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 MigoXLab/webqa-agent --skill ui-auditgit clone --depth 1 https://github.com/MigoXLab/webqa-agentWrote 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/migoxlab/webqa-agent/ui-audit)<a href="https://agentmods.dev/skills/migoxlab/webqa-agent/ui-audit"><img src="https://agentmods.dev/badge/skills/migoxlab/webqa-agent/ui-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/migoxlab/webqa-agent/ui-audit"><img src="https://agentmods.dev/badge/skills/migoxlab/webqa-agent/ui-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00014 | $0.01243 |
| Opus 5.5 | $0.00006 | $0.00497 |
| Sonnet 5.5 | $0.00003 | $0.00249 |
| Haiku 4.5 | $0.00001 | $0.00124 |
Grade A, and why
ui-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 1mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Audit Skill
Evaluate interfaces against proven UX principles.
When to Use
- Auditing a web page for UI/UX quality
- Evaluating accessibility compliance
- Reviewing visual hierarchy and design consistency
- Assessing navigation and information architecture
Core Audit Process
- Take a screenshot of the current page state.
- Take an accessibility snapshot to get the semantic structure.
- Load the core framework reference for the decisioning model:
load_skill(skill_name="ui-audit", reference="00-core-framework") - Evaluate required sections (always include):
- Visual Hierarchy — load
23-patterns-visual-hierarchyif needed - Visual Style — load
12-checklist-visual-styleif needed - Accessibility — load
27-patterns-accessibilityif needed
- Visual Hierarchy — load
- Evaluate contextual sections (include when relevant):
- Navigation (multi-page) — load
31-patterns-navigation - Cognitive Load (complex flows) — load
22-patterns-cognitive-load - Error Handling (forms) — load
26-patterns-error-handling - Onboarding (new users) — load
29-patterns-onboarding - Feedback (interactive) — load
25-patterns-feedback
- Navigation (multi-page) — load
- Generate the audit report in the JSON format below.
Required Audit Sections (always include)
- Visual Hierarchy — headings, CTAs, grouping, reading flow, type scale, color hierarchy, whitespace
- Visual Style — spacing consistency, color usage, elevation/depth, typography, motion/animation
- Accessibility — keyboard navigation, focus states, contrast ratios, screen reader support, touch targets
Contextual Sections (include when relevant)
- Navigation — wayfinding, breadcrumbs, menu structure, information architecture
- Usability — discoverability, feedback, error handling, cognitive load
- Onboarding — first-run, tutorials, progressive disclosure
- Social Proof — testimonials, trust signals, social integration
- Forms — labels, validation, error messages, field types
What ships with it
21 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/00-core-framework.md 5.2 KB
- references/01-anchors.md 6.0 KB
- references/02-information-scaffold.md 11 KB
- references/10-checklist-new-interfaces.md 7.4 KB
- references/11-checklist-fidelity.md 8.1 KB
- references/12-checklist-visual-style.md 8.9 KB
- references/13-checklist-innovation.md 8.7 KB
- references/20-patterns-chunking.md 8.9 KB
- references/21-patterns-progressive-disclosure.md 9.7 KB
- references/22-patterns-cognitive-load.md 8.2 KB
- references/23-patterns-visual-hierarchy.md 9.2 KB
- references/24-patterns-social-proof.md 9.2 KB
- references/25-patterns-feedback.md 9.8 KB
- references/26-patterns-error-handling.md 8.7 KB
- references/27-patterns-accessibility.md 9.9 KB
- references/28-patterns-personalization.md 9.5 KB
- references/29-patterns-onboarding.md 9.6 KB
- references/30-patterns-information.md 10 KB
- references/31-patterns-navigation.md 13 KB
- references/40-defects-text-quality.md 1.6 KB
- references/41-defects-layout-missing.md 2.5 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.
- 1mo ago First seen · 122 lines · 14 tokens per session scan A 117ae836012f
ui-audit is a skill published in the GitHub repository MigoXLab/webqa-agent (234 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,243 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
web-design
Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.
a2ui
Make a reply easier to read and act on with rich blocks inside ordinary Markdown — a choice the user picks from, a form that collects several answers, a procedure as steps with warnings in place, a callout, a Mermaid diagram, a weather card, a live clock or countdown, and a dashboard of gauges for a system snapshot, a…
bento-slides
Create and edit Bento presentations — self-contained .bento.html decks whose document is JSON. Use whenever the user wants a slide deck or presentation: from scratch, from source material, or by improving an existing file.