Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
.claude/skills/dicklesworthstone-playwright-cli/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -42% | 0% |
bashplaywright-cli open https://playwright.dev playwright-cli click e15 playwright-cli type "page.click" playwright-cli press Enter
playwright-cli open https://example.combashplaywright-cli open https://example.com/ playwright-cli close playwright-cli type "search query" playwright-cli click e3 playwright-cli dblclick e7 playwright-cli fill e5 "user@example.com" playwright-cli drag e2 e8 playwright-cli hover e4 playwright-cli select e9 "option-value" playwright-cli upload ./document.pdf playwright-cli check e12 playwright-cli uncheck e12 playwright-cli snapshot playwright-cli eval "document.title" playwright-cli eval "el => el.textContent" e5 playwright-cli dialog-accept playwright-cli dialog-accept "confirmation text" playwright-cli dialog-dismiss playwright-cli resize 1920 1080
bashplaywright-cli go-back playwright-cli go-forward playwright-cli reload
bashplaywright-cli press Enter playwright-cli press ArrowDown playwright-cli keydown Shift playwright-cli keyup Shift
bashplaywright-cli mousemove 150 300 playwright-cli mousedown playwright-cli mousedown right playwright-cli mouseup playwright-cli mouseup right playwright-cli mousewheel 0 100
bashplaywright-cli screenshot playwright-cli screenshot e5 playwright-cli pdf
bashplaywright-cli tab-list playwright-cli tab-new playwright-cli tab-new https://example.com/page playwright-cli tab-close playwright-cli tab-close 2 playwright-cli tab-select 0
bashplaywright-cli console playwright-cli console warning playwright-cli network playwright-cli run-code "await page.waitForTimeout(1000)" playwright-cli tracing-start playwright-cli tracing-stop
bashplaywright-cli --session=mysession open example.com playwright-cli --session=mysession click e6 playwright-cli session-list playwright-cli session-stop mysession playwright-cli session-stop-all playwright-cli session-delete playwright-cli session-delete mysession
bashplaywright-cli open https://example.com/form playwright-cli snapshot playwright-cli fill e1 "user@example.com" playwright-cli fill e2 "password123" playwright-cli click e3 playwright-cli snapshot
bashplaywright-cli open https://example.com playwright-cli tab-new https://example.com/other playwright-cli tab-list playwright-cli tab-select 0 playwright-cli snapshot
bashplaywright-cli open https://example.com playwright-cli click e4 playwright-cli fill e7 "test" playwright-cli console playwright-cli network
bashplaywright-cli open https://example.com playwright-cli tracing-start playwright-cli click e4 playwright-cli fill e7 "test" playwright-cli tracing-stop
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 18,109 | 23,779 | +31% | 1 | 1 | 0% | 2,770 | 1,756 | -37% | 0 | 0 | — |
case-02 | fail→pass | 16,711 | 6,876 | -59% | 1 | 1 | 0% | 2,670 | 1,920 | -28% | 0 | 0 | — |
case-03 | fail→pass | 20,959 | 4,745 | -77% | 1 | 1 | 0% | 4,288 | 1,935 | -55% | 0 | 0 | — |
case-04 | pass→pass | 8,221 | 7,480 | -9% | 1 | 1 | 0% | 1,867 | 2,534 | +36% | 0 | 0 | — |
case-05 | pass→pass | 10,659 | 7,696 | -28% | 1 | 1 | 0% | 1,926 | 2,290 | +19% | 0 | 0 | — |
case-06 | pass→pass | 6,742 | 4,352 | -35% | 1 | 1 | 0% | 1,189 | 1,742 | +47% | 0 | 0 | — |
case-07 | fail→pass | 10,425 | 5,936 | -43% | 1 | 1 | 0% | 1,772 | 1,952 | +10% | 0 | 0 | — |
case-08 | fail→pass | 13,817 | 2,312 | -83% | 1 | 1 | 0% | 2,278 | 1,324 | -42% | 0 | 0 | — |
case-09 | fail→pass | 8,546 | 2,503 | -71% | 1 | 1 | 0% | 1,531 | 1,194 | -22% | 0 | 0 | — |
case-10 | fail→pass | 12,642 | 2,843 | -78% | 1 | 1 | 0% | 2,397 | 1,329 | -45% | 0 | 0 | — |
case-11 | fail→pass | 15,559 | 1,475 | -91% | 1 | 1 | 0% | 2,308 | 1,159 | -50% | 0 | 0 | — |
case-12 | fail→pass | 8,902 | 2,639 | -70% | 1 | 1 | 0% | 1,650 | 1,191 | -28% | 0 | 0 | — |
case-13 | fail→pass | 10,816 | 1,382 | -87% | 1 | 1 | 0% | 1,746 | 1,056 | -40% | 0 | 0 | — |
case-14 | fail→pass | 17,965 | 4,172 | -77% | 1 | 1 | 0% | 2,625 | 1,661 | -37% | 0 | 0 | — |
case-15 | fail→pass | 6,602 | 1,259 | -81% | 1 | 1 | 0% | 1,237 | 1,057 | -15% | 0 | 0 | — |
case-16 | fail→pass | 15,814 | 1,833 | -88% | 1 | 1 | 0% | 2,991 | 1,153 | -61% | 0 | 0 | — |
case-17 | fail→pass | 10,497 | 1,712 | -84% | 1 | 1 | 0% | 1,690 | 1,161 | -31% | 0 | 0 | — |
case-18 | fail→pass | 6,067 | 3,133 | -48% | 1 | 1 | 0% | 1,032 | 1,082 | +5% | 0 | 0 | — |
case-19 | fail→pass | 8,955 | 1,238 | -86% | 1 | 1 | 0% | 1,570 | 1,137 | -28% | 0 | 0 | — |
case-20 | fail→pass | 10,285 | 1,651 | -84% | 1 | 1 | 0% | 1,451 | 1,069 | -26% | 0 | 0 | — |
case-21 | fail→pass | 11,757 | 3,332 | -72% | 1 | 1 | 0% | 1,697 | 1,156 | -32% | 0 | 0 | — |
case-22 | fail→pass | 7,087 | 1,319 | -81% | 1 | 1 | 0% | 1,089 | 1,110 | +2% | 0 | 0 | — |
case-23 | fail→pass | 11,141 | 1,754 | -84% | 1 | 1 | 0% | 1,789 | 1,107 | -38% | 0 | 0 | — |
case-24 | fail→pass | 9,159 | 1,939 | -79% | 1 | 1 | 0% | 1,300 | 1,119 | -14% | 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. 24 cases were attempted. The headline lift of +88 percentage points is the difference between those two pass rates over the 24 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.