feature-discovery

Dynamically load relevant feature documentation by parsing YAML frontmatter to index metadata, then lazily loading only the matched docs in response to user queries. This query-driven approach avoids loading unnecessary content.

Lazy frontmatter discovery is the process of extracting and indexing feature metadata from YAML frontmatter in docs without loading the full content. It matches user queries against feature names, descriptions, and components to load only relevant docs.

Yes, you can surface feature context without loading all docs by using query-driven matching. The system parses frontmatter to index features and lazily loads only the documentation matched by name, description, or components.

Match user questions to feature names and components by indexing YAML frontmatter metadata. The system enforces frontmatter-based naming and query matching to surface the most relevant feature documentation on demand.

The best way to provide contextual learning is to lazily load targeted feature docs parsed from YAML frontmatter. This supplies only the relevant context to AI sessions, accelerating feature understanding and decision making.