Route generation of Figma-aware repository rules to Figma's current official MCP workflow without reproducing upstream instructions. Use when AGENTS.md, CLAUDE.md, or client rules must reflect verified Figma and codebase conventions.
Route Figma-to-code implementation to Figma's current official MCP workflow while preserving repository conventions and independent verification. Use when a supplied Figma selection must become production code.
Route a Figma library build to Figma's current official MCP workflow and this repository's portable design-system skills without reproducing upstream instructions. Use when creating tokens, components, documentation, and code mappings in Figma.
Route exact Figma Plugin API questions to current official typings and developer documentation without redistributing upstream reference material. Use when an implementation depends on verified node, variable, component, style, or editor API behavior.
Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this feel more alive". For fixing existing animations, use…
Flutter and Dart widget generation — transforms Mémoire component specs into Flutter widgets with Material 3, Riverpod state management, and responsive layouts.
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the…
Organize product content, objects, navigation, search, filters, labels, and hierarchy around user mental models and retrieval tasks. Use when people cannot find, understand, or predict where information and actions belong.
Design complete product workflows across states, inputs, feedback, permissions, interruptions, errors, undo, and recovery. Use when a feature needs behavioral structure beyond static screens; use visual craft skills only after the interaction model is coherent.
User interview and transcript analysis — parsing speaker-labeled transcripts, extracting pain points/goals/behaviors, sentiment analysis, and persona generation from qualitative data.
Design, implement, and verify App Intents, App Entities, App Shortcuts, widgets, Siri, Spotlight, and Apple Intelligence surfaces with stable identity and safe execution.
Scaffolds shadcn-based React compositions into src/app/sandbox/page.tsx from a spec (from screenshot-decoder) or a plain brief. Use AFTER screenshot-decoder, or directly when the user gives a text-only brief.