What problem does it solve? Choosing a visual direction for a UI screen is slow when you can only imagine one option at a time. This Skill generates several distinct AI design mockups in parallel, opens them side-by-side in your browser, and captures structured feedback so you can pick and iterate on a direction quickly. ## Core Features & Use Cases - Parallel Variant Generation: Launch multiple design directions at once via subagents, each with its own brief, quality check, and retry logic. - Comparison Board with Feedback Loop: Serve an HTML board over HTTP where you pick favorites, request remixes, or ask for more variants like a chosen one. - Taste Memory: Reads prior approved designs to bias new generations toward your demonstrated aesthetic preferences. - Evolve Mode: Screenshot a running local site and generate improvement variants when you say "I don't like how this looks." - Use Case: You are building a settings page and unsure of the layout. Run the Skill, get 3 distinct visual directions in about 60 seconds, compare them in your browser, and iterate until one is approved. ## Quick Start Ask the AI to run /design-shotgun to explore design options for the screen you are working on.
