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 rshzrh/ui-design-skills --skill ui-webgit clone --depth 1 https://github.com/rshzrh/ui-design-skillsWrote 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/rshzrh/ui-design-skills/ui-web)<a href="https://agentmods.dev/skills/rshzrh/ui-design-skills/ui-web"><img src="https://agentmods.dev/badge/skills/rshzrh/ui-design-skills/ui-web/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/rshzrh/ui-design-skills/ui-web"><img src="https://agentmods.dev/badge/skills/rshzrh/ui-design-skills/ui-web.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00099 | $0.01809 |
| Opus 5.5 | $0.00040 | $0.00724 |
| Sonnet 5.5 | $0.00020 | $0.00362 |
| Haiku 4.5 | $0.00010 | $0.00181 |
Grade A, and why
ui-web 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 1mo 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.
ui-web — Slop-Free Web UI Skill
You are generating production-grade web UI in React + TypeScript + Tailwind. This skill exists because untouched LLMs produce AI slop: purple→blue gradients, Inter everywhere, 3-icon-card grids, "Lightning fast / Powered by AI" copy, glassmorphism by default, arbitrary spacing values, and the median of every Tailwind tutorial scraped from GitHub. This skill replaces guesses with constraints.
The non-negotiable rule: NEVER use a buzzword in place of a token. Words like clean, modern, professional, sleek, premium are banned from your reasoning. Every aesthetic choice must trace back to a named anchor recipe in anchors.md and a token in the project's tailwind.config.ts.
Workflow (follow in order)
Step 0 — Project scan (decides bootstrap vs extend mode)
Before any other action, check for:
DESIGN_RULES.md # at repo root → if exists, you are in EXTEND mode
tailwind.config.{ts,js} # → if exists with custom theme, you are in EXTEND mode
app/globals.css # check for CSS custom properties / tokens
src/styles/tokens.css
- If
DESIGN_RULES.mdexists: read it. Read the existingtailwind.config.*. Skip to Step 3 (Phase 2: UI). Use only existing tokens. NEVER add new colors/spacing/radii without asking. - If tokens exist but no
DESIGN_RULES.md: read tokens, infer the closest matching anchor, ask the user to confirm the inferred anchor, then writeDESIGN_RULES.mdand proceed to Phase 2. - If neither exists: you are in bootstrap mode. Continue to Step 1.
Step 1 — Intake (interactive, bootstrap only)
Use AskUserQuestion to gather, in this order:
- Anchor pick — show the 8 recipes from
anchors.md(one-line summary each). Let the user pick 1–3. If 2–3, ask which is primary and which contributes type vs color vs motion. - Ban menu — show the 8 ban patterns from
ban-patterns.mdwith the 3 default-on items pre-checked. Confirm. - Project context:
- Content density: airy / balanced / dense
- Primary surface: marketing site / app / docs / dashboard / mobile-web
- Dark mode: required / optional / none
- Brand color (if any): hex value or "derive from anchor"
What ships with it
10 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.
- 1mo ago First seen · 101 lines · 99 tokens per session scan A cb4bb3d45192
ui-web is a skill published in the GitHub repository rshzrh/ui-design-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 99 tokens to every session and 1,809 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
atelier-components
Atelier suite — turn the design system into real, accessible, production code. Scaffold a premium React/Next + Tailwind v4 + shadcn/ui project, wire the atelier-foundations tokens into shadcn's theme variables, install the best-in-class single-purpose components (Vaul drawer, Sonner toast, cmdk command palette, Tremor…
tamagui-v6-config
Tamagui v6 theme system: the light/dark/accent/brand/inverse/level/active theme family, the background-active one-off key, and recipe-tree authoring with createV6Config. Use when choosing a theme for a surface, building a selected/emphasis state, or authoring a custom v6 colors pack.
tamagui-theme-generator
Generate custom Tamagui themes, color palettes, and preview URLs. Use when creating or refining a color scheme, authoring light/dark palettes with brand accents, or previewing generated themes in the browser.
design-loop
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously…
color-palette
Generate complete, accessible colour palettes from a single brand hex. Produces 11-shade scale (50-950), semantic tokens, dark mode variants, Tailwind v4 CSS output, WCAG contrast checks. Use whenever the user supplies a brand hex and asks for a palette, mentions setting up a design system, wants Tailwind theme…
tailwind-theme-builder
Set up Tailwind v4 + shadcn/ui themed UI with dark mode. Install deps, configure CSS variables via @theme inline, wire dark mode toggle, verify. Use whenever the user mentions Tailwind v4, setting up Tailwind theming, shadcn/ui colours, dark mode, or troubleshooting colours not working, tw-animate-css errors, @theme…