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 agentmods add skills/mblode/agent-skills/ui-designnpx skills add mblode/agent-skills --skill ui-designgit clone --depth 1 https://github.com/mblode/agent-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/mblode/agent-skills/ui-design)<a href="https://agentmods.dev/skills/mblode/agent-skills/ui-design"><img src="https://agentmods.dev/badge/skills/mblode/agent-skills/ui-design.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.04807 |
| Opus 5 | $0.00040 | $0.02403 |
| Sonnet 5 | $0.00016 | $0.00961 |
| Haiku 4.5 | $0.00008 | $0.00481 |
Grade A, and why
ui-design 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Design
Owns everything that touches the built artifact: pick the visual direction, implement it in code, and audit what shipped.
- IS: choosing visual direction (palettes, type scales, tokens, layout systems, CRO strategy, brand boards), building UI in code, and auditing built React or Next frontends for user-facing defects with
file:lineevidence, applied fixes, and a ship verdict. - IS NOT: deciding what an interface should do before it exists (use
product-design); non-UI correctness and code quality (usepr-reviewer); agentic-app review (useax-audit); deep typography or motion passes (usetypography-audit,ui-animation); the wording of a string (usecopywriting).
Contents
- product-design, ui-design, or ui-animation?
- Modes
- Direction mode
- Extract mode
- Build mode
- Audit mode
- Other modes
- Quality Bar
- Verify
- Gotchas
- Related skills
Routing boundary
product-design owns action semantics, scope, reversibility, and contested state choices. ui-design builds and styles those states. ui-animation owns timing, gestures, and measured motion. A routine missing loading or error state stays with the UI build; a gesture replacing a control needs a product decision and an accessible alternative before its physics.
Modes
Resolve one mode before acting, and load only that mode's files.
| Mode | Dispatch when the user asks for | Load |
|---|---|---|
| Direction | visual direction, palettes, fonts, tokens, a brand kit, "pick a style"; deliverable is a spec, not code | the Direction section below |
| Extract | recording what an existing codebase already decided: "what design system does this use", "document our tokens", "inventory our components and scales" | references/design-system-extract.md only |
| Build | the target does not exist yet: "build a landing page", "create a dashboard", "add a pricing section" | direction/aesthetic-direction.md, design-guidelines.md, then the applicable files from its index |
| Audit | the target exists and no change was named: "audit this component", "check my UI", "is this accessible", "design QA this page", "is this ready to ship". Deslop scope on "remove AI slop", "looks vibe coded", "simplify this UI" | references/feature-playbooks.md and rules/ only |
| Options | variants to compare in the browser: "show me 3 hero layouts" | ideas.md plus the guidelines per variant |
| Scaffold | semantic, unstyled markup from a screenshot, Figma export, mockup, or wireframe | markup-from-image.md only; the scaffold stays unstyled |
| Retrofit | one dimension added to existing UI: "add dark mode", "make this responsive", "fix this on mobile" | add-dark-mode.md, make-responsive.md; for raster images also dark-mode-image.md (requires the imagegen skill, Codex) |
| Componentize | extracting components or cleaning up classes: "componentize this page", "clean up the Tailwind" | componentize.md; for cleanup also canonicalize-tailwind.md |
What ships with it
60 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.
- add-dark-mode.md 1.0 KB
- canonicalize-tailwind.md 1.5 KB
- componentize.md 2.4 KB
- dark-mode-image.md 2.6 KB
- design-guidelines.md 8.0 KB
- direction/aesthetic-direction.md 3.9 KB
- direction/brand-kit-prompt.md 9.7 KB
- direction/cro.md 5.6 KB
- direction/design-in-code.md 839 B
- direction/marketing-ui.md 7.0 KB
- direction/modern.md 4.2 KB
- direction/product-ui.md 5.7 KB
- direction/testing.md 4.3 KB
- evals/evals.json 1.4 KB
- evaluations/fixtures/clean-settings.tsx 2.2 KB
- evaluations/fixtures/delete-version-modal.tsx 834 B
- evaluations/fixtures/invite-member-form.tsx 1.5 KB
- evaluations/fixtures/pricing-page.tsx 822 B
- evaluations/fixtures/real-proof-landing.tsx 1.8 KB
- evaluations/merge-routing.json 3.7 KB
- evaluations/refine-ai-ui.json 2.9 KB
- guidelines/assets-api.md 6.6 KB
- guidelines/avatars.md 476 B
- guidelines/badges.md 312 B
- guidelines/border-radius.md 817 B
- guidelines/buttons.md 3.1 KB
- guidelines/colors.md 2.5 KB
- guidelines/copywriting.md 1.4 KB
- guidelines/custom-fonts.md 791 B
- guidelines/dark-mode.md 2.1 KB
- guidelines/dashboards.md 386 B
- guidelines/description-lists.md 346 B
- guidelines/feature-lists.md 271 B
- guidelines/flexbox-layout.md 725 B
- guidelines/font-recommendations.md 7.1 KB
- guidelines/footers.md 429 B
- guidelines/form-controls.md 6.7 KB
- guidelines/general.md 5.6 KB
- guidelines/headers.md 391 B
- guidelines/heading-groups.md 1.7 KB
- guidelines/icons.md 1.8 KB
- guidelines/images.md 1006 B
- guidelines/landing-pages.md 1.3 KB
- guidelines/login-pages.md 346 B
- guidelines/logo-clouds.md 414 B
- guidelines/materials.md 2.4 KB
- guidelines/navigation.md 1.3 KB
- guidelines/pagination.md 207 B
- guidelines/placeholder-content.md 2.0 KB
- guidelines/pricing-cards.md 1.8 KB
- guidelines/prose-content.md 2.0 KB
- guidelines/responsive-design.md 1.7 KB
- guidelines/section-layout.md 2.6 KB
- guidelines/shadows.md 1.5 KB
- guidelines/surfaces.md 3.2 KB
- guidelines/svg.md 699 B
- guidelines/tables.md 1.6 KB
- guidelines/team-sections.md 376 B
- guidelines/testimonials.md 753 B
- guidelines/typography.md 2.6 KB
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 · -24 lines · -161 tokens per session a0456b3ebf78
- 6d ago First seen · 251 lines · 241 tokens per session scan A 498c1beabcd3
ui-design is a skill published in the GitHub repository mblode/agent-skills (102 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 4,807 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
frontend-design
Guidance for distinctive, intentional visual design when building or reshaping UI, HTML/React artifacts, dashboards, charts, and visual reports. Use before implementation to choose a content-specific structure, typography, and visual system that does not read as a templated default.
taste-skill
Use this skill when the task involves building or improving any web UI, frontend component, dashboard, or landing page. Enforces high-end design standards and eliminates generic AI-generated interface patterns.
tailwind-v4-shadcn
Production-tested setup for Tailwind CSS v4 with shadcn/ui, Vite, and React. Use when: initializing React projects with Tailwind v4, setting up shadcn/ui, implementing dark mode, debugging CSS variable issues, fixing theme switching, migrating from Tailwind v3, or encountering color/theming problems. Covers: @theme…
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.