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 cass-2003/local-workflow-skill --skill uidesigngit clone --depth 1 https://github.com/cass-2003/local-workflow-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/cass-2003/local-workflow-skill/uidesign)<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/uidesign"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/uidesign/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/cass-2003/local-workflow-skill/uidesign"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/uidesign.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 | $0.00200 | $0.02352 |
| Opus 5 | $0.00100 | $0.01176 |
| Sonnet 5 | $0.00040 | $0.00470 |
| Haiku 4.5 | $0.00020 | $0.00235 |
Grade A, and why
UIdesign 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 9d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Design Workflow
Use this skill to turn a UI request into a coherent, implemented, and visually verified interface. It is optimized for Claude Code and Codex working inside real codebases, where the agent must infer constraints, use existing design systems, make conservative product decisions, and validate the result in a browser or screenshot.
Essential Principles
- Design from the user's job, not decoration. Identify the primary user, their task, and the density they need before choosing layout, tone, or visual expression.
- Use the project's system before inventing one. Existing components, tokens, spacing, typography, icons, routes, and copy patterns are the source of truth unless they are broken or absent.
- Make the first screen useful. Apps and tools should open directly into the working experience; marketing-style landing pages belong only when the user explicitly asks for one.
- Treat accessibility as structure. Keyboard flow, focus states, contrast, semantic labels, target sizes, and reduced-motion behavior shape the UI, not a final lint pass.
- Design every state. Empty, loading, error, disabled, active, hover, focus, overflow, small-screen, and long-content states are part of the component contract.
- Use real icon systems. Do not use emoji as production UI icons or controls; use the project's existing SVG/vector icon system, or choose a consistent library such as Lucide, Tabler, Heroicons, Phosphor, or Fluent Icons when no system exists.
- Verify visually before claiming success. Run the app, inspect the UI at relevant desktop and mobile viewports, and fix obvious overlap, blank areas, clipping, broken assets, and unreadable text.
When To Use
- Building or redesigning a frontend screen, dashboard, app, internal tool, SaaS view, landing page, or game-like interface.
- Creating or extending a component library, design system, tokens, theme, icon system, or reusable UI pattern.
- Improving UI polish, layout, hierarchy, responsive behavior, accessibility, visual consistency, or interaction quality.
- Translating a screenshot, mockup, product description,
DESIGN.md, brand guide, or vague "make this look better" request into code. - Reviewing a UI implementation for design risks before handoff.
- Acting as the UI quality pass inside a larger
devworkflow.
What ships with it
4 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.
- 9d ago First seen · 147 lines · 200 tokens per session scan A 0f7fa1113381
UIdesign is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 2mo ago), licensed MIT. It adds 200 tokens to every session and 2,352 once invoked, about $0.0010 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 2026-09-03.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.