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 R0STEFAN/webstudio-ai-agent --skill design-taste-frontendgit clone --depth 1 https://github.com/R0STEFAN/webstudio-ai-agentWrote 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/r0stefan/webstudio-ai-agent/design-taste-frontend)<a href="https://agentmods.dev/skills/r0stefan/webstudio-ai-agent/design-taste-frontend"><img src="https://agentmods.dev/badge/skills/r0stefan/webstudio-ai-agent/design-taste-frontend/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/r0stefan/webstudio-ai-agent/design-taste-frontend"><img src="https://agentmods.dev/badge/skills/r0stefan/webstudio-ai-agent/design-taste-frontend.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 | $0.00061 | $0.21912 |
| Opus 5 | $0.00030 | $0.10956 |
| Sonnet 5 | $0.00012 | $0.04382 |
| Haiku 4.5 | $0.00006 | $0.02191 |
Grade A, and why
design-taste-frontend 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 10d 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.
This is a copy
100% identical to design-taste-frontend — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1,207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tasteskill: Anti-Slop Frontend Skill
Landing pages, portfolios, and redesigns. Not dashboards, not data tables, not multi-step product UI. Every rule below is contextual. None of it fires automatically. First read the brief, then pull only what fits.
0. BRIEF INFERENCE (Read the Room Before Anything Else)
Before touching code or tweaking dials, infer what the user actually wants. Most LLM design output is bad because the model jumps to a default aesthetic instead of reading the room.
0.A Read these signals first
- Page kind - landing (SaaS / consumer / agency / event), portfolio (dev / designer / creative studio), redesign (preserve vs overhaul), editorial / blog.
- Vibe words the user used - "minimalist", "calm", "Linear-style", "Awwwards", "brutalist", "premium consumer", "Apple-y", "playful", "serious B2B", "editorial", "agency-y", "glassy", "dark tech".
- Reference signals - URLs they linked, screenshots they pasted, products they named, brands they're competing with.
- Audience - B2B procurement panel vs. design-conscious consumer vs. recruiter scanning a portfolio. The audience picks the aesthetic, not your taste.
- Brand assets that already exist - logo, color, type, photography. For redesigns, these are starting material, not optional input (see Section 11).
- Quiet constraints - accessibility-first audiences, public-sector, regulated industries, trust-first commerce, kids' products. These constraints OVERRIDE aesthetic preference.
0.B Output a one-line "Design Read" before generating
Before any code, state in one line: "Reading this as: <page kind> for <audience>, with a <vibe> language, leaning toward <design system or aesthetic family>."
Example reads:
- "Reading this as: B2B SaaS landing for technical buyers, with a Linear-style minimalist language, leaning toward Tailwind utilities + Geist + restrained motion."
- "Reading this as: solo designer portfolio for hiring managers, with an editorial / kinetic-type language, leaning toward native CSS + scroll-driven animation + custom typography."
- "Reading this as: redesign of a public-sector service site, with a trust-first language, leaning toward GOV.UK Frontend or USWDS."
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.
- 10d ago First seen · 1,207 lines · 61 tokens per session scan A aa194351b246
design-taste-frontend is a skill published in the GitHub repository R0STEFAN/webstudio-ai-agent (0 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 21,912 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to design-taste-frontend, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
frontend-ui-engineering
Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.
ui-designer
Elite UI/UX Design Lead & Frontend Architect. Generates distinctive, non-templated interfaces with opinionated aesthetics, deliberate typography, and exact UX copy. Triggers on UI design, frontend styling, or layout creation.
layout-audit
Audit the structure and spacing of a localhost page — spacing scale consistency, whether spacing groups related content, container width and line measure, optical alignment, grid versus flex misuse, magic z-index values and overflow. Use when the user mentions spacing, padding or margins, says a layout feels cramped…
motion-system
Audit and fix the animation on a running localhost page — durations, easing, which properties are animated, reduced-motion handling and missing exit transitions — then propose a named duration and easing token set. Use when the user mentions animation, transitions, motion, easing, timing, something feeling…
polish-pass
Run the last-10% polish checklist on a localhost page — focus rings, selection colour, scroll behaviour, tabular numbers, heading wrap balance, paragraph measure, skeletons, empty and error states, hover/active/disabled states, cursors, icon sizing and stroke, favicon and title, 404 and offline. Use when the user asks…
color-system
Audit and fix colour on a running localhost page — whether the accent is the framework default, hardcoded hex values instead of tokens, pure black and white, a flat neutral ramp, weak contrast on text and controls, and colour used as the only signal of state. Use when the user mentions colour, palette, theme, accent…