skill-progressive-disclosure-architecture-pattern
The WebGPU skill (github.com/dgreenheck/webgpu-claude-skill) demonstrates a layered documentation pattern: overview → cheatsheet → deep docs → examples. Current skills in the ecosystem load all content in a flat single file, causing context bloat for simple queries. Adopting the progressive disclosure pattern (load overview first, pull deep docs only when needed) can significantly reduce per-session context cost for skill-heavy workflows. This architectural pattern should be backported when refactoring any skill that exceeds ~400 lines.
Related
- progressive-disclosure-skill-architecture-from-webgpu
- progressive-disclosure-layered-skill-architecture-pattern
- progressive-disclosure-skill-architecture-pattern
- progressive-disclosure-docs-pattern-for-skills
- progressive-disclosure-skill-architecture-missing-from-curre
- skills-over-600-lines-split-via-progressive-disclosure