How much can I expect to reduce my token count?

While automated metadata adds a small amount of overhead, the structural optimizations and conversion of prose to structured data typically yield a net reduction of 20-40%.

Is this skill suitable for creative writing?

It is not recommended for creative writing or legal documents, as it focuses on technical clarity and data density which may strip the intentional style or nuance required in those fields.

How does the Mermaid diagram integration work?

The optimizer flags specific sections with complex relationships or flows in the front-matter, suggesting them as candidates for visualization to help LLMs parse logic more effectively.

Does this tool change the core meaning of my documents?

No, the optimizer is designed to preserve all semantic information while improving the structure and removing redundant formatting noise.

Markdown Optimizer

Name: Markdown Optimizer
Author: mvdmakesthings

bymvdmakesthings

学習とドキュメンテーション

Optimizes markdown documents to maximize information density and parsing efficiency for Large Language Models.

概要

Markdown Optimizer is a specialized tool designed to prepare technical documentation, notes, and research for ingestion by AI models. It enhances documents by adding rich YAML front-matter, normalizing heading hierarchies, and stripping redundant noise to ensure high information density. By identifying opportunities for Mermaid diagrams and converting verbose prose into structured formats like tables or lists, this skill helps reduce token overhead while significantly improving the clarity and scannability of context provided to Claude and other LLMs.

主な機能

Smart identification of sections suitable for Mermaid diagram visualization.
Automated YAML front-matter generation with token estimates and key concepts.
0 GitHub stars
Relationship mapping via metadata to connect related documents in a knowledge base.
Intelligent heading normalization to ensure consistent document hierarchy.
Noise reduction and redundancy removal to improve token-to-information ratio.

ユースケース

Standardizing metadata and structure across large technical documentation repositories.
Preparing internal technical documentation for use as a RAG (Retrieval-Augmented Generation) knowledge base.
Condensing verbose research notes into token-efficient context for Claude prompts.

概要

主な機能

Smart identification of sections suitable for Mermaid diagram visualization.
Automated YAML front-matter generation with token estimates and key concepts.
0 GitHub stars
Relationship mapping via metadata to connect related documents in a knowledge base.
Intelligent heading normalization to ensure consistent document hierarchy.
Noise reduction and redundancy removal to improve token-to-information ratio.

ユースケース

Standardizing metadata and structure across large technical documentation repositories.
Preparing internal technical documentation for use as a RAG (Retrieval-Augmented Generation) knowledge base.
Condensing verbose research notes into token-efficient context for Claude prompts.