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 | $0.00225 | $0.05798 |
| Opus 5.5 | $0.00090 | $0.02319 |
| Sonnet 5.5 | $0.00045 | $0.01160 |
| Haiku 4.5 | $0.00022 | $0.00580 |
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 28d 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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI/UX Audit
Find the interface problems AI tools ship, report them with fixes (audit), or avoid them while building (build mode), and push the visual quality from correct to exceptional.
Most AI UI failures share one cause: the model writes a plausible snapshot of one state at one width, never sees the rendered result, and carries no design system from one component to the next. So the page looks right in a screenshot and breaks when content grows, the viewport narrows, an error occurs, or a second component arrives with slightly different padding. The cure is to measure the render instead of reasoning about it, and to hold every element to one global system.
Modes
| Mode | Triggered by | Read | Output |
|---|---|---|---|
| Full audit | "audit this page", "is this ready to ship", "full review" | This file, the matching profile, references/visual-excellence.md, references/alignment-consistency.md, references/user-simulation.md, then the category references for what the page contains (table below) |
Scored report |
| Quick review | "why does this card look off", "check this button" | This file and the one or two references the question touches | Short answer, no score |
| Build | Creating or restyling a page, dashboard, report or component | This file, the matching profile, references/visual-excellence.md and references/alignment-consistency.md; the pre-flight checklist below stands in for the category references, so open those only when a question comes up |
The code, then a short hand-over |
A matching profile overrides the universal defaults wherever they differ.
Step 1: measure the render
Run the bundled script on the page before judging anything:
python3 <skill folder>/scripts/uicheck.py page.html --json checks.json --shots shots/
It needs Python Playwright with Chromium (it also accepts an http(s) URL; add --dark for the dark
theme, --widths 320,360,768,1280,1440 to change widths). It renders at 360, 768 and 1280px and
measures horizontal overflow, contrast, target sizes, unnamed controls, invisible focus, unsized
media, heading order, small text, widows and wrapping button labels, lone grid items, card rows off a
shared line, tile values off a baseline, side-by-side control heights, non-concentric corners,
near-miss left edges, padding asymmetry, mixed media ratios, icon and chip size drift, gutters,
table header alignment, long tables without a sticky header, heading proximity, and a census of
radii, shadows, font sizes, families and section paddings.
What ships with it
18 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/alignment-consistency.md 9.9 KB
- references/color-states-forms.md 5.4 KB
- references/content-honesty.md 3.8 KB
- references/data-viz-tables.md 4.6 KB
- references/durable-fixes.md 3.0 KB
- references/examples.md 4.8 KB
- references/interaction-responsive-a11y.md 5.3 KB
- references/motion-performance.md 2.6 KB
- references/navigation-icons.md 2.0 KB
- references/profile-analytics-report.md 3.6 KB
- references/profile-ecommerce.md 3.8 KB
- references/profile-kids-app.md 3.4 KB
- references/profile-marketing-landing.md 4.2 KB
- references/profile-saas-dashboard.md 3.5 KB
- references/structure-typography.md 5.3 KB
- references/user-simulation.md 2.4 KB
- references/visual-excellence.md 7.8 KB
- scripts/uicheck.py 32 KB runs code
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.
- 28d ago Changed · +146 lines · -1 tokens per session 589561094a0b
- 1mo 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 (6 stars, last pushed 29d ago), licensed MIT. It adds 225 tokens to every session and 5,798 once invoked, about $0.0009 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
diagram-design
Design editorial-quality diagrams as self-contained inline SVG — architecture diagrams, flows, sequences, state machines, data models, timelines, layer stacks, quadrants, comparisons, system maps, change views, deployment maps, and dependency graphs. Use when explaining how a system is arranged, how a process moves…
writing-documents
Write structured software-delivery and consultancy documents as Markdown in the repo by default. Use for canonical decision, contract, procedure, learning, system, incident, suite, plan, assurance, and brief types, including design and architecture docs, requirements, delivery plans, reviews, status, release, support…
brand-theme-design
Turn a brand into a working theme for this design system — from a screenshot, a website, a PDF brand guide, a style guide, or a handful of hex values. Use when asked to match a company's brand, apply brand colors or brand guidelines to documents, make reports look like an existing site or product, build a theme from a…
chart-design
Design honest, accessible charts of quantitative data as inline SVG — bar and column charts, line and time series, limit ledgers, distributions, scatter plots, small multiples, and waterfall bridges. Use when visualizing measured values, choosing a chart type, picking or fixing chart colors, building a categorical…
presentation-design
Design presentation decks as self-contained 16:9 HTML slides that export cleanly to PDF — board updates, project reviews, findings readouts, proposals, and conference talks. Use when building a deck, slides, a presentation, or a leadership readout; when converting a report or a set of findings into slides; or when an…
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…