mineru-pdf-converter

Convert PDF files to Markdown with images, tables, and formulas.

52|11|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/InternScience/ChemClaw --skill mineru-pdf-converter-internscience
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mineru-pdf-converter
Source: https://github.com/InternScience/ChemClaw/tree/main/skills/mineru-pdf-converter
Command: npx skills add https://github.com/InternScience/ChemClaw --skill mineru-pdf-converter-internscience

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, urllib3, pymupdf, and includes scripts (resource) components.

What problem does it solve?

Converts PDFs to Markdown while preserving text, images, tables, and formulas, and handles very large files by automatic batching.

Core Features & Use Cases

  • Automatic splitting large PDFs into batches of up to 600 pages
  • Full output set includes full.md, images/, layout.json, and *_origin.pdf
  • Batch processing: convert multiple PDFs in one run or per-file
  • Python API support: can be driven programmatically via the included script

Quick Start

Provide a PDF file path and run the MinerU PDF converter to produce a complete Markdown package with images and metadata.

Frequently Asked Questions about mineru-pdf-converter

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

FAQPage Schema
How do I convert a PDF to Markdown while preserving images and tables?

To convert a PDF to Markdown while preserving images and tables, this Skill outputs a full.md file alongside an images directory and layout metadata. It handles structured documents like academic papers and reports.

What is the best way to batch process large PDF files for Markdown conversion?

For batch processing large PDF files for Markdown conversion, this Skill automatically splits documents into batches of up to 600 pages. This ensures very large files are handled efficiently without manual intervention.

Do I need an API token to convert PDFs to Markdown?

Yes, you need a MinerU API token to convert PDFs to Markdown using this Skill. The script relies on the MinerU service to perform the actual conversion and requires this token for authentication.

Can I use Python to automate PDF to Markdown conversion?

Yes, you can use Python to automate PDF to Markdown conversion because this Skill provides Python API support. You can drive the included script programmatically to convert multiple PDFs in one run or per-file.

What output files are generated when converting a PDF to Markdown?

When converting a PDF to Markdown, the full output set includes full.md, an images directory, layout.json, and copies of the origin PDF. This preserves the document layout, formulas, and metadata.