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 anton-abyzov/vskill --skill frontend-designgit clone --depth 1 https://github.com/anton-abyzov/vskillWrote 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/anton-abyzov/vskill/frontend-design)<a href="https://agentmods.dev/skills/anton-abyzov/vskill/frontend-design"><img src="https://agentmods.dev/badge/skills/anton-abyzov/vskill/frontend-design/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/anton-abyzov/vskill/frontend-design"><img src="https://agentmods.dev/badge/skills/anton-abyzov/vskill/frontend-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 106 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00133 | $0.02160 |
| Opus 5 | $0.00067 | $0.01080 |
| Sonnet 5 | $0.00027 | $0.00432 |
| Haiku 4.5 | $0.00013 | $0.00216 |
Grade A, and why
frontend-design 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Design with Visual Verification
Build distinctive, production-grade frontend interfaces — then verify they actually look right in a real browser. This skill closes the gap between "generate code" and "ship something beautiful" by combining bold design thinking with a browser-based verification loop.
Why Visual Verification Matters
Writing frontend code without seeing the result is like painting blindfolded. Generic AI-generated UIs happen because the model never sees what it produced — it can't catch misaligned layouts, clashing colors, or broken animations. This skill ensures you always close the loop: generate code, open it in a browser, see what it looks like, and iterate until it's genuinely good.
Phase 1: Design Thinking
Before writing any code, commit to a clear aesthetic direction. The goal is intentionality — bold maximalism and refined minimalism both work when executed with precision.
Aesthetic Direction
Pick a strong conceptual direction and execute it consistently:
- Purpose: What problem does this interface solve? Who uses it?
- Tone: Choose something specific — brutally minimal, retro-futuristic, luxury editorial, organic/natural, playful, industrial, art deco, soft/pastel. Vague directions produce vague results.
- Differentiation: What makes this memorable? Identify one signature element someone will remember.
Typography
Font choice is the single biggest design signal. Generic fonts (Inter, Roboto, Arial, system defaults) immediately signal "AI-generated."
- Pair a distinctive display font with a refined body font
- Use a clear typographic scale (e.g., Golden Ratio: 1.618 multiplier between sizes)
- Load fonts from Google Fonts or bundle them — never rely on system fonts for character
- Vary choices across projects — converging on the same "safe" picks (Space Grotesk, Poppins) defeats the purpose
Color & Theme
- Commit to a cohesive palette using CSS variables for consistency
- A dominant color with sharp accents outperforms timid, evenly-distributed palettes
- Dark mode: deep, rich backgrounds (not pure black) with vibrant accents that pop
- Light mode: warm off-whites (not sterile #fff) with deeper accent variants
- Never default to purple gradients on white — the most recognizable AI-slop pattern
What ships with it
27 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.
- evals/.gitignore 18 B
- evals/activation-prompts.json 4.2 KB
- evals/benchmark.json 511 B
- evals/evals.json 9.3 KB
- evals/history/2026-04-24T22-59-36.742Z.json 5.6 KB
- evals/history/2026-04-24T22-59-39.006Z.json 4.2 KB
- evals/history/2026-04-24T22-59-57.262Z.json 3.5 KB
- evals/history/2026-04-24T23-00-42.297Z.json 4.3 KB
- evals/history/2026-04-24T23-02-29.235Z.json 5.4 KB
- evals/history/2026-04-24T23-03-58.540Z.json 511 B
- frontend-design-workspace/iteration-1/benchmark.json 1.9 KB
- frontend-design-workspace/iteration-1/eval-1-landing-page/eval_metadata.json 1.6 KB
- frontend-design-workspace/iteration-1/eval-1-landing-page/with_skill/grading.json 3.6 KB
- frontend-design-workspace/iteration-1/eval-1-landing-page/with_skill/output.md 37 KB
- frontend-design-workspace/iteration-1/eval-1-landing-page/without_skill/grading.json 3.8 KB
- frontend-design-workspace/iteration-1/eval-1-landing-page/without_skill/output.md 33 KB
- frontend-design-workspace/iteration-1/eval-4-no-browser/eval_metadata.json 1.2 KB
- frontend-design-workspace/iteration-1/eval-4-no-browser/with_skill/grading.json 2.5 KB
- frontend-design-workspace/iteration-1/eval-4-no-browser/with_skill/output.md 18 KB
- frontend-design-workspace/iteration-1/eval-4-no-browser/without_skill/grading.json 2.5 KB
- frontend-design-workspace/iteration-1/eval-4-no-browser/without_skill/output.md 18 KB
- frontend-design-workspace/iteration-1/eval-6-console-errors/eval_metadata.json 1.0 KB
- frontend-design-workspace/iteration-1/eval-6-console-errors/with_skill/grading.json 1.9 KB
- frontend-design-workspace/iteration-1/eval-6-console-errors/with_skill/output.md 7.4 KB
- frontend-design-workspace/iteration-1/eval-6-console-errors/without_skill/grading.json 2.0 KB
- frontend-design-workspace/iteration-1/eval-6-console-errors/without_skill/output.md 5.0 KB
- references/browser-verification-setup.md 5.2 KB
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 · 183 lines · 133 tokens per session scan A 38040d01bc21
frontend-design is a skill published in the GitHub repository anton-abyzov/vskill (45 stars, last pushed 2d ago), licensed MIT. It adds 133 tokens to every session and 2,160 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 2026-08-30.
Other skills, from other repositories
skillshare-ui-website-style
Skillshare frontend design system for the React dashboard (ui/) and Docusaurus website (website/). Use this skill whenever you: build or modify a dashboard page or component in ui/src/, style or layout website pages or custom CSS in website/, create new React components for the dashboard, add pages to the dashboard…
tailwind-design-system
Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
frontend-blueprint
AI frontend specialist and design consultant that guides users through a structured discovery process before generating any code. Collects visual references, design tokens, typography, icons, layout preferences, and brand guidelines to ensure the final output matches the user's vision with high fidelity. Use when the…
figma-implement-design
Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and project-convention translation). Use when the user provides Figma URLs or node IDs and asks to implement designs or components that must match Figma specs. Requires a working…
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications. Generates creative, polished code that avoids generic AI aesthetics. Do NOT use for design review or audit (use web-design-guidelines…