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 YuqingNicole/variant-design-skill --skill variant-componentgit clone --depth 1 https://github.com/YuqingNicole/variant-design-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/yuqingnicole/variant-design-skill/variant-component)<a href="https://agentmods.dev/skills/yuqingnicole/variant-design-skill/variant-component"><img src="https://agentmods.dev/badge/skills/yuqingnicole/variant-design-skill/variant-component/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/yuqingnicole/variant-design-skill/variant-component"><img src="https://agentmods.dev/badge/skills/yuqingnicole/variant-design-skill/variant-component.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Prompt Injection · line 49 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.01015 |
| Opus 5 | $0.00039 | $0.00508 |
| Sonnet 5 | $0.00016 | $0.00203 |
| Haiku 4.5 | $0.00008 | $0.00102 |
Grade A, and why
variant-component 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before generating code, load
skills/shared/code-output.mdfor framework detection and output conventions.
Component Mode
When the user asks for a component rather than a full page, switch to Component Mode. Generates isolated, self-contained UI pieces — not full layouts.
Triggers
| User says | Action |
|---|---|
| "design a button system" / "button variants" | Button component set: all sizes, all states |
| "design a form" / "input components" | Form component set: inputs, selects, errors, validation |
| "card component" / "design a card" | Card variants: default, hover, selected, loading, empty |
| "modal" / "dialog component" | Modal with header, body, footer, dismiss, focus trap |
| "design a [X] component" | Single component, all 8 interactive states |
| "component library" / "design system components" | Set of 5–8 related components as a unified system |
| "nav component" / "sidebar component" | Navigation piece with all states and responsive behavior |
Component Mode Workflow
Step 1: Clarify scope — single component or a system of related components?
Step 2: Define states — for every component, design all 8 states before coding:
default → hover → focus → active → disabled → loading → error → success
Step 3: Define variants — size scales, visual emphasis, semantic variants:
| Component | Common variants |
|---|---|
| Button | sizes (sm/md/lg) × types (primary/secondary/ghost/destructive) |
| Input | sizes × states × types (text/password/search/textarea) |
| Card | default / interactive (hover) / selected / loading (skeleton) / empty |
| Badge / Tag | semantic colors (info/success/warning/error) × sizes |
| Avatar | sizes × states (online/offline/loading) × fallback (initials/icon) |
| Modal | sizes (sm/md/lg/fullscreen) × dismissible/non-dismissible |
Step 4: Generate — produce a single HTML file (or TSX) showing all variants side by side on a neutral background, with clear labels. Component files go to variant-output/component-[name].html.
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 · 101 lines · 0 tokens per session scan A 98e53b05fdd5
variant-component is a skill published in the GitHub repository YuqingNicole/variant-design-skill (46 stars, last pushed 26d ago), licensed MIT. It adds 79 tokens to every session and 1,015 once invoked, about $0.0004 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
gacha-ui
Explore UI directions by generating several genuinely-different real-data HTML mockups in parallel, serving them so the user picks side-by-side, distilling each pick into locked constraints, and narrowing round by round until approved — then landing the winner in the real stack and refining. Use when the user wants to…
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.