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.
npx skills add Muminur/frontend-design-craft-skill --skill tastegit clone --depth 1 https://github.com/Muminur/frontend-design-craft-skillWrote 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.
[](https://agentmods.dev/skills/muminur/frontend-design-craft-skill/taste)<a href="https://agentmods.dev/skills/muminur/frontend-design-craft-skill/taste"><img src="https://agentmods.dev/badge/skills/muminur/frontend-design-craft-skill/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.
<a href="https://agentmods.dev/skills/muminur/frontend-design-craft-skill/taste"><img src="https://agentmods.dev/badge/skills/muminur/frontend-design-craft-skill/taste.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00102 | $0.02292 |
| Opus 5 | $0.00051 | $0.01146 |
| Sonnet 5 | $0.00020 | $0.00458 |
| Haiku 4.5 | $0.00010 | $0.00229 |
Grade A, and why
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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taste
Most AI-generated frontends look the same because the training data has a center of mass. Left alone, the model reaches for the same purple-blue gradient, the same Inter heading, the same three-column feature grid, the same glassmorphism card with a soft shadow. Taste is the layer that names those tells and refuses to produce them.
This is about deliberate aesthetic choices, not just absence of bad ones. A site without AI tells but with no opinion is still bland. The skill operates in two passes:
- Subtract — strip the generic patterns.
- Add — pick a specific archetype and commit to it.
The ban list (subtract first)
These patterns are recognizable as AI-generated on sight. They are banned by default — overridable only with an explicit reason.
Visual
- Purple → blue / pink → orange / teal → blue gradients. Especially as hero backgrounds, button fills, or text fills.
- Gradient text. Almost always reads as autogenerated. Exception: a logo or brand mark where the gradient is the brand.
- Glassmorphism / frosted glass cards. Especially with backdrop-filter blur and a 1px white border. Done to death.
- Neon glows on buttons or text. The "AI sci-fi" look.
- Bento-box layouts where every section is a rounded card with the same radius and shadow. Bento works when the cards have visual variety; the AI default has none.
- Soft drop shadows on every element. Shadow is a tool, not a default.
- Pure black backgrounds (
#000) for "premium" / "dark" sites. Useoklch(15% 0.01 250)or similar — a very dark tinted neutral.
Typography
Interas the default sans. Substitute with Geist, General Sans, Söhne, Cabinet Grotesk, IBM Plex, Hanken Grotesk, etc.- Heading sizes that are too large for the column they sit in. A 72px headline in an 800px-wide section needs to break across lines intentionally, or shrink.
- Sentence case for every label. Mix sentence case with all-caps tracking labels for emphasis.
- Centered paragraphs of body copy longer than two short lines.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 168 lines · 102 tokens per session scan A 7467ac5ffe81
taste is a skill published in the GitHub repository Muminur/frontend-design-craft-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 102 tokens to every session and 2,292 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.