Install any skill in seconds. Free to start, no credit card required.
Get Started Free →iOS UI testing with XCUITest framework covering element queries, gesture simulation, accessibility testing, and Xcode test plan configuration.
.claude/skills/pramoddutta-xcuitest-ios-testing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-14 | ✓→✗ | ▼ Worse | 50% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 64% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 44% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 28% | 0% |
You are an expert QA engineer specializing in xcuitest ios testing. When the user asks you to write, review, debug, or set up xcuitest related tests or configurations, follow these detailed instructions.
When setting up xcuitest, follow these steps:
swift// Example xcuitest pattern // Adapt this pattern to your specific use case and framework
Integrate xcuitest into your CI/CD pipeline:
When xcuitest issues arise:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 23,840 | 29,913 | +25% | 1 | 1 | 0% | 2,842 | 4,863 | +71% | 0 | 0 | — |
case-02 | pass→pass | 22,104 | 24,046 | +9% | 1 | 1 | 0% | 2,377 | 3,902 | +64% | 0 | 0 | — |
case-03 | pass→pass | 21,031 | 21,564 | +3% | 1 | 1 | 0% | 2,514 | 3,611 | +44% | 0 | 0 | — |
case-04 | fail→fail | 26,207 | 28,059 | +7% | 1 | 1 | 0% | 3,107 | 4,412 | +42% | 0 | 0 | — |
case-05 | pass→pass | 28,183 | 30,390 | +8% | 1 | 1 | 0% | 3,337 | 4,263 | +28% | 0 | 0 | — |
case-06 | pass→pass | 15,752 | 23,430 | +49% | 1 | 1 | 0% | 2,324 | 3,469 | +49% | 0 | 0 | — |
case-07 | pass→pass | 23,710 | 28,384 | +20% | 1 | 1 | 0% | 2,473 | 4,056 | +64% | 0 | 0 | — |
case-08 | pass→pass | 24,247 | 27,864 | +15% | 1 | 1 | 0% | 2,624 | 3,651 | +39% | 0 | 0 | — |
case-09 | pass→pass | 23,684 | 20,959 | -12% | 1 | 1 | 0% | 2,780 | 3,811 | +37% | 0 | 0 | — |
case-10 | fail→pass | 22,022 | 22,755 | +3% | 1 | 1 | 0% | 2,562 | 3,713 | +45% | 0 | 0 | — |
case-11 | pass→pass | 19,800 | 17,479 | -12% | 1 | 1 | 0% | 2,129 | 2,730 | +28% | 0 | 0 | — |
case-12 | pass→pass | 13,008 | 15,754 | +21% | 1 | 1 | 0% | 1,129 | 2,169 | +92% | 0 | 0 | — |
case-13 | pass→pass | 21,312 | 24,787 | +16% | 1 | 1 | 0% | 2,436 | 3,624 | +49% | 0 | 0 | — |
case-14 | pass→fail | 24,754 | 25,247 | +2% | 1 | 1 | 0% | 2,709 | 4,070 | +50% | 0 | 0 | — |
case-15 | pass→pass | 19,174 | 23,316 | +22% | 1 | 1 | 0% | 2,193 | 3,396 | +55% | 0 | 0 | — |
case-16 | pass→pass | 18,848 | 24,948 | +32% | 1 | 1 | 0% | 2,643 | 4,292 | +62% | 0 | 0 | — |
case-17 | pass→pass | 19,804 | 26,804 | +35% | 1 | 1 | 0% | 2,786 | 3,992 | +43% | 0 | 0 | — |
case-18 | pass→pass | 21,247 | 21,106 | -1% | 1 | 1 | 0% | 2,311 | 3,856 | +67% | 0 | 0 | — |
case-19 | pass→pass | 23,386 | 17,994 | -23% | 1 | 1 | 0% | 2,457 | 3,540 | +44% | 0 | 0 | — |
case-20 | pass→pass | 13,231 | 13,826 | +4% | 1 | 1 | 0% | 1,340 | 2,225 | +66% | 0 | 0 | — |
case-21 | pass→pass | 26,568 | 29,353 | +10% | 1 | 1 | 0% | 3,663 | 4,803 | +31% | 0 | 0 | — |
case-22 | pass→pass | 11,222 | 14,825 | +32% | 1 | 1 | 0% | 902 | 2,048 | +127% | 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. 22 cases were attempted. The headline lift of 0 percentage points is the difference between those two pass rates over the 22 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.