stitch-design-taste

Generate a semantic DESIGN.md capturing UI atmosphere, palette, typography, layout, and interaction intent.

Updated Apr 24, 2026
One-click install
npx skills add https://github.com/otto-poblysh/pedagemy-early-access --skill stitch-design-taste-otto-poblysh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: stitch-design-taste
Source: https://github.com/otto-poblysh/pedagemy-early-access/tree/main/.agents/skills/stitch-design-taste
Command: npx skills add https://github.com/otto-poblysh/pedagemy-early-access --skill stitch-design-taste-otto-poblysh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of generic, inconsistent UI design outputs by encoding a strict, reusable premium design language into a Stitch-readable DESIGN.md.

Core Features & Use Cases

  • Creates a semantic design contract for screen generation, translating taste rules into agent-friendly instructions.
  • Enforces visual standards with calibrated color roles, typography architecture, and explicit banned patterns.
  • Defines layout and motion intent so generated screens follow grid-first responsive structure and hardware-friendly interaction constraints.

Quick Start

Ask the agent to generate a new DESIGN.md for your product using the stitch-design-taste rules and your chosen vibe (density, variance, and motion intent).

Frequently Asked Questions about stitch-design-taste

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate consistent UI design rules for Google Stitch?

To generate consistent UI design rules for Google Stitch, this Skill produces a semantic DESIGN.md that encodes atmosphere, palette, typography, and layout intent into agent-friendly instructions. It enforces strict anti-generic constraints to standardize premium screen generation.

Why does my generated landing page UI look generic and inconsistent?

Generated UI looks generic when lacking a strict design contract. This Skill solves the problem by translating taste rules into a Stitch-readable DESIGN.md, banning generic fonts and colors while enforcing grid-first responsive layouts and spring microinteractions.

How do I enforce typography and color calibration rules in an automated UI generation workflow?

You enforce typography and color calibration by generating a DESIGN.md with explicit banned patterns, calibrated color roles, and typography architecture. This semantic contract ensures automated UI generation workflows adhere to premium, non-generic visual standards.

Can I use this to create design system rules for dashboards and feature-heavy product interfaces?

Yes, you can use this to create design system rules for dashboards and feature-heavy product interfaces. The generated DESIGN.md applies directly to screen generation workflows in Google Stitch, defining layout and motion intent for complex marketing and product UI.

What are the best constraints to prevent generic outputs in automated UI design?

The best constraints to prevent generic outputs include banned fonts and colors, grid-first responsive rules, spring-microinteraction philosophy, and explicit never-do anti-patterns. This Skill encodes these premium design language constraints directly into your generation instructions.