skills.rest
linxule
linxuleCOMMUNITY
Explore all skills by this author →
Website𝕏@LinXuleGitHub

document-conversion

Select MinerU or Markdownify to convert complex PDFs into markdown.

14|1|Updated Dec 8, 2025
Search Tags:#document processing#data extraction#academic papers#table extraction#pdf conversion#markdownify#mineru
One-click install
npx skills add https://github.com/linxule/interpretive-orchestration --skill document-conversion
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: document-conversion
Source: https://github.com/linxule/interpretive-orchestration/tree/main/skills/document-conversion
Command: npx skills add https://github.com/linxule/interpretive-orchestration --skill document-conversion

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires MinerU.

What problem does it solve?

This Skill eliminates the frustration of converting complex documents, especially PDFs with intricate layouts, tables, or figures, into analyzable markdown. It intelligently selects the best available conversion tool (MinerU or Markdownify) to ensure high accuracy and preserve formatting.

Core Features & Use Cases

  • Intelligent Tool Selection: Automatically chooses between MinerU (for complex PDFs with VLM mode) and Markdownify (for simpler documents or audio) based on document characteristics and API availability.
  • Robust PDF Parsing: Extracts text, tables, figures, and formulas from academic papers with high accuracy.
  • Multi-format Support: Handles various document types beyond PDFs, including DOCX, PPTX, XLSX, and images.
  • Use Case: You have a collection of academic papers, some with multi-column layouts and complex tables. This skill will process them, using MinerU for the challenging ones and Markdownify for the rest, delivering clean markdown for all.

Quick Start

Convert the academic paper at https://example.com/paper.pdf using MinerU's VLM mode, enabling formula and table recognition.

Frequently Asked Questions about document-conversion

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

FAQPage Schema
How do I convert complex PDFs with tables and figures to markdown?▼

PDF conversion to markdown works best with intelligent tool selection. This Skill automatically chooses between MinerU for complex layouts and Markdownify for simpler documents, preserving tables, figures, and text formatting while extracting structured content accurately.

When should I use MinerU versus Markdownify for document processing?▼

MinerU excels at academic papers and PDFs with multi-column layouts, complex tables, and formulas using VLM mode. Markdownify handles simpler documents and audio formats efficiently. This Skill selects the optimal method based on document complexity and API availability.

Can I batch process multiple academic papers with different layouts?▼

Yes. This Skill supports batch processing with page-range extraction, applying tool-selection logic across multiple documents. It handles varied complexity levels, OCR fallbacks, and output quality checks to ensure consistent markdown conversion.

What document formats can be converted beyond PDF?▼

Beyond PDFs, this Skill converts DOCX, PPTX, XLSX, and images to markdown. Multi-format support combined with intelligent tool routing ensures accurate extraction across document types while preserving layouts and data structure.

How does this handle PDFs when MinerU API isn't available?▼

The Skill implements tool-selection logic that automatically falls back to Markdownify when MinerU is unavailable. OCR fallbacks and quality checks ensure conversion continues reliably across different API availability scenarios.

What's the best way to extract text and data from research papers at scale?▼

Batch processing with intelligent tool selection handles research papers at scale. The Skill orchestrates MinerU and Markdownify outputs, supports selective page extraction, and applies OCR fallbacks to deliver clean, structured markdown from academic documents consistently.

Related Skills

Explore More Education & Research Skills→
linxulelinxule
14

interview-ingest

Transcribe audio interviews and convert PDFs into analyzable markdown.

Community
Intermediate
vecearvecear

doc-to-vector-dataset-generator

Convert documents into chunked JSONL datasets with metadata for embedding search.

Community
Advanced
Arry8Arry8
1

mineru

Convert PDFs, images, and web pages into Markdown, HTML, LaTeX, or DOCX.

Community
Advanced
changgengluchanggenglu

markdown-engineer

Extend Markdown parsing with custom TOC generation and sanitized rendering.

Community
Advanced