Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cross-browser and cross-device testing using BrowserStack or Sauce Labs
.claude/skills/a5c-ai-browser-stack/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -21% | 0% |
Execute cross-browser and cross-device testing using cloud testing platforms like BrowserStack or Sauce Labs.
json{ "type": "object", "properties": { "platform": { "type": "string", "enum": ["browserstack", "saucelabs"], "default": "browserstack" }, "testUrl": { "type": "string", "description": "URL to test" }, "browsers": { "type": "array", "items": { "type": "object", "properties": { "browser": { "type": "string" }, "version": { "type": "string" }, "os": { "type": "string" } } } }, "devices": { "type": "array", "items": { "type": "object", "properties": { "device": { "type": "string" }, "osVersion": { "type": "string" } } } }, "testType": { "type": "string", "enum": ["screenshot", "functional", "visual-regression", "performance"], "default": "screenshot" }, "viewports": { "type": "array", "items": { "type": "object", "properties": { "width": { "type": "number" }, "height": { "type": "number" } } } } }, "required": ["testUrl"] }
json{ "type": "object", "properties": { "testResults": { "type": "array", "items": { "type": "object", "properties": { "browser": { "type": "string" }, "device": { "type": "string" }, "status": { "type": "string" }, "screenshotUrl": { "type": "string" } } } }, "compatibilityMatrix": { "type": "object", "description": "Browser/device compatibility summary" }, "issues": { "type": "array", "description": "Detected compatibility issues" }, "reportUrl": { "type": "string", "description": "URL to full test report" } } }
javascriptconst result = await skill.execute({ platform: 'browserstack', testUrl: 'https://example.com', browsers: [ { browser: 'chrome', version: 'latest', os: 'Windows 11' }, { browser: 'safari', version: 'latest', os: 'OS X Sonoma' } ], devices: [ { device: 'iPhone 15', osVersion: '17' }, { device: 'Samsung Galaxy S24', osVersion: '14' } ], testType: 'screenshot' });
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 19,118 | 13,612 | -29% | 1 | 1 | 0% | 2,695 | 2,562 | -5% | 0 | 0 | — |
case-02 | fail→fail | 16,247 | 14,549 | -10% | 1 | 1 | 0% | 2,152 | 2,736 | +27% | 0 | 0 | — |
case-03 | fail→fail | 18,295 | 15,118 | -17% | 1 | 1 | 0% | 2,534 | 3,006 | +19% | 0 | 0 | — |
case-04 | fail→pass | 11,164 | 9,580 | -14% | 1 | 1 | 0% | 1,138 | 1,797 | +58% | 0 | 0 | — |
case-05 | fail→pass | 14,861 | 9,979 | -33% | 1 | 1 | 0% | 1,742 | 1,955 | +12% | 0 | 0 | — |
case-06 | fail→pass | 14,956 | 8,928 | -40% | 1 | 1 | 0% | 1,950 | 1,566 | -20% | 0 | 0 | — |
case-07 | fail→pass | 13,806 | 8,482 | -39% | 1 | 1 | 0% | 1,817 | 1,536 | -15% | 0 | 0 | — |
case-08 | fail→pass | 16,703 | 10,154 | -39% | 1 | 1 | 0% | 2,467 | 1,946 | -21% | 0 | 0 | — |
case-09 | fail→pass | 17,131 | 12,588 | -27% | 1 | 1 | 0% | 2,230 | 1,911 | -14% | 0 | 0 | — |
case-20 | pass→pass | 22,192 | 47,468 | +114% | 1 | 1 | 0% | 3,619 | 5,163 | +43% | 0 | 0 | — |
case-10 | fail→pass | 19,276 | 10,001 | -48% | 1 | 1 | 0% | 2,619 | 1,918 | -27% | 0 | 0 | — |
case-11 | fail→pass | 22,674 | 12,323 | -46% | 1 | 1 | 0% | 3,785 | 2,136 | -44% | 0 | 0 | — |
case-12 | fail→fail | 19,401 | 14,416 | -26% | 1 | 1 | 0% | 3,079 | 2,900 | -6% | 0 | 0 | — |
case-13 | fail→pass | 25,876 | 17,276 | -33% | 1 | 1 | 0% | 3,691 | 3,531 | -4% | 0 | 0 | — |
case-14 | fail→pass | 20,190 | 16,319 | -19% | 1 | 1 | 0% | 2,739 | 3,110 | +14% | 0 | 0 | — |
case-15 | fail→pass | 16,142 | 9,793 | -39% | 1 | 1 | 0% | 2,062 | 1,481 | -28% | 0 | 0 | — |
case-16 | fail→pass | 16,139 | 8,915 | -45% | 1 | 1 | 0% | 2,221 | 1,594 | -28% | 0 | 0 | — |
case-17 | fail→pass | 14,073 | 12,827 | -9% | 1 | 1 | 0% | 1,871 | 2,027 | +8% | 0 | 0 | — |
case-18 | fail→fail | 10,424 | 7,473 | -28% | 1 | 1 | 0% | 874 | 1,191 | +36% | 0 | 0 | — |
case-19 | fail→pass | 18,108 | 22,743 | +26% | 1 | 1 | 0% | 2,514 | 2,112 | -16% | 0 | 0 | — |
case-21 | pass→pass | 18,827 | 16,512 | -12% | 1 | 1 | 0% | 2,680 | 3,256 | +21% | 0 | 0 | — |
case-22 | pass→pass | 18,212 | 13,355 | -27% | 1 | 1 | 0% | 2,481 | 3,394 | +37% | 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 +64 percentage points is the difference between those two pass rates over the 22 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.