Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Migrate from Cypress or Selenium to Playwright. Use when user mentions "cypress", "selenium", "migrate tests", "convert tests", "switch to playwright", "move from cypress", or "replace selenium".
.claude/skills/alirezarezvani-migrate/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 90% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-23 | ✓→✗ | ▼ Worse | -40% | 0% |
| case-24 | ✓→✗ | ▼ Worse | -58% | 0% |
Interactive migration from Cypress or Selenium to Playwright with file-by-file conversion.
$ARGUMENTS can be:
"from cypress" — migrate Cypress test suite"from selenium" — migrate Selenium/WebDriver testsUse Explore subagent to scan:
cypress/ directory or cypress.config.ts → Cypressselenium, webdriver in package.json deps → Selenium.py test files with selenium imports → Selenium (Python)Count files and categorize:
Migration Assessment:
- Total test files: X
- Cypress custom commands: Y
- Cypress fixtures: Z
- Estimated effort: [small|medium|large]| Size | Files | Approach | |---|---|---| | Small (1-10) | Convert sequentially | Direct conversion | | Medium (11-30) | Batch in groups of 5 | Use sub-agents | | Large (31+) | Use /batch | Parallel conversion with /batch |
Run /pw:pw-init first if Playwright isn't configured.
For each file, apply the appropriate mapping:
Load cypress-mapping.md for complete reference.
Key translations:
cy.visit(url) → page.goto(url)
cy.get(selector) → page.locator(selector) or page.getByRole(...)
cy.contains(text) → page.getByText(text)
cy.find(selector) → locator.locator(selector)
cy.click() → locator.click()
cy.type(text) → locator.fill(text)
cy.should('be.visible') → expect(locator).toBeVisible()
cy.should('have.text') → expect(locator).toHaveText(text)
cy.intercept() → page.route()
cy.wait('@alias') → page.waitForResponse()
cy.fixture() → JSON import or test data fileCypress custom commands → Playwright fixtures or helper functions Cypress plugins → Playwright config or fixtures before/beforeEach → test.beforeAll() / test.beforeEach()
Load selenium-mapping.md for complete reference.
Key translations:
driver.get(url) → page.goto(url)
driver.findElement(By.id('x')) → page.locator('#x') or page.getByTestId('x')
driver.findElement(By.css('.x')) → page.locator('.x') or page.getByRole(...)
element.click() → locator.click()
element.sendKeys(text) → locator.fill(text)
element.getText() → locator.textContent()
WebDriverWait + ExpectedConditions → expect(locator).toBeVisible()
driver.switchTo().frame() → page.frameLocator()
Actions → locator.hover(), locator.dragTo()During conversion, upgrade selectors to Playwright best practices:
#id → getByTestId() or getByRole().class → getByRole() or getByText()[data-testid] → getByTestId()test.extend()After converting each file:
bashnpx playwright test <converted-file> --reporter=list
Fix any compilation or runtime errors before moving to the next file.
After all files are converted:
package.jsoncypress.config.ts, etc.)Ask user before deleting anything.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 28,510 | 16,224 | -43% | 1 | 1 | 0% | 4,407 | 1,398 | -68% | 0 | 0 | — |
case-02 | fail→fail | 23,363 | 11,402 | -51% | 1 | 1 | 0% | 4,618 | 1,393 | -70% | 0 | 0 | — |
case-03 | fail→fail | 19,596 | 15,629 | -20% | 1 | 1 | 0% | 3,982 | 1,308 | -67% | 0 | 0 | — |
case-04 | pass→pass | 10,270 | 33,561 | +227% | 1 | 1 | 0% | 1,932 | 2,982 | +54% | 0 | 0 | — |
case-05 | pass→pass | 12,158 | 6,050 | -50% | 1 | 1 | 0% | 1,405 | 2,219 | +58% | 0 | 0 | — |
case-06 | pass→pass | 18,444 | 13,023 | -29% | 1 | 1 | 0% | 2,597 | 3,460 | +33% | 0 | 0 | — |
case-07 | pass→pass | 15,494 | 13,977 | -10% | 1 | 1 | 0% | 1,862 | 2,772 | +49% | 0 | 0 | — |
case-08 | pass→pass | 11,235 | 8,794 | -22% | 1 | 1 | 0% | 2,128 | 2,678 | +26% | 0 | 0 | — |
case-09 | pass→pass | 6,675 | 10,706 | +60% | 1 | 1 | 0% | 1,211 | 2,082 | +72% | 0 | 0 | — |
case-10 | pass→pass | 14,515 | 12,196 | -16% | 1 | 1 | 0% | 1,760 | 2,321 | +32% | 0 | 0 | — |
case-11 | pass→pass | 10,970 | 6,799 | -38% | 1 | 1 | 0% | 1,041 | 2,085 | +100% | 0 | 0 | — |
case-12 | pass→pass | 7,370 | 3,404 | -54% | 1 | 1 | 0% | 1,008 | 1,612 | +60% | 0 | 0 | — |
case-13 | fail→pass | 22,236 | 7,650 | -66% | 1 | 1 | 0% | 2,828 | 2,406 | -15% | 0 | 0 | — |
case-14 | fail→fail | 11,088 | 12,409 | +12% | 1 | 1 | 0% | 1,876 | 2,176 | +16% | 0 | 0 | — |
case-15 | pass→pass | 17,081 | 9,125 | -47% | 1 | 1 | 0% | 2,406 | 2,840 | +18% | 0 | 0 | — |
case-16 | fail→pass | 4,277 | 2,992 | -30% | 1 | 1 | 0% | 734 | 1,392 | +90% | 0 | 0 | — |
case-17 | fail→pass | 16,229 | 9,202 | -43% | 1 | 1 | 0% | 1,678 | 1,720 | +3% | 0 | 0 | — |
case-18 | fail→fail | 11,697 | 3,407 | -71% | 1 | 1 | 0% | 1,173 | 1,565 | +33% | 0 | 0 | — |
case-19 | fail→fail | 6,970 | 10,369 | +49% | 1 | 1 | 0% | 1,277 | 1,974 | +55% | 0 | 0 | — |
case-20 | pass→pass | 17,949 | 8,191 | -54% | 1 | 1 | 0% | 1,860 | 2,584 | +39% | 0 | 0 | — |
case-21 | pass→pass | 11,352 | 11,630 | +2% | 1 | 1 | 0% | 2,182 | 2,238 | +3% | 0 | 0 | — |
case-22 | pass→pass | 16,835 | 43,812 | +160% | 1 | 1 | 0% | 3,964 | 7,027 | +77% | 0 | 0 | — |
case-23 | pass→fail | 16,688 | 13,138 | -21% | 1 | 1 | 0% | 2,285 | 1,372 | -40% | 0 | 0 | — |
case-24 | pass→fail | 22,867 | 10,893 | -52% | 1 | 1 | 0% | 3,321 | 1,381 | -58% | 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, and 19 counted toward the lift figure. The other 5 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +4 percentage points is the difference between those two pass rates over the 19 comparable cases. 2 cases got worse with the skill loaded, and they are 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/11/2026 | +9% |
Other measured skills in the registry, with their headline benchmark lift.