multi-format-document-optimizer

Convert DOCX, PPTX, HTML, Markdown, and images into optimized PDFs.

5|4|Updated Nov 9, 2025
One-click install
npx skills add https://github.com/takusaotome/claude-skills-library --skill multi-format-document-optimizer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: multi-format-document-optimizer
Source: https://github.com/takusaotome/claude-skills-library/tree/main/skills/multi-format-document-optimizer
Command: npx skills add https://github.com/takusaotome/claude-skills-library --skill multi-format-document-optimizer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires docling, imagemagick, fpdf2, playwright, pymupdf, pyyaml, mistune, markdown2, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the problem of turning messy, multi-format documents into consistent, optimized PDFs without manual image handling or repeated tool juggling.

Core Features & Use Cases

  • Multi-format conversion: Automatically converts DOCX/PPTX/HTML/Markdown/images into optimized PDFs via a Markdown intermediate.
  • Image optimization inside PDFs: Extracts embedded PDF images, compresses/re-encodes them, and rebuilds the PDF for smaller file size and better target output.
  • Quality presets + batch support: Uses preset-driven pipelines (web/print/archive/minimal) and can process directories consistently.

Quick Start

Tell the AI to convert input files into web-optimized PDFs while compressing embedded images for faster online publishing.

Frequently Asked Questions about multi-format-document-optimizer

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

FAQPage Schema
How do I convert DOCX and PPTX files to optimized PDFs for web publishing?

You can convert DOCX and PPTX files into web-ready PDFs by chaining conversion and image optimization steps via a Markdown intermediate, applying quality presets to control DPI and image resizing bounds.

What's the best way to compress images embedded inside a PDF?

Extract embedded images from the source PDF, compress and re-encode them using ImageMagick based on quality presets, then rebuild the PDF for a smaller, publication-ready file.

Does this document optimization pipeline support batch processing for directories?

Yes, document optimization supports batch processing for directories, allowing you to apply consistent quality presets like web, print, or minimal across multiple files for uniform output.

Can I convert Markdown and HTML to PDF with configurable quality presets?

Yes, you can convert Markdown and HTML to PDF using quality presets like web, print, and archive that control image format, DPI, resizing bounds, and metadata stripping for consistent publication-ready output.

Do I need ImageMagick and docling installed to run document conversion tasks?

Yes, you need ImageMagick, docling, and markdown-to-pdf tooling installed to execute the conversion pipelines, handle image extraction, and perform the required image optimization steps.

What limitations exist when using OCR-enabled conversion for multi-format documents?

OCR-enabled conversion processes documents through docling and markdown intermediates, meaning complex formatting or non-text layouts in source PDFs may lose fidelity when re-encoded into the final optimized PDF.