Borrowing it
Nothing to install: this file belongs to bonnguyenitc/antigravity-superpowers. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bonnguyenitc/antigravity-superpowers/main/.agent/skills/ux-designer/SKILL.mdgit clone --depth 1 https://github.com/bonnguyenitc/antigravity-superpowersWrote 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/bonnguyenitc/antigravity-superpowers/ux-designer)<a href="https://agentmods.dev/skills/bonnguyenitc/antigravity-superpowers/ux-designer"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/antigravity-superpowers/ux-designer/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/bonnguyenitc/antigravity-superpowers/ux-designer"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/antigravity-superpowers/ux-designer.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 | $0.00037 | $0.01165 |
| Opus 5.5 | $0.00015 | $0.00466 |
| Sonnet 5.5 | $0.00007 | $0.00233 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
ux-designer 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Designer Lens
Philosophy: Design is problem solving, not decoration. Good UX is invisible — users accomplish their goal without noticing the interface. The best design eliminates decisions the user shouldn't have to make.
⚠️ ASK BEFORE ASSUMING
| What | Why it matters |
|---|---|
| Platform? iOS / Android / Web / Desktop | Each has distinct patterns and constraints |
| Stage? Early exploration / Detailed design / Polish | Changes fidelity needed |
| User research available? | Can't design for a user you haven't talked to |
| Design system exists? | Whether to extend or create from scratch |
Core Instincts
- Design for the job-to-be-done — what is the user trying to accomplish? Remove everything that doesn't serve that
- Hierarchy guides the eye — size, color, and position communicate importance; every screen needs one clear primary action
- Friction has a cost — every tap, field, and decision users must make is a drop in task completion
- Don't make me think (Steve Krug) — if users have to figure it out, the design failed
- Test with 5 users — 5 usability test sessions reveal ~85% of usability problems
Hick's Law & Fitts' Law Applied
Hick's Law: Decision time = log2(N choices)
→ More options = slower decisions = more friction
→ Max 5–7 items in navigation; fewer primary actions per screen
Fitts' Law: Time to tap = a + b × log2(distance/size + 1)
→ Bigger targets = faster taps
→ Primary CTA: minimum 44×44pt (iOS) / 48×48dp (Android) / 44×44px (web)
→ Place common actions closer to thumb (bottom of screen on mobile)
Design Hierarchy Checklist
Every screen needs exactly:
- 1 primary action (largest, highest contrast, most prominent)
- 0–2 secondary actions (smaller, lower contrast)
- 0–1 tertiary action (text link or icon)
If a screen has 3+ things competing for attention → redesign.
❌ Anti-Patterns to Avoid
| ❌ NEVER DO | Why | ✅ DO INSTEAD |
|---|---|---|
| Design in isolation without user feedback | Solving assumed problems | User interviews before wireframing |
| 5+ items in primary navigation | Cognitive overload, users freeze | 4–5 items max; progressive disclosure for the rest |
| Decorative animations only | Distraction without purpose | Animations that communicate state change or guide attention |
| Red for non-error states | Deep-wired association: red = danger | Reserve red for errors/destructive actions only |
| Long onboarding before value | Users leave before experiencing product | Show value first, teach later |
| Placeholder text as labels | Disappears on input, user forgets context | Floating labels or static labels above inputs |
| Custom gestures with no affordance | Undiscoverable | Teach novel gestures with a coach mark on first encounter |
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 · 129 lines · 37 tokens per session scan A 2f4a1a73c8c9
ux-designer is a skill published in the GitHub repository bonnguyenitc/antigravity-superpowers (20 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 1,165 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
iot-ai-web-visual-quality
Bounded visual-quality guidance for websites, dashboards, frontend UI, design systems and graphic prompts.
garden-web-design
Derived web-design quality checklist. Reference-only. Not a Garden runtime.
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop.
dataviz
Design guidance for charts, graphs, dashboards, maps, and data visualizations, including a local palette validator.
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
brand-identity
Use when a project needs its visual foundation built or consolidated into one system: logo brief, color system in HEX/RGB/CMYK/OKLCH with proven AA contrast, type system, usage rules, and an exported W3C design-tokens.json that later skills consume. NOT the applied UI pixels (that is design), NOT the words or tone…