design-taste-frontend

Installation
Summary

Concise, distinctive landing pages and portfolios that avoid templated AI aesthetics.

  • Reads the design brief first to infer the right aesthetic direction (SaaS minimalist, agency experimental, premium consumer, etc.) before touching code, preventing default AI patterns
  • Configures three core dials—design variance, motion intensity, and visual density—that drive layout, animation, and spacing decisions throughout the page
  • Enforces strict anti-patterns: bans em-dashes, generic serif fonts, beige+brass premium palettes, three-equal-feature-cards, and other LLM tells; audits every visible string for AI hallucination
  • Implements real design systems (Material, Carbon, Fluent, Polaris, Primer, GOV.UK) when applicable; otherwise builds with Tailwind, Motion, and GSAP for custom aesthetics
  • Requires a mandatory pre-flight checklist covering contrast, button wrapping, hero fit, color consistency, motion justification, and 50+ other production-readiness gates before shipping
SKILL.md

tasteskill v2

A page built by a model usually looks like the average of every page the model has seen: a centred headline over three lines, a little label above it, a row of icon cards, a soft gradient, a few thin rules and a monospace caption. Nothing in it is wrong and nothing in it was decided.

This skill replaces those defaults with decisions, in four ways:

  1. A script deals the directions, you choose among them. Asked to invent a look, a model picks the category default every time. scripts/draw.mjs deals three of twenty researched directions; you choose the one that carries the subject's idea, and the script then deals its type system, palette, hero and section compositions from a library distilled from 247 real sites.
  2. The idea comes from the subject. In the study, what separated the best sites from the forgettable ones was a concept taken from the thing itself, not the styling.
  3. A house style with no ornaments, measured in a real browser by scripts/inspect.mjs, so the rules are checked rather than hoped for.
  4. You look at what you made. Screenshots at three widths, a juror's rubric, fix, look again.
Related skills
Installs
721.3K
GitHub Stars
108.6K
First Seen
Feb 21, 2026