skills.rest
benbrastmckie
benbrastmckieCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

document-converter

Convert documents bidirectionally between Markdown, DOCX, and PDF formats.

444|464|Updated Jun 1, 2020
Search Tags:#automation#pdf#markdown#document conversion#text extraction#docx#file format
One-click install
npx skills add https://github.com/benbrastmckie/.config --skill document-converter
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: document-converter
Source: https://github.com/benbrastmckie/.config/tree/main/.claude/skills/document-converter
Command: npx skills add https://github.com/benbrastmckie/.config --skill document-converter

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandoc, python3, markitdown, pymupdf4llm, google-genai, pdf2docx, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill eliminates the tedious, manual process of converting documents between formats and extracting content, saving you significant time and effort. It handles complex conversions and content extraction from various document types, allowing you to automate workflows that would otherwise be repetitive and error-prone.

Core Features & Use Cases

  • Bidirectional Conversion: Seamlessly convert between Markdown, DOCX, and PDF formats.
  • Intelligent Content Extraction: Accurately pull text and structured data from PDFs and DOCX files, with enhanced quality for PDF-to-Markdown using optional Gemini API integration.
  • Automatic Tool Selection & Fallback: The skill intelligently detects and prioritizes available conversion tools (e.g., MarkItDown, Pandoc, PyMuPDF4LLM, Typst, XeLaTeX), ensuring the best possible output quality and reliability.
  • Batch Processing: Convert multiple files at once, processing entire directories concurrently to save hours of manual work.
  • Use Case: Imagine you have a folder of 50 PDF research papers. Use this Skill to automatically convert them all to Markdown, making their content easily searchable and analyzable for your literature review.

Quick Start

Convert the attached 'report.pdf' to Markdown. Then, convert 'notes.md' to a DOCX file.

Frequently Asked Questions about document-converter

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

FAQPage Schema
How do I convert PDF files to Markdown format?▼

PDF to Markdown conversion extracts text and structure from PDFs using tools like MarkItDown or PyMuPDF4LLM, with optional Gemini API integration for enhanced quality. The Skill automatically selects the best available tool and preserves document structure in the output.

Can I batch convert multiple documents at once?▼

Batch processing converts entire directories of documents concurrently, handling multiple files simultaneously. This processes large collections—like 50 research papers—in a single operation, saving hours of manual work across Markdown, DOCX, and PDF formats.

What file formats does this support for conversion?▼

Bidirectional conversion supports Markdown, DOCX, and PDF formats. The Skill handles content extraction and structural preservation across all three formats, with intelligent tool selection between Pandoc, MarkItDown, PyMuPDF4LLM, pdf2docx, Typst, and XeLaTeX.

Does it work offline or do I need an API?▼

The Skill operates in both offline and API modes. Offline conversions use Pandoc, MarkItDown, and pdf2docx; optional Gemini API integration enhances PDF-to-Markdown quality. Mode selection is automatic based on your configuration and available tools.

How does it handle complex document structures?▼

Automatic tool detection prioritizes conversion tools based on document complexity and format requirements. Fallback mechanisms ensure reliability; timeout and concurrency controls prevent bottlenecks. Error handling and fidelity validation maintain structure and media preservation across conversions.

Can I extract text and data from PDFs and DOCX files?▼

Intelligent content extraction pulls text and structured data from PDFs and DOCX files with accuracy. Enhanced extraction for PDFs uses optional Gemini API integration, enabling easy searchability and analysis of extracted content for workflows like literature reviews.

Related Skills

Explore More Content & Communication Skills→
mfmezgermfmezger
5

convert-to-markdown

Convert PDF, DOCX, PPTX, XLSX, HTML, EPUB, and images to Markdown.

Community
Intermediate
cafe3310cafe3310
248

markdown-new

Convert webpages, websites, search results, and documents into clean Markdown.

Community
Intermediate
leanderriefelleanderriefel

docx

Create and edit Word documents with formatting using docx-js and pandoc.

Community
Advanced
fabioc-alohafabioc-aloha
1

image-handling

Convert, optimize, and generate images using command-line tools and Replicate API.

Community
Advanced