Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when building or reviewing web and iOS product UI and you need real UI references, structured design contracts, or implementation validation through UIZZE MCP.
.claude/skills/lingxling-uizze-ui-research/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-19 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-20 | ✗→✓ | ▲ Improved | -46% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -11% | 0% |
Use UIZZE to give coding agents real product-UI context before implementation rather than relying on a generic styling prompt. The public catalog is free to browse; the hosted MCP workflow requires full access and a configured UIZZE agent token.
This skill turns UI research into an explicit workflow: retrieve relevant references, translate transferable patterns into a design contract, implement within the current project's system, and run the available validation or critique gates.
Confirm that the UIZZE MCP connection is already configured with a valid agent token before invoking hosted workflows. If it is unavailable, use the free public catalog for research or ask the user to configure access; do not attempt to bypass access controls or expose credentials.
Use the available UIZZE tools to find screens, flows, components, or elements that match the product task. Focus on transferable patterns such as hierarchy, navigation, interaction states, spacing, density, and responsive behavior.
Create or use a structured design contract when the task needs explicit acceptance criteria. Adapt patterns to the existing project design system instead of treating any reference as a visual template.
Use the available UIZZE validation, audit, or critique workflow when the implementation is ready for review. Resolve the findings in the project and run normal project tests before calling the work complete.
textUse UIZZE to research real iOS onboarding flows for a subscription product. Identify transferable patterns for progressive disclosure and permission timing, turn them into a concise design contract, then propose an implementation that fits this app's existing design system.
textUse UIZZE to inspect relevant real product settings screens, audit this implementation against a design contract for hierarchy, form states, and navigation, then list the concrete changes needed before release.
Solution: Extract the interaction or hierarchy pattern, then implement it using the target project's own design system and content.
Solution: Search for the smallest useful set of matching screens or flows first, then define constraints before coding.
Solution: Store credentials only in supported local configuration or environment variables and rotate a token if it is exposed.
@stitch-ui-design - Use when generating or iterating UI concepts in Google Stitch.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 16,789 | 9,846 | -41% | 1 | 1 | 0% | 2,237 | 2,515 | +12% | 0 | 0 | — |
case-19 | fail→pass | 14,561 | 6,414 | -56% | 1 | 1 | 0% | 1,779 | 1,889 | +6% | 0 | 0 | — |
case-20 | fail→pass | 27,754 | 9,262 | -67% | 1 | 1 | 0% | 4,263 | 2,315 | -46% | 0 | 0 | — |
case-01 | fail→fail | 38,707 | 24,128 | -38% | 1 | 1 | 0% | 7,940 | 5,593 | -30% | 0 | 0 | — |
case-02 | fail→fail | 42,047 | 24,421 | -42% | 1 | 1 | 0% | 8,243 | 5,568 | -32% | 0 | 0 | — |
case-03 | fail→fail | 38,824 | 32,303 | -17% | 1 | 1 | 0% | 7,361 | 5,983 | -19% | 0 | 0 | — |
case-05 | fail→pass | 11,031 | 7,767 | -30% | 1 | 1 | 0% | 1,734 | 2,153 | +24% | 0 | 0 | — |
case-06 | pass→pass | 14,389 | 8,711 | -39% | 1 | 1 | 0% | 2,067 | 2,083 | +1% | 0 | 0 | — |
case-07 | pass→pass | 14,073 | 7,440 | -47% | 1 | 1 | 0% | 2,004 | 2,080 | +4% | 0 | 0 | — |
case-08 | pass→pass | 19,969 | 12,125 | -39% | 1 | 1 | 0% | 2,554 | 2,981 | +17% | 0 | 0 | — |
case-09 | pass→pass | 13,300 | 10,454 | -21% | 1 | 1 | 0% | 1,940 | 2,161 | +11% | 0 | 0 | — |
case-10 | pass→pass | 11,677 | 8,201 | -30% | 1 | 1 | 0% | 1,528 | 2,126 | +39% | 0 | 0 | — |
case-11 | pass→pass | 13,302 | 4,582 | -66% | 1 | 1 | 0% | 1,772 | 1,572 | -11% | 0 | 0 | — |
case-12 | pass→pass | 11,180 | 6,448 | -42% | 1 | 1 | 0% | 1,572 | 1,725 | +10% | 0 | 0 | — |
case-13 | pass→pass | 17,388 | 12,076 | -31% | 1 | 1 | 0% | 2,949 | 2,927 | -1% | 0 | 0 | — |
case-14 | pass→pass | 100,699 | 26,313 | -74% | 1 | 1 | 0% | 1,783 | 2,126 | +19% | 0 | 0 | — |
case-15 | pass→pass | 19,492 | 16,186 | -17% | 1 | 1 | 0% | 2,624 | 3,123 | +19% | 0 | 0 | — |
case-16 | fail→fail | 9,353 | 4,093 | -56% | 1 | 1 | 0% | 1,539 | 1,512 | -2% | 0 | 0 | — |
case-17 | fail→pass | 14,342 | 4,452 | -69% | 1 | 1 | 0% | 1,963 | 1,608 | -18% | 0 | 0 | — |
case-18 | fail→pass | 15,510 | 11,053 | -29% | 1 | 1 | 0% | 2,520 | 2,253 | -11% | 0 | 0 | — |
case-21 | pass→fail | 19,765 | 10,941 | -45% | 1 | 1 | 0% | 2,823 | 2,406 | -15% | 0 | 0 | — |
case-22 | pass→pass | 11,912 | 8,605 | -28% | 1 | 1 | 0% | 1,900 | 2,265 | +19% | 0 | 0 | — |
case-23 | pass→pass | 13,934 | 6,322 | -55% | 1 | 1 | 0% | 1,843 | 1,817 | -1% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +17 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.