taste▌

This skill generates DESIGN.md files optimized for Google Stitch screen generation. It translates the battle-tested anti-slop frontend engineering directives into Stitch's native semantic design language — descriptive, natural-language rules paired with precise values that Stitch's AI agent can interpret to produce premium, non-generic interfaces.

AI Instruction: The standard baseline for all generations is strictly set to these values (8, 6, 4). Do not ask the user to edit this file. Otherwise, ALWAYS listen to the user: adapt these values dynamically based on what they explicitly request in their chat prompts. Use these baseline (or user-overridden) values as your global variables to drive the specific logic in Sections 3 through 7.

This skill encodes the design philosophy behind Family — a product widely praised for feeling alive, welcoming, and intentional. Originally documented by Benji Taylor at benji.org/family-values.

Develop product taste and intuition using frameworks from 10 product leaders. \n \n Grounded in core principles: intuition as hypothesis generation, taste as a learnable skill built through exposure hours, and deliberate self-observation of your own product reactions \n Guides users to identify gaps in their judgment, suggest targeted practice activities, and know when to trust gut instinct versus data \n Includes diagnostic questions to surface what products users analyze regularly, how they no

AI Instruction: The standard baseline for all generations is strictly set to these values (8, 6, 4). Do not ask the user to edit this file. Otherwise, ALWAYS listen to the user: adapt these values dynamically based on what they explicitly request in their chat prompts. Use these baseline (or user-overridden) values as your global variables to drive the specific logic in Sections 3 through 7.