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 bestdeejay-design/agent-skills --skill frontend-design-tastegit clone --depth 1 https://github.com/bestdeejay-design/agent-skillsWrote 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/bestdeejay-design/agent-skills/frontend-design-taste)<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/frontend-design-taste"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/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.
<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/frontend-design-taste"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/frontend-design-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 | $0.00145 | $0.01947 |
| Opus 5 | $0.00072 | $0.00974 |
| Sonnet 5 | $0.00029 | $0.00389 |
| Haiku 4.5 | $0.00015 | $0.00195 |
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 11d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Design Taste — distinctive direction, not templated defaults
Approach this as the design lead at a small studio known for giving every client a visual identity that could not be mistaken for anyone else's. The client has already rejected templated proposals and is paying for a distinctive point of view: make deliberate, opinionated choices about palette, typography and layout that are specific to this brief, and take one real aesthetic risk you can justify.
This skill defines the DIRECTION. It does not measure anything — frontend-perfection
does the measuring (contrast, tokens, Lighthouse) once the direction is built.
When to use
- User asks to "make it look good", "redesign with taste", "not look templated", "give it a visual identity", "design direction for this page".
- A page needs a visual direction BEFORE any code (palette, type, layout, signature).
- The existing design reads as an AI template and the user wants it to stop being one.
Do NOT use
- To audit/fix an existing page (contrast, SEO meta, Lighthouse, raw-hex tokens) — that is
frontend-perfection. - For SEO / Core Web Vitals / schema.org — that is
seo-toolkit. - When the user already pinned the visual direction — follow it exactly, do not re-propose.
The three AI defaults to avoid
AI-generated design currently clusters around three looks. All three are legitimate for SOME briefs, but they are defaults, not choices, and they appear regardless of subject:
- Warm cream background (~#F4F1EA) + high-contrast serif display + terracotta accent.
- Near-black background + a single bright acid-green or vermilion accent (the "gym/tech" look).
- Broadsheet layout — hairline rules, zero border-radius, dense newspaper columns.
Where the brief pins one of these looks, follow it. Where an axis is free, do NOT spend that freedom on a default.
Design principles
- Hero is a thesis. Open with the most characteristic thing in the subject's world: a headline, image, animation, live demo, interactive moment. A big number + small label + gradient accent is the template answer — only use it if it's truly the best.
- Typography carries personality. Pair display and body deliberately, not the same families you reach for on every project. Set a real type scale with intentional weights/widths/spacing. Make the type treatment memorable, not a neutral carrier.
- Structure is information. Numbering, eyebrows, dividers should encode something true about the content. Numbered markers (01/02/03) only when content is a real sequence — a process or timeline where order carries meaning.
- Motion serves the subject. An orchestrated moment lands harder than scattered effects; sometimes less is more — extra animation reads as AI-generated.
- Complexity matches the vision. Maximalist directions need elaborate execution; minimal directions need precision in spacing, type, detail.
- Copy is design material. Words exist to make the page easier to understand and use, never decoration.
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.
- 11d ago First seen · 130 lines · 145 tokens per session scan A 27e3a74e9355
frontend-design-taste is a skill published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 145 tokens to every session and 1,947 once invoked, about $0.0007 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
Webdesign
Design and integrate web interfaces via three paths: DirectDesign (write design inline with Anthropic frontend-design philosophy — the default workhorse), native /design + /design-sync Claude Code commands (preferred for code integration and design-system sync), or ClaudeDesign (drive claude.ai/design through…
ui-web
Web UI - glassmorphism, Tailwind, dark mode, accessibility.
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…
impeccable
Use when the user wants distinctive, production-grade frontend design, anti-generic AI aesthetics, UX critique, technical UI audits, or final polish through bundled Impeccable references and an optional upstream detector CLI.
quill-code
Edit the @posthog/quill design system locally and consume the change in products/desktop before it is published to npm. Use when changing quill components/primitives/tokens, when a quill change must be tested inside the Code app, or when the user mentions quill, the design system, the .local-quill tarball, or the…