Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Pause the execution of the script for a specified duration.
.claude/skills/testdriverai-testdriver-wait/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -27% | 0% |
<!-- Generated from wait.mdx. DO NOT EDIT. -->
The wait method pauses test execution for a specified number of milliseconds before continuing. This is useful for adding delays between actions, waiting for animations to complete, or pausing for state changes to settle.
javascriptawait testdriver.wait(timeout);
| Argument | Type | Default | Description | | --------- | -------- | ------- | ------------------------------------- | | timeout | number | 3000 | The duration in milliseconds to wait. |
javascript// Wait 2 seconds for an animation to complete await testdriver.find('submit button').click(); await testdriver.wait(2000); // Wait 5 seconds await testdriver.wait(5000); // Wait with default timeout (3 seconds) await testdriver.wait();
find() with a timeout option instead:javascript // ✅ Better for waiting for elements const element = await testdriver.find('success message', { timeout: 30000 });
// ❌ Don't do this for element waiting await testdriver.wait(5000); const element = await testdriver.find('success message');
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→pass | 9,959 | 4,784 | -52% | 1 | 1 | 0% | 1,529 | 1,226 | -20% | 0 | 0 | — |
case-12 | pass→pass | 2,534 | 1,408 | -44% | 1 | 1 | 0% | 434 | 621 | +43% | 0 | 0 | — |
case-17 | fail→pass | 4,433 | 1,533 | -65% | 1 | 1 | 0% | 673 | 604 | -10% | 0 | 0 | — |
case-01 | fail→pass | 7,303 | 14,862 | +104% | 1 | 1 | 0% | 1,207 | 759 | -37% | 0 | 0 | — |
case-02 | fail→pass | 8,207 | 2,059 | -75% | 1 | 1 | 0% | 1,273 | 679 | -47% | 0 | 0 | — |
case-03 | fail→pass | 6,399 | 2,094 | -67% | 1 | 1 | 0% | 964 | 705 | -27% | 0 | 0 | — |
case-04 | pass→pass | 6,432 | 2,313 | -64% | 1 | 1 | 0% | 943 | 797 | -15% | 0 | 0 | — |
case-05 | fail→pass | 7,162 | 1,645 | -77% | 1 | 1 | 0% | 1,143 | 622 | -46% | 0 | 0 | — |
case-07 | pass→pass | 5,989 | 2,514 | -58% | 1 | 1 | 0% | 1,024 | 850 | -17% | 0 | 0 | — |
case-08 | pass→pass | 9,666 | 2,232 | -77% | 1 | 1 | 0% | 1,449 | 736 | -49% | 0 | 0 | — |
case-09 | pass→pass | 6,379 | 4,493 | -30% | 1 | 1 | 0% | 1,195 | 1,261 | +6% | 0 | 0 | — |
case-10 | fail→pass | 6,882 | 2,020 | -71% | 1 | 1 | 0% | 1,160 | 608 | -48% | 0 | 0 | — |
case-11 | fail→pass | 11,657 | 2,837 | -76% | 1 | 1 | 0% | 1,881 | 909 | -52% | 0 | 0 | — |
case-13 | pass→pass | 3,814 | 1,708 | -55% | 1 | 1 | 0% | 615 | 635 | +3% | 0 | 0 | — |
case-14 | fail→pass | 11,045 | 5,279 | -52% | 1 | 1 | 0% | 1,613 | 1,355 | -16% | 0 | 0 | — |
case-15 | pass→pass | 11,037 | 5,110 | -54% | 1 | 1 | 0% | 1,777 | 1,142 | -36% | 0 | 0 | — |
case-16 | fail→pass | 9,703 | 4,375 | -55% | 1 | 1 | 0% | 1,636 | 1,217 | -26% | 0 | 0 | — |
case-18 | fail→pass | 9,674 | 2,289 | -76% | 1 | 1 | 0% | 1,598 | 833 | -48% | 0 | 0 | — |
case-19 | pass→pass | 9,790 | 3,009 | -69% | 1 | 1 | 0% | 1,343 | 806 | -40% | 0 | 0 | — |
case-20 | pass→pass | 5,017 | 1,639 | -67% | 1 | 1 | 0% | 818 | 575 | -30% | 0 | 0 | — |
case-21 | fail→pass | 15,092 | 4,318 | -71% | 1 | 1 | 0% | 2,454 | 1,137 | -54% | 0 | 0 | — |
case-22 | fail→pass | 31,439 | 1,968 | -94% | 1 | 1 | 0% | 4,709 | 605 | -87% | 0 | 0 | — |
case-23 | fail→pass | 4,794 | 2,375 | -50% | 1 | 1 | 0% | 667 | 699 | +5% | 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 +61 percentage points is the difference between those two pass rates over the 23 comparable cases.
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.