Lightweight Skill Metadata Specification With Minimal Required Fields

via “skill metadata extraction and tagging”

Digital brain as skills for AI coding CLIs — no vector DB, no embeddings, no infrastructure

Unique: Extracts metadata from markdown structure (YAML frontmatter, code fence language tags, heading levels) rather than requiring a separate metadata file, keeping skills self-contained and editable in any text editor

vs others: More portable than database-based metadata (Notion, Obsidian) because metadata lives in the markdown file itself and is version-controllable