What is frontend-design-taste?

A design guide for building frontends with a deliberate visual direction instead of common, repetitive interface patterns. It provides choices for visual variety, motion, density, performance, and mobile layouts.

Use it when creating landing pages, interface components, or design systems, or when deciding how an existing frontend should look.

Without clear design decisions, generated interfaces often converge on the same fonts, layouts, colors, and decorative effects. This guide helps set and enforce a distinct direction.

frontend-design-taste — Skill by Kevin-Liu-01/Agent-Machines

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Kevin-Liu-01/Agent-Machines --skill frontend-design-taste

Clone the repo

git clone --depth 1 https://github.com/Kevin-Liu-01/Agent-Machines

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/frontend-design-taste/github.svg)](https://agentmods.dev/skills/kevin-liu-01/agent-machines/frontend-design-taste)

Your own site

<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/frontend-design-taste"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/frontend-design-taste/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/frontend-design-taste"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/frontend-design-taste.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,143 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00079	$0.03143
Opus 5.5	$0.00032	$0.01257
Sonnet 5.5	$0.00016	$0.00629
Haiku 4.5	$0.00008	$0.00314

Measured 2mo ago against content hash 7388376defd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

frontend-design-taste scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

knowledge/skills/frontend-design-taste/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Design Taste — Anti-Slop Framework

Adapted from tasteskill.dev and Kevin's design wiki. For Sigil projects, also read .cursor/rules/taste-enforcement.mdc which enforces these rules at the Cursor level.

The Problem

LLMs default to the center of their training data: Inter font, generic card grids, blue accent, minimal animation, centered hero, blur blobs. The fix is not better prompting — it is providing a real design system with tokens, variance dials, explicit creative direction, and hard-banned patterns.

Variance Dials

Three numbers drive all downstream decisions. Defaults shown below — adapt dynamically based on user requests.

DESIGN_VARIANCE:  8  (1=Perfect Symmetry, 10=Artsy Chaos)
MOTION_INTENSITY: 6  (1=Static, 10=Cinematic)
VISUAL_DENSITY:   4  (1=Art Gallery, 10=Cockpit)

DESIGN_VARIANCE

1-3: Flexbox justify-center, strict 12-column symmetrical grids, equal paddings.
4-7: Overlapping margins (-mt-8), varied image aspect ratios, left-aligned headers over center-aligned data.
8-10: Masonry, CSS Grid with fractional units (2fr 1fr 1fr), massive empty zones (pl-[20vw]).
MOBILE OVERRIDE: Levels 4-10 MUST collapse to single-column (w-full px-4 py-8) below md:.

MOTION_INTENSITY

1-3: No automatic animations. CSS :hover and :active only.
4-7: Fluid CSS transitions with cubic-bezier(0.16, 1, 0.3, 1). Cascade animation-delay for load-ins. Only transform and opacity.
8-10: Scroll-triggered reveals, parallax, spring physics via Motion hooks. Never window.addEventListener('scroll').

VISUAL_DENSITY

1-3: Art gallery. Huge section gaps. Expensive and clean.
4-7: Standard web app spacing.
8-10: Cockpit. Tiny paddings. No card boxes; border-t / divide-y only. font-mono for all numbers.

Before Generating UI

Read ~/Documents/GitHub/kevin-wiki/wiki/design/design-system.md for current tokens
Read ~/Documents/GitHub/kevin-wiki/wiki/design/aesthetic-systems.md for archetypes
Choose an archetype (see below) before writing any component code
Lock the six style variables
If in a Sigil project: read .cursor/rules/taste-enforcement.mdc

Read the full file on GitHub · 283 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 283 lines · 79 tokens per session scan A 7388376defd9

Subscribe to this mod's changes

frontend-design-taste is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed 15d ago), licensed MIT. It adds 79 tokens to every session and 3,143 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

CSS and styling Claude Code Design and UX Frontend ai-agent cron hermes-agent mcp microvm model-context-protocol

frontend-design-taste next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
frontend-design-tasteKevin-Liu-01/Agent-Machines	Skill	29	15d ago	MIT	A	79	Claude Code, Codex
web-prototypenexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	59	Claude Code, Codex
velar-luxury-real-estatenexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	119	Claude Code, Codex
web-prototype-taste-brutalistnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	70	Claude Code, Codex
web-prototype-taste-softnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	69	Claude Code, Codex
mockup-device-3dnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	39	Claude Code, Codex
open-design-homepagenexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	65	Claude Code, Codex