Borrowing it
Nothing to install: this file belongs to WingedGuardian/GENesis-AGI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/WingedGuardian/GENesis-AGI/main/.claude/skills/taste/SKILL.mdgit clone --depth 1 https://github.com/WingedGuardian/GENesis-AGIWrote 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/wingedguardian/genesis-agi/taste)<a href="https://agentmods.dev/skills/wingedguardian/genesis-agi/taste"><img src="https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/taste/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/wingedguardian/genesis-agi/taste"><img src="https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/taste.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.01160 |
| Opus 5 | $0.00044 | $0.00580 |
| Sonnet 5 | $0.00018 | $0.00232 |
| Haiku 4.5 | $0.00009 | $0.00116 |
Grade A, and why
taste 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Rule
Set the three dials on purpose before you generate a single element.
AI-generated UI has a signature: every dial parked in the timid middle. Uniform cards on a uniform grid, one gratuitous fade on everything, medium whitespace everywhere, a purple-to-blue gradient, everything centered. It is not ugly — it is characterless. The fix is not "more polish". It is a deliberate choice on each dial, made before generation, matched to the product and its audience.
State the three values out loud (in a comment, a plan line, or your reasoning) before writing markup or styles. If you cannot say why each dial sits where it does, you are about to produce slop.
The Three Dials
1. Variance — sameness ↔ contrast
How much elements differ from one another in size, weight, shape, and rhythm.
- Low (calm, systematic): dashboards, data tables, settings, docs. The job is scanning and trust, so repetition and a strict grid help.
- High (expressive, hierarchical): landing pages, hero sections, pitch decks. One element must dominate; the rest recede. Deliberate asymmetry.
- Slop tell: every card the same size and weight, so nothing leads the eye. Fix by making the most important thing visibly bigger/bolder/first, and letting secondary things be genuinely smaller.
2. Motion — stillness ↔ animation
How much moves, and whether motion carries meaning.
- Low (still, fast): productivity tools, dense dashboards, anything used many times a day. Motion is friction here; prefer instant state changes.
- High (guided, narrative): onboarding, marketing, a single celebratory moment. Motion should explain (where a thing came from, what changed), not decorate.
- Slop tell: a blanket fade/slide on every element, or hover effects that do nothing. Every animation must answer "what does this help the user understand?" If nothing, cut it.
3. Density — airy ↔ packed
How much information and how little whitespace per screen.
- Low (airy, focused): landing pages, empty states, a single primary action. Whitespace is the message.
- High (packed, professional): trading/ops dashboards, tables, power-user tools where more-on-screen beats more-scrolling. Density is a feature for experts, not a failure.
- Slop tell: the same medium padding on everything regardless of context — a data table that wastes half the screen, or a landing hero crammed edge to edge. Match density to how the surface is actually used.
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 · 99 lines · 88 tokens per session scan A 883b56070436
taste is a skill published in the GitHub repository WingedGuardian/GENesis-AGI (96 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 1,160 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
anti-slop-frontend
Use when anti-slop frontend framework for AI agents. Enforces better layout, typography, motion, and spacing to counter generic AI-generated boilerplate UIs. Use when building frontend, countering generic AI UIs, need distinctive visual design, image-to-code pipeline.
ui-design
Comprehensive UI design skill covering fundamentals, patterns, and anti-patterns. Layout, typography, color, spacing, accessibility, motion, and component design. Use when building any web interface, reviewing design quality, or creating distinctive UIs.
absolute-ui
Build polished, intentional UIs with concrete CSS/Tailwind values — typography, color, layout, spacing, dark mode, accessibility, animations, components. Encodes specific, opinionated rules with exact values, not vague advice. Covers buttons, cards, forms, tables, navigation, dashboards, landing pages, onboarding, and…
emil-design-skills
Use when collection of 8 design engineering skills by Emil Kowalski (Vercel, Linear) — animation standards, UI craft, Apple design principles, library selection, and prototyping. Based on years of production experience. Use when the user asks about UI polish, animation decisions, or wants to audit/improve interface…
canvas-design
Design philosophy docs and canvas-based visual creation. Use when articulating design principles, crafting multi-page design documents, or exploring aesthetic philosophy with intentional design thinking.
motion-dev
Use when React animation library — spring physics, gesture animations, layout animations, scroll effects, SVG path drawing. Successor to Framer Motion. Use when building UI animations, micro-interactions, page transitions, shared element transitions, parallax effects.