mineru-pdf

Parse documents via the MinerU API and convert results to Markdown.

1|Updated Apr 4, 2026

Search Tags:#ocr #markdown #document-processing #batch-processing #url-parsing #mineru-api

Ready to run

npx skills add https://github.com/WuYuStar/opencode-skills --skill mineru-pdf-wuyustar

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: mineru-pdf
Source: https://github.com/WuYuStar/opencode-skills/tree/main/mineru-pdf
Command: npx skills add https://github.com/WuYuStar/opencode-skills --skill mineru-pdf-wuyustar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables automated extraction of content from a wide range of documents (PDFs, Word, PowerPoint, images) using the MinerU API and converts it into Markdown, eliminating tedious manual transcription and formatting.

Core Features & Use Cases

Single-file URL parsing to fetch and process documents from the web
Local file upload parsing for on-device documents
Batch processing to handle multiple files concurrently
Smart API selection that chooses precise vs lightweight parsing based on file size/pages
Automatic result handling: polling, downloading, decompressing, and extracting Markdown
Output formats include Markdown, JSON, DOCX, HTML, and LaTeX

Quick Start

Upload a document or provide a URL and get a ready-to-use Markdown document generated in your output directory.

Frequently Asked Questions about mineru-pdf

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

FAQPage Schema

How do I convert PDF documents to Markdown automatically?▼

Batch processing of multiple PDF files is supported through concurrent task handling. The Skill automatically manages asynchronous operations, polling the MinerU API until all files are processed and extracted as Markdown documents.

Can I parse Word and PowerPoint files into Markdown using MinerU?▼

Yes, MinerU supports parsing a wide range of documents including Word and PowerPoint files into Markdown. It eliminates manual transcription by automatically extracting content and providing multi-format outputs like Markdown, JSON, DOCX, HTML, and LaTeX.

Does MinerU API support batch processing for document conversion?▼

Batch processing of multiple files is supported through concurrent task handling. The Skill automatically manages asynchronous operations, polling the MinerU API until all files are processed and extracted as Markdown documents.

What is the best way to handle large PDF files with MinerU parsing?▼

For large PDF files, the Skill uses smart API selection to automatically choose between precise and lightweight parsing modes based on file size and pages. This ensures reliable document processing without manual configuration.

Do I need to install dependencies to use MinerU for document parsing?▼

Yes, the Python requests library is required as a dependency. The Skill automatically enforces environment token checks and dependency verification before initiating MinerU API tasks to ensure robust operation and reliable error handling.