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 EnchStyle/ui-ux-audit-skill --skill ui-ux-auditgit clone --depth 1 https://github.com/EnchStyle/ui-ux-audit-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/enchstyle/ui-ux-audit-skill/ui-ux-audit)<a href="https://agentmods.dev/skills/enchstyle/ui-ux-audit-skill/ui-ux-audit"><img src="https://agentmods.dev/badge/skills/enchstyle/ui-ux-audit-skill/ui-ux-audit/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/enchstyle/ui-ux-audit-skill/ui-ux-audit"><img src="https://agentmods.dev/badge/skills/enchstyle/ui-ux-audit-skill/ui-ux-audit.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 | $0.00226 | $0.03994 |
| Opus 5 | $0.00113 | $0.01997 |
| Sonnet 5 | $0.00045 | $0.00799 |
| Haiku 4.5 | $0.00023 | $0.00399 |
Grade A, and why
ui-ux-audit 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI/UX Audit
Catch the UI problems AI consistently introduces, and either report them with concrete fixes (audit) or avoid them while writing code (prevention).
Why this skill exists
Almost every AI UI failure traces back to one root cause: the model generates a plausible static snapshot of a single state (usually the happy path on a desktop viewport), it cannot see the rendered result, and it carries no persistent design system across generations. The output looks right in a screenshot and breaks the moment content grows, the viewport shrinks, an error occurs, or a second component is generated with slightly different padding. A human developer carries an internalised model of "what happens when this grows, shrinks, errors, or gets tapped." This skill forces that model into view: every check below exists because AI reliably gets it wrong.
The three modes
1. Full audit. Triggered by explicit requests like "run a full UI audit", "audit this app/page/component", "full design review", "is this ready to ship". This is the heavyweight, systematic pass: read ALL reference files listed below, simulate the real user first (the method in references/user-simulation.md), then walk every category in order, and produce the scored report defined in this file. Do not skip categories because they look fine at a glance; AI failures hide in the categories that were not checked.
2. Quick review. Triggered by narrower requests like "review this button", "fix the spacing here", "why does this look off". Identify which categories the request touches, read only the matching reference files, scan, and report findings in the same finding format but without the full scored ceremony (severity tags still required; score optional unless asked).
3. Prevention. Active whenever writing or editing any UI code. Before writing, run the Pre-flight checklist at the bottom of this file mentally, and read any reference file relevant to what is being built (e.g. building a form: read references/color-states-forms.md). Do not produce a report; just ship code that passes the audit it would otherwise fail.
What ships with it
14 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.
- references/anti-slop-copy.md 6.7 KB
- references/color-states-forms.md 7.9 KB
- references/consistency-tokens-nav.md 6.8 KB
- references/data-viz-tables.md 5.8 KB
- references/durable-fixes.md 4.1 KB
- references/examples.md 4.2 KB
- references/interaction-responsive-a11y.md 6.5 KB
- references/motion-performance.md 5.6 KB
- references/profile-ecommerce.md 7.9 KB
- references/profile-example-kids-app.md 9.2 KB
- references/profile-marketing-landing.md 7.4 KB
- references/profile-saas-dashboard.md 8.9 KB
- references/structure-typography.md 8.6 KB
- references/user-simulation.md 6.3 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.
- 10d ago First seen · 194 lines · 226 tokens per session scan A da7c9373a736
ui-ux-audit is a skill published in the GitHub repository EnchStyle/ui-ux-audit-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 226 tokens to every session and 3,994 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
ui-ux-laws
Priority-ordered rulebook of core UX/UI laws, cognitive-psychology principles, Nielsen's usability heuristics, and accessibility requirements that Claude must actively apply (not just cite) whenever it designs, builds, redesigns, reviews, or critiques any user interface — websites, web/mobile apps, dashboards, forms…
scroll-craft
Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photos and footage or…
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
information-architecture
Design the structure of a website or product including sitemap, navigation, URL structure, content types, taxonomy, and labeling. Use this skill whenever the user asks to plan a sitemap, design navigation, structure URLs, define content types, build taxonomies, design site search, or organize content at the system…
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…