digitize scanned contracts and reports for a searchable knowledge base?

The best way to digitize scanned contracts and reports for a searchable knowledge base is using an OCR-based extraction workflow. This approach converts document images and PDFs into structured Markdown and JSON, enabling easy ingestion and archival.

Do I need PyMuPDF to extract text from PDF files using PaddleOCR?

You do need PyMuPDF to extract text from PDF files using PaddleOCR. The Skill relies on PyMuPDF to render PDF pages into images, which PaddleOCR then processes to generate structured Markdown and JSON outputs.

Can I use this OCR workflow to parse multiple pages from a single PDF document?

You can use this OCR workflow to parse multiple pages from a single PDF document. The process relies on PaddleOCR and PyMuPDF to render each page, extracting text and layout to output per-page Markdown and JSON structured data.