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 | $0.00000 | $0.02341 |
| Opus 5.5 | $0.00000 | $0.00936 |
| Sonnet 5.5 | $0.00000 | $0.00468 |
| Haiku 4.5 | $0.00000 | $0.00234 |
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 today.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
variant-generate: Generate three distinct design directions from a brief, each with a distinct product trade-off; locked brand tokens stay identical. Then refine them with variation actions, zone edits, undo and export. Triggers on: design options for X, show me variations, give me UI directions, vary this design, change the style, remix colors, shuffle layout, design a dashboard/landing page/app/editorial
Generate
Load map
Read files only at the step that names them, and only the section you need. Do not read ahead: the first generation needs the files in the first block, later turns load the second block on demand.
| When | Read |
|---|---|
| Existing project, before generating | references/workflow/project-discovery.md |
| The user points to a direction card | references/sources/direction-cards.md |
| Writing code | skills/shared/code-output.md |
| Vue, Astro or Svelte output | skills/shared/frameworks.md |
Recording .variant-context.json |
references/workflow/project-context.md |
| Building the comparison and previews | references/workflow/preview.md |
| Checking before presenting | references/workflow/quality-baseline.md |
| Money, privacy, permissions, deletion, health, safety or AI-derived conclusions | references/workflow/design-declaration.md, then references/workflow/product-integrity-gate.md |
| Later turn | Example | Read |
|---|---|---|
| Variation action | A vary strong, B remix colors, Mix A + B, Polish C, Critique B, tokens A, C → mobile |
skills/variant-generate/actions.md, then references/workflow/history.md |
| Zone edit | B vary subtle — hero, zones A |
skills/variant-generate/zones.md, then references/workflow/history.md |
| Undo, pick, recover | undo B, pick B |
references/workflow/history.md |
| Reopen or compare | open B, compare |
references/workflow/preview.md |
| Export or integrate (prepare target baseline before staging) | react B, export to next, integrate B, copy |
skills/shared/export.md |
| Context | show context, reset context |
references/workflow/project-context.md |
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.
- today Changed · -294 lines · -129 tokens per session aa0096ef9140
- today Changed · +2 lines e421e53a5c9f
- 17d ago Changed 33137ede4d86
- 22d ago Changed · +9 lines · +129 tokens per session 4ac52a6ceb63
- 1mo ago Changed · +4 lines b654b0ce2285
- 1mo 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 (47 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,341 tokens. 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.
openclaw-carapace
Build or modify OpenClaw application UI using canonical semantic tokens, themes, shared CSS foundations, consumer adapters, and established local primitives. Use for product interfaces, component styling, theme work, or design-token integration.
openclaw-design-system
Compatibility alias for existing OpenClaw installations that now applies Carapace semantic tokens, themes, shared CSS foundations, consumer adapters, and established local primitives.
openclaw-brand
Apply OpenClaw visual identity to logos, typography, imagery, voice, documents, presentations, social graphics, and launch materials. Use when the task changes brand identity rather than ordinary product UI or public-page composition.
openclaw-design-audit
Audit OpenClaw frontend code and rendered interfaces for Carapace drift, token misuse, primitive reimplementation, accessibility problems, responsive defects, and off-brand copy. Use for design reviews, compliance checks, or scheduled audit-and-fix workflows.