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-generategit 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-generate)<a href="https://agentmods.dev/skills/yuqingnicole/variant-design-skill/variant-generate"><img src="https://agentmods.dev/badge/skills/yuqingnicole/variant-design-skill/variant-generate/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-generate"><img src="https://agentmods.dev/badge/skills/yuqingnicole/variant-design-skill/variant-generate.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 Rogue Agent · line 10 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.05303 |
| Opus 5 | $0.00067 | $0.02652 |
| Sonnet 5 | $0.00027 | $0.01061 |
| Haiku 4.5 | $0.00013 | $0.00530 |
Grade A, and why
variant-generate 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.
How it starts
The opening of the file, as written. The whole thing — 402 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.
Core Workflow
0. Load Persisted Context (Every Session)
Before parsing the prompt, run the context check from "Project Context Initialization → Session Start". If a .variant-context.json exists, apply its values as soft constraints on all generation steps: palette selection, font choices, direction, and framework output format. The user can override any field by stating a preference explicitly.
1. Parse → Detect → Load
Check designSystem.confirmed in context first:
If designSystem.confirmed: true:
- Read
variant-output/design-system.css— load all token values - Print:
✦ DS locked: [palette] · [fonts] · variations differ in layout only - Skip palette/font selection — tokens are fixed
- Load scenario reference for layout and interaction patterns only
If no confirmed DS:
- Standard flow: identify scenario, load domain reference file + relevant design system references, pick 3 starter prompts and palettes
2. Generate 3 Distinct Variations
If DS confirmed: Each variation = a different structural arrangement. Visual language (colors, fonts, components) does not change between A, B, C. Variations differ in:
- Grid and layout pattern
- Information hierarchy (what leads, what's secondary)
- Density and spacing rhythm (using only DS spacing tokens)
- Which components are focal vs. supporting
If no DS confirmed: Each variation = a different studio's interpretation. Never two in the same direction.
Universal aesthetic directions:
| Direction | Feel | Signature |
|---|---|---|
| Minimal / Editorial | Type-driven, generous space | One strong font, minimal color |
| Bold / Expressive | High contrast, graphic | Dominant color block |
| Dark / Premium | Moody, atmospheric | Deep bg, elevated surfaces (not shadows) |
| Warm / Human | Rounded, approachable | Soft palette, organic forms |
| Data / Technical | Dense, systematic | Grid, monospace, tight |
| Neo-brutalist | Raw, unconventional | Bold outlines, broken grid |
| Luxury / Silence | Maximum negative space | One image, sparse text |
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 · 402 lines · 0 tokens per session scan A 04fb6671457f
variant-generate is a skill published in the GitHub repository YuqingNicole/variant-design-skill (46 stars, last pushed 27d ago), licensed MIT. It adds 133 tokens to every session and 5,303 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
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.
industrial-brutalist-ui
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.