ux-quality

ux-quality is a skill for Claude Code, Codex from clubpay/ronykit. It costs 80 tokens per session (2,460 once invoked), scanned A, original, BSD-3-Clause.

A guide for making web interfaces usable, accessible, and clear while people interact with them. It covers keyboard use, screen readers, forms, navigation, loading, errors, and motion.

In plain words
What is it for?
Building or reviewing forms, dialogs, menus, tables, multi-step workflows, mobile interactions, and empty, loading, and error states.
Why use it?
It helps find problems that may not be visible in a screenshot, such as missing focus indicators, unclear errors, broken keyboard controls, or confusing loading states.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Building or reviewing forms, dialogs, menus, tables, multi-step workflows, mobile interactions, and empty, loading, and error states.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/clubpay/ronykit/ux-quality
Install

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.

Any agent
npx skills add clubpay/ronykit --skill ux-quality
Clone the repo
git clone --depth 1 https://github.com/clubpay/ronykit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ux-quality

README.md
[![agentmods](https://agentmods.dev/badge/skills/clubpay/ronykit/ux-quality.svg)](https://agentmods.dev/skills/clubpay/ronykit/ux-quality)
Your own site
<a href="https://agentmods.dev/skills/clubpay/ronykit/ux-quality"><img src="https://agentmods.dev/badge/skills/clubpay/ronykit/ux-quality.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,460 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.02460
Opus 5 $0.00040 $0.01230
Sonnet 5 $0.00016 $0.00492
Haiku 4.5 $0.00008 $0.00246

Measured 8d ago against content hash 0c5f7df2356a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ux-quality 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 8d 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.

ronyup/internal/skeleton/skills/ux-quality/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX Quality

This is the usability layer beneath the visual layer. frontend-design decides how a UI looks and dashboard-ui decides how data is laid out — this skill decides whether the result is actually operable: reachable by keyboard, legible to a screen reader, clear in every state, and forgiving of mistakes. Most "this feels unprofessional / janky" feedback traces to a gap here, not to the palette.

Pair with shadcn and nextjs-modern for implementation; cross-reference frontend-design (look), dashboard-ui (data density), and react-performance (runtime perf) instead of duplicating them.

When to use

  • Building or reviewing forms, modals, menus, tables, multi-step flows, or any interactive component.
  • An audit pass: "is this accessible / keyboard-navigable / usable on mobile?"
  • Debugging the "looks fine but feels off" class — missing states, no focus ring, layout-shifting press, errors with no recovery path.
  • Designing empty / loading / error states for any data surface.

Priority order

Fix top-down — the first two categories are correctness, not polish.

# Category Severity
1 Accessibility CRITICAL
2 Interaction & touch CRITICAL
3 Forms & feedback HIGH
4 Navigation HIGH
5 Motion MEDIUM

1. Accessibility (CRITICAL)

The floor, not an enhancement. Verify with a keyboard and a screen reader, not by eye.

  • Contrast ≥ 4.5:1 for body text (3:1 for large text and meaningful UI glyphs); check light and dark independently — don't assume one transfers.
  • Visible focus on every interactive element (2–4px ring); never remove the outline without replacing it. Tab order must match visual order.
  • Full keyboard operability — everything clickable is reachable and triggerable by keyboard; no mouse-only or hover-only actions.
  • Name every control — icon-only buttons get an aria-label; inputs get a real <label>; meaningful images get descriptive alt (decorative → alt="").
  • Semantic HTML — real <button>/<a>/<nav>/<h1–h6>; sequential headings, no level skips. Don't rebuild native controls from <div>s.
  • Color is never the only signal — pair status color with an icon, label, or shape (red border and an error message).
  • prefers-reduced-motion respected; support browser zoom / text scaling without clipping or overlap (never disable zoom in the viewport meta).
  • Live regions — announce async results (aria-live="polite", or role="alert" for errors); don't let toasts steal focus.

Read the full file on GitHub · 201 lines

Changes

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.

  1. 8d ago First seen · 201 lines · 80 tokens per session scan A 0c5f7df2356a

Subscribe to this mod's changes

ux-quality is a skill published in the GitHub repository clubpay/ronykit (38 stars, last pushed today), licensed BSD-3-Clause. It adds 80 tokens to every session and 2,460 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.

Related

Other skills, from other repositories

create-remotion-geist

Create Remotion videos using the Geist design system aesthetic. Use when asked to create videos, animations, or motion graphics that should follow Vercel's visual style - dark theme, spring animations, Geist typography, and the Geist color palette.

Marve10s/Better-Fullstack · 54 tokens

multitenant

Multi-tenant / multitenancy patterns in Vovk.ts — hosting multiple tenants from one Next.js app via subdomain routing. Covers the multitenant() helper from vovk, the Next.js proxy.ts file that wires it up, the overrides shape (static / dynamic / nested subdomain patterns), the vovk.config.mjs changes needed (switch to…

finom/vovk · 239 tokens

a2ui-rendering

Use when an agent renders rich UI back to a client surface (cards, dashboards, forms, modals) using the A2UI v0.8.0 declarative protocol. Required whenever the response should display structured components rather than plain text, or whenever the validateandemita2ui tool is in scope.

GoogleCloudPlatform/race-condition · 70 tokens

principle-product-design

UX and product design principles — Nielsen's 10 usability heuristics, visual hierarchy, interaction design patterns, design-system compliance, and responsive layout. Accessibility/WCAG conformance is delegated to swe-workbench:principle-accessibility. Auto-load when reviewing UX, evaluating usability, assessing visual…

lugassawan/swe-workbench · 81 tokens

principle-accessibility

Accessibility (a11y) principles — WCAG 2.2 AA conformance, semantic HTML, keyboard navigation, focus management, focus traps, color contrast, alt text, screen reader compatibility, reduced motion. Auto-load when reviewing frontend or UI code, evaluating ARIA usage, auditing color contrast, building modals or dialogs…

lugassawan/swe-workbench · 89 tokens

nextjs-dashboard

Next.js 15+ App Router dashboard skill — server/client components, mobile nav, polling, data tables, skeleton states, and production-grade dashboard UX patterns.

LuuOW/meridian-mcp · 35 tokens