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-uxgit 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-ux)<a href="https://agentmods.dev/skills/yuqingnicole/variant-design-skill/variant-ux"><img src="https://agentmods.dev/badge/skills/yuqingnicole/variant-design-skill/variant-ux/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-ux"><img src="https://agentmods.dev/badge/skills/yuqingnicole/variant-design-skill/variant-ux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Excessive Agency · line 74 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 173 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00092 | $0.03923 |
| Opus 5 | $0.00046 | $0.01962 |
| Sonnet 5 | $0.00018 | $0.00785 |
| Haiku 4.5 | $0.00009 | $0.00392 |
Grade A, and why
variant-ux 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 13d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Review Mode
When the user wants to evaluate usability rather than generate visuals, switch to UX Review mode. Load references/ux-heuristics.md and references/ux-psychology.md. Load additional references as the review scope demands (see "When to Load Which Reference" below).
Triggers
| User says | Action | Load |
|---|---|---|
| "ux review" / "heuristic review" / "usability audit" | Full heuristic evaluation against Nielsen's 10 | ux-heuristics.md + ux-psychology.md |
| "review this design" / "what's wrong with this UI" | Heuristic scan → findings list with severity | ux-heuristics.md |
| "check usability" / "is this good UX" | Walk through flow, flag violations | ux-heuristics.md + ux-psychology.md |
| "cognitive load" / "too complex?" | Cognitive load analysis → reduction suggestions | ux-psychology.md |
| "why do users get confused here" | Mental model analysis → mismatch diagnosis | ux-psychology.md |
| "affordances" / "does this look clickable" | Affordance/signifier audit | ux-psychology.md |
| "dark patterns" / "is this ethical" | Dark pattern scan | ux-psychology.md |
| "navigation" / "can't find" / "information architecture" / "IA" | IA audit — labels, hierarchy, findability | ux-information-architecture.md |
| "site structure" / "how to organize" / "card sort" / "tree test" | IA design or validation | ux-information-architecture.md |
| "accessibility" / "a11y" / "screen reader" / "keyboard navigation" | Accessibility audit against WCAG 2.1 AA | ux-accessibility.md |
| "WCAG" / "alt text" / "aria" / "focus" | Specific accessibility check | ux-accessibility.md |
| "user testing" / "how to test this" / "usability test" | Research method recommendation + test plan | ux-research-methods.md |
| "what do users think" / "how do I get feedback" | Research method selection | ux-research-methods.md |
| "NPS" / "SUS" / "survey" / "interview users" | Measurement framework or interview guidance | ux-research-methods.md |
| "transition feels wrong" / "animation timing" / "state choreography" / "loading feels laggy" | Component transition audit | ux-interaction-transitions.md |
| "touch target" / "thumb zone" / "mobile gesture" / "iOS vs Android" | Mobile interaction audit | ux-mobile-patterns.md |
| "onboarding" / "empty state" / "first use" / "aha moment" / "activation" | Onboarding flow review | ux-onboarding.md |
| "chart" / "dashboard" / "data viz" / "KPI card" / "which chart" | Data visualization audit or recommendation | ux-data-visualization.md |
| "content model" / "taxonomy" / "multilingual" / "RTL" / "localization" | Content structure review | ux-content-strategy.md |
| "design tokens" / "token naming" / "theming" / "dark mode architecture" | Token architecture review | ux-design-tokens.md |
| "component spec" / "button states" / "modal behavior" / "ARIA" | Component spec review | ux-component-specs.md |
| "design critique" / "feedback on design" / "design review meeting" | Critique framework guidance | ux-design-critique.md |
| "conversion" / "landing page" / "trust signals" / "CTA copy" / "pricing page" | Conversion UX audit | ux-conversion-patterns.md |
| "error message" / "error state" / "form error" / "validation" / "recovery path" / "prevent errors" | Error design audit — classification, messaging, prevention | ux-error-design.md |
| "empty state" / "no data" / "blank state" / "nothing here" / "zero state" | Empty state design — all 4 types | ux-empty-states.md |
| "notification" / "toast" / "banner" / "badge" / "push notification" / "alert priority" | Notification system design and priority rules | ux-notifications.md |
| "table" / "data table" / "sorting" / "filtering" / "pagination" / "bulk select" / "row actions" | Table and list interaction design | ux-tables-lists.md |
| "search" / "autocomplete" / "search results" / "search bar" / "faceted search" / "command palette" | Search pattern design — input, suggestions, results | ux-search-patterns.md |
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.
- 13d ago First seen · 239 lines · 0 tokens per session scan A 9c1c2d4314fd
variant-ux is a skill published in the GitHub repository YuqingNicole/variant-design-skill (46 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 3,923 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 2026-08-30.
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…
stitch-design
Automate high-fidelity UI prototyping with Google Stitch MCP. Use when the user needs to generate, iterate, or refine UI screens via Stitch prompts.
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.
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
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…
imagegen-frontend-mobile
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured…