wiki-llms-txt
Generates llms.txt and llms-full.txt files for LLM-friendly project documentation following the llms.txt specification. Use when the user wants to create LLM-readable summaries, llms.txt files, or make their wiki accessible to language models.
sniffable-python
Structure Python so LLMs can understand it in 50 lines.
toon
Token-Oriented Object Notation (TOON) format for LLM-optimized data encoding. Converts JSON to compact, human-readable format that minimizes tokens (~40% reduction) while improving LLM comprehension accuracy.
llm-doc-gen
LLM-powered documentation generation for narrative architecture docs, tutorials, and developer guides. Uses AI consultation to create contextual, human-readable documentation from code analysis and spec data.
youtube-korean-transcript
Extracts one readable markdown transcript from a YouTube URL or video ID using yt-dlp with Korean-first subtitle selection, then routes non-Korean output through an LLM translation workflow. Use when users ask to extract, structure, timestamp, or translate YouTube transcripts (especially into Korean).