progressive-metadata

Pattern for creating skills with YAML frontmatter that enables progressive disclosure and token optimization. Use when building skills, optimizing context usage, or implementing domain expertise with minimal token overhead. Demonstrates how to structure SKILL.md files with metadata-driven loading that achieves 84% token reduction compared to manual instructions. Triggers on "create skill with metadata", "token optimization", "progressive disclosure", "skill frontmatter", "efficient skill design".

// tip: Run this command in your terminal to install the skill