skills.rest
justcyl
justcylCOMMUNITY
Explore all skills by this author →
GitHub

pdf-process-mineru

Extract structured data from PDF documents into Markdown or JSON using MinerU.

Updated Feb 23, 2026
Search Tags:#ocr#pdf#markdown#json#mineru#data-extraction#pdf-parsing
One-click install
npx skills add https://github.com/justcyl/my-skills --skill pdf-process-mineru
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf-process-mineru
Source: https://github.com/justcyl/my-skills/tree/main/.skills/archived-skills/pdf-process-mineru
Command: npx skills add https://github.com/justcyl/my-skills --skill pdf-process-mineru

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

PDF documents are often locked in inaccessible formats, and manual extraction is time-consuming. This skill uses MinerU to parse PDFs and convert content into machine-readable Markdown or JSON, enabling automated data extraction, structure preservation, and downstream processing.

Core Features & Use Cases

  • PDF to Markdown: preserve document structure, formulas, tables, and images with OCR support.
  • PDF to JSON: output detailed layout and structure with blocks, images, tables, and formulas.
  • Customizable parsing: choose backend, language, enable_formula, enable_table, and page range for precise control.

Quick Start

Use the PDF Parser to convert a PDF file into Markdown or JSON by specifying the input PDF and an output directory.

Frequently Asked Questions about pdf-process-mineru

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

FAQPage Schema
How do I convert a scanned PDF to Markdown while preserving formulas and tables?▼

To convert a scanned PDF to Markdown, this skill applies MinerU OCR to extract text, formulas, and tables while preserving document structure. It outputs machine-readable Markdown, enabling automated data extraction from academic papers and technical reports.

Can I extract structured JSON data from PDF documents?▼

Yes, you can extract structured JSON data from PDF documents. The parser outputs detailed layout blocks, images, tables, and formulas as JSON, providing structured data for downstream processing and automated workflows.

Does MinerU PDF parsing support CPU-only environments without GPU acceleration?▼

MinerU PDF parsing supports CPU-only environments by falling back to CPU processing when GPUs are unavailable. It includes robust error handling to ensure PDF data extraction completes even without hardware acceleration.

How can I parse specific page ranges from a large PDF file?▼

You can parse specific page ranges from a large PDF file using customizable parsing options. The skill allows page range control, enabling precise extraction of targeted sections into Markdown or JSON outputs.

What is the best way to extract data from academic papers with complex layouts?▼

The best way to extract data from academic papers with complex layouts is using MinerU parsing. It applies OCR to preserve structure, formulas, and tables, converting technical reports into editable Markdown or JSON formats.

How do I configure language and backend settings for PDF OCR processing?▼

You configure language and backend settings for PDF OCR processing through customizable parsing options. The skill supports backend selection and language options to ensure accurate data extraction across different document types.

Related Skills

Explore More Software Engineering Skills→
surus-latsurus-lat
8

synthesize-data

Generate synthetic benchmark datasets as JSONL input-output pairs from task specifications.

Official
Intermediate
sahiixxsahiixx

ai-tools

Generate embeddings, analyze images, and extract structured JSON from text and documents.

Community
Advanced
sjtu-sai-agentssjtu-sai-agents
215

pdf

Extract text and tables from PDFs using Python libraries.

Official
Advanced
Ubuntu-Tech-SolutionsUbuntu-Tech-Solutions

pdf-processing

Extract text, tables, and metadata from PDF documents.

Official
Intermediate