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 oyi77/1ai-skills --skill ui-critiquegit clone --depth 1 https://github.com/oyi77/1ai-skillsWrote 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/oyi77/1ai-skills/ui-critique)<a href="https://agentmods.dev/skills/oyi77/1ai-skills/ui-critique"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/ui-critique/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/oyi77/1ai-skills/ui-critique"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/ui-critique.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 | $0.00030 | $0.00989 |
| Opus 5 | $0.00015 | $0.00495 |
| Sonnet 5 | $0.00006 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
ui-critique 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Structured framework for reviewing UI designs. Evaluates visual hierarchy, consistency, accessibility, spacing, typography, color usage, and provides actionable improvement recommendations.
Capabilities
- Analyze visual hierarchy and information architecture
- Check consistency across components and pages
- Evaluate accessibility (contrast, focus states, semantic HTML)
- Review responsive behavior across breakpoints
- Provide specific, actionable improvement recommendations
When to Use
Trigger phrases:
-
"ui critique"
-
"Structured UI review — visual hierarchy, consistency, accessibility, and actiona"
-
Before launching a new UI or redesign
-
Onboarding a new team member to design standards
-
User complaints about usability or confusion
-
Pre-launch design review checklist
When NOT to Use
- Task is about content strategy, not creation (use strategy skills)
- Task is about content distribution (use distribution skills)
- You need to analyze content performance (use analytics skills)
- Task is about content moderation (use moderation tools)
- You don't have content guidelines
- Task requires domain expertise (consult experts)
Pseudo Code
The ui-critique workflow follows a standard pipeline pattern.
Core flow:
# ui-critique primary flow
input = prepare(raw_data)
result = process(input, config={accessibility, actionable, consistency, critique, feedback})
validate(result)
deliver(result)
Error handling:
on error:
log(error_details)
retry_with_backoff(max=3)
if still_failing: alert_and_escalate()
Core Workflow
# ui-critique primary flow
input = prepare(raw_data)
result = process(input, config={accessibility, actionable, consistency, critique, feedback})
validate(result)
deliver(result)
Error Handling
on error:
log(error_details)
retry_with_backoff(max=3)
if still_failing: alert_and_escalate()
Critique Framework
def critique_ui(screenshot, url):
checks = {
"visual_hierarchy": check_hierarchy(screenshot), # Can user find CTA in 3s?
"consistency": check_spacing_and_colors(screenshot), # Same patterns everywhere?
"contrast": check_color_contrast(screenshot), # WCAG AA compliant?
"responsive": check_mobile_view(url), # Works on 320px?
"loading": check_performance(url), # LCP < 2.5s?
"accessibility": check_aria_and_semantics(url) # Screen reader friendly?
}
return generate_report(checks)
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.
- 8d ago First seen · 149 lines · 30 tokens per session scan A 39f1623bf739
ui-critique is a skill published in the GitHub repository oyi77/1ai-skills (12 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 989 once invoked, about $0.0002 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
frontend-design
Design and implement polished web components, pages, and applications with a coherent visual direction and usable interaction states.
figma
Fetch Figma design context, variables, screenshots, and assets through MCP when working from Figma URLs or node IDs, or diagnosing its integration.
responsive-design-advisor
Design responsive layouts with breakpoints, mobile-first approach, and flexible grids. Use when creating responsive designs, implementing breakpoints, or optimizing for multiple screen sizes.
hypnotic-pattern
Hypnotic Pattern mesmerizes everyone who looks at it. The real-world version is attention design: loading animations, progress indicators, onboarding flows, and visual patterns that keep users oriented and engaged during a bounded experience. The line between helpful focus and addictive capture is the central design…
popular-web-designs
54 production-quality design systems extracted from real websites. Load a template to generate HTML/CSS that matches the visual identity of sites like Stripe, Linear, Vercel, Notion, Airbnb, and more. Each template includes colors, typography, components, layout rules, and ready-to-use CSS values.
figma-implement-design
Implement UI from Figma URLs or node IDs with visual fidelity, project conventions, and design assets. Requires an available Figma MCP connection.