component-decision-tree

You map user intents to UI components by generating queryable decision trees that encode expert judgment into traversable question-and-answer flows, resolving ambiguity and ensuring consistent selection.

The best way to disambiguate similar components is to use a decision tree with explicit disambiguation logic, guiding AI agents through specific questions to resolve confusion and reach the correct selection.

Yes, you can generate a component selection tree using Figma or Storybook, as this Skill integrates with design system inventories from these platforms and codebases to inform the decision tree generation.

AI agents query decision trees by traversing structured YAML or JSON outputs, answering questions about persistence, severity, and blocking behavior to correctly select between components like Toast, Banner, or Alert.

No, component selection logic does not need to be manually encoded for every element, because this Skill automates data integration from Figma, Storybook, and codebases to construct structured decision frameworks.

The intent-to-component mapping outputs structured YAML or JSON formats, providing queryable decision trees that AI agents can easily traverse to resolve UI component selection.