What problem does it solve? Maintaining a consistent visual identity across projects and coding agents is hard when design decisions live in scattered style guides. This Skill produces a single DESIGN.md file that combines machine-readable design tokens with human-readable rationale, then validates it for structural errors and WCAG contrast issues. ## Core Features & Use Cases - Authoring: Generate a complete DESIGN.md spec with colors, typography, spacing, rounded corners, and component tokens using token references like {colors.primary}. - Validation & Diffing: Run the @google/design.md CLI to lint structure, catch broken token references, detect WCAG AA/AAA contrast failures, and diff versions for regressions. - Exporting: Convert the spec to Tailwind theme JSON or W3C DTCG design tokens JSON for direct use in build pipelines. - Use Case: A team wants every AI coding agent to apply the same brand. You author a DESIGN.md with their palette and type scale, lint it to confirm contrast compliance, and export a tailwind.theme.json for their frontend repo. ## Quick Start Create a DESIGN.md design token spec for my brand with a blue accent color and Inter typography, then lint it for WCAG contrast issues.