skill-chunk-md

What problem does it solve?

Long-form Markdown docs often become hard to navigate and retrieve specific information from, especially when chunk boundaries are unclear and frontmatter metadata is missing.

Core Features & Use Cases

• Semantic chunking of Markdown into self-contained chunks using <Chunk> tags to preserve meaning and enable precise retrieval.
• YAML frontmatter integration to store chunk metadata (ids, tags, context, and optional RAG fields) for LanceDB/LightRAG/HippoRAG pipelines.
• End-to-end workflow guidance for validating, exporting, and indexing chunks to support scalable RAG architectures.

Quick Start

Provide a Markdown document and the skill will return a CtxFST-formatted version with <Chunk> wrappers and frontmatter.