How does this skill reduce token usage?

It identifies redundant prose, removes formatting noise, and converts verbose descriptions into structured formats like tables or lists, typically yielding a 20-40% reduction in net token count.

Is it safe to use on creative writing or legal documents?

It is not recommended for creative or legal text where specific phrasing and nuance are required. It is best used for technical documentation, notes, and knowledge bases.

Does it automatically create Mermaid diagrams?

The skill identifies specific sections that would benefit from visualization and suggests the appropriate diagram type (flowchart, architecture, etc.) in the YAML front-matter for you to implement.

Can I use the optimized files as reference material for other skills?

Yes, optimized markdown is specifically designed to be stored in 'references/' directories to provide Claude with high-density domain knowledge during specialized tasks.

Markdown Content Optimizer

Name: Markdown Content Optimizer
Author: mvdmakesthings

bymvdmakesthings

学習とドキュメンテーション

Optimizes and structures Markdown documentation to maximize information density and parsing efficiency for Large Language Models.

概要

The Markdown Optimizer skill transforms standard documentation into high-efficiency reference material specifically tuned for LLM ingestion. By automatically generating YAML metadata, normalizing heading structures, and identifying opportunities for visual Mermaid diagrams, it helps users reduce token overhead by 20-40% while significantly enhancing semantic clarity. This tool is essential for developers and technical writers who need to prepare large knowledge bases, research notes, or technical specs for use within LLM context windows or RAG systems.

主な機能

Heading hierarchy normalization for improved document parsing
Intelligent identification of sections suitable for Mermaid diagrams
0 GitHub stars
Noise reduction through removal of redundant lines and formatting
Token count estimation to track optimization efficiency
Automated YAML front-matter generation with key concepts and TOC

ユースケース

Compressing large documentation sets to fit within LLM context windows without losing meaning
Converting verbose research notes into structured, scannable reference guides for AI agents
Preparing technical documentation for use as RAG (Retrieval-Augmented Generation) source material

概要

主な機能

Heading hierarchy normalization for improved document parsing
Intelligent identification of sections suitable for Mermaid diagrams
0 GitHub stars
Noise reduction through removal of redundant lines and formatting
Token count estimation to track optimization efficiency
Automated YAML front-matter generation with key concepts and TOC

ユースケース

Compressing large documentation sets to fit within LLM context windows without losing meaning
Converting verbose research notes into structured, scannable reference guides for AI agents
Preparing technical documentation for use as RAG (Retrieval-Augmented Generation) source material