Does it preserve tables and images?

Yes, the tool is optimized for table preservation (using MarkItDown for pipe-style markdown) and automatically handles image extraction and directory organization.

Can I convert multiple files at once?

Yes, the skill supports batch processing and can handle parallel conversions (defaulting to 4 concurrent tasks) to speed up large-scale document transformations.

Does this skill require an internet connection?

While it can use the Gemini API for enhanced quality, it features a robust 'Offline Mode' that uses local tools like Pandoc and Python libraries for all conversions.

How does this skill handle complex PDF layouts?

The skill uses a priority matrix that prefers the Gemini API for vision-based layout understanding, which offers 95%+ fidelity. It falls back to local tools like PyMuPDF4LLM or MarkItDown if an API key is not provided.

Which document formats are supported for generation?

You can generate professional DOCX files via Pandoc and high-quality PDF files using either the Typst or XeLaTeX engines through Markdown source files.

Document Converter

Name: Document Converter
Author: benbrastmckie

bybenbrastmckie

•

426

内容管理

Converts documents bidirectionally between Markdown, DOCX, and PDF formats with high-fidelity text extraction and layout preservation.

关于

The Document Converter skill provides a robust orchestration layer for transforming files across Markdown, DOCX, and PDF formats using industry-standard tools like Pandoc, MarkItDown, and the Gemini API. It intelligently selects the best conversion engine based on document complexity and available environment configurations, ensuring maximum fidelity for tables, layouts, and images. Whether you are extracting structured content from legacy PDFs for LLM analysis or generating professional reports from Markdown source files, this skill automates the process with built-in fallback mechanisms, batch processing capabilities, and progress monitoring.

主要功能

Intelligent tool priority matrix featuring Pandoc, MarkItDown, and PyMuPDF4LLM
Automatic image extraction and embedding for document-to-markdown workflows
Batch processing support with parallel execution and progress streaming
High-fidelity PDF text extraction using Gemini API vision-based understanding
Bidirectional conversion between Markdown, DOCX, and PDF formats
426 GitHub stars

使用场景

Extracting clean Markdown content from complex PDF or Word reports for AI analysis
Generating professional DOCX or PDF documents from Markdown documentation source files
Automating the conversion of legacy document archives into structured, web-ready formats

关于

主要功能

Intelligent tool priority matrix featuring Pandoc, MarkItDown, and PyMuPDF4LLM
Automatic image extraction and embedding for document-to-markdown workflows
Batch processing support with parallel execution and progress streaming
High-fidelity PDF text extraction using Gemini API vision-based understanding
Bidirectional conversion between Markdown, DOCX, and PDF formats
426 GitHub stars

使用场景

Extracting clean Markdown content from complex PDF or Word reports for AI analysis
Generating professional DOCX or PDF documents from Markdown documentation source files
Automating the conversion of legacy document archives into structured, web-ready formats