Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Writes E2E tests with Playwright including test scripts, page objects, test fixtures, reporters, CI integration, API mocking, and visual regression testing.
.claude/skills/paperclipai-playwright-expert/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✓→✗ | ▼ Worse | -12% | 0% |
| case-22 | ✓→✗ | ▼ Worse | -28% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -36% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 10% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 0% | 0% |
name: playwright-expert description: > Writes E2E tests with Playwright including test scripts, page objects, test fixtures, reporters, CI integration, API mocking, and visual regression testing. metadata: sources:
repo: jeffallan/claude-skills path: skills/playwright-expert/SKILL.md commit: 3bf9a24b76a7c122f1fc05e83929fbc84e1c207a attribution: Jeffallan license: MIT usage: referenced
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 8,250 | 5,264 | -36% | 1 | 1 | 0% | 1,578 | 1,010 | -36% | 0 | 0 | — |
case-01 | pass→pass | 7,863 | 7,473 | -5% | 1 | 1 | 0% | 1,663 | 1,823 | +10% | 0 | 0 | — |
case-02 | pass→pass | 10,522 | 9,911 | -6% | 1 | 1 | 0% | 2,160 | 2,165 | +0% | 0 | 0 | — |
case-03 | pass→pass | 9,303 | 6,693 | -28% | 1 | 1 | 0% | 1,826 | 1,498 | -18% | 0 | 0 | — |
case-05 | pass→pass | 20,743 | 11,961 | -42% | 1 | 1 | 0% | 3,500 | 2,535 | -28% | 0 | 0 | — |
case-06 | pass→pass | 14,648 | 13,899 | -5% | 1 | 1 | 0% | 2,835 | 3,092 | +9% | 0 | 0 | — |
case-07 | pass→pass | 7,694 | 5,621 | -27% | 1 | 1 | 0% | 1,330 | 1,308 | -2% | 0 | 0 | — |
case-08 | pass→pass | 8,462 | 5,724 | -32% | 1 | 1 | 0% | 1,508 | 1,125 | -25% | 0 | 0 | — |
case-09 | pass→pass | 4,005 | 4,636 | +16% | 1 | 1 | 0% | 839 | 1,140 | +36% | 0 | 0 | — |
case-10 | pass→pass | 13,258 | 9,484 | -28% | 1 | 1 | 0% | 2,567 | 2,027 | -21% | 0 | 0 | — |
case-11 | pass→pass | 11,224 | 12,173 | +8% | 1 | 1 | 0% | 2,191 | 1,624 | -26% | 0 | 0 | — |
case-12 | pass→pass | 11,251 | 10,749 | -4% | 1 | 1 | 0% | 2,201 | 1,961 | -11% | 0 | 0 | — |
case-13 | pass→pass | 12,022 | 5,992 | -50% | 1 | 1 | 0% | 2,024 | 1,366 | -33% | 0 | 0 | — |
case-14 | pass→pass | 9,907 | 5,886 | -41% | 1 | 1 | 0% | 1,929 | 1,230 | -36% | 0 | 0 | — |
case-15 | pass→fail | 8,516 | 7,370 | -13% | 1 | 1 | 0% | 1,768 | 1,556 | -12% | 0 | 0 | — |
case-16 | pass→pass | 5,326 | 5,395 | +1% | 1 | 1 | 0% | 1,037 | 1,266 | +22% | 0 | 0 | — |
case-17 | pass→pass | 9,483 | 9,756 | +3% | 1 | 1 | 0% | 1,862 | 2,049 | +10% | 0 | 0 | — |
case-18 | pass→pass | 2,774 | 3,727 | +34% | 1 | 1 | 0% | 530 | 843 | +59% | 0 | 0 | — |
case-19 | pass→pass | 8,874 | 3,996 | -55% | 1 | 1 | 0% | 1,883 | 929 | -51% | 0 | 0 | — |
case-20 | pass→pass | 4,386 | 3,835 | -13% | 1 | 1 | 0% | 771 | 775 | +1% | 0 | 0 | — |
case-21 | pass→pass | 5,003 | 5,878 | +17% | 1 | 1 | 0% | 928 | 1,157 | +25% | 0 | 0 | — |
case-22 | pass→fail | 9,190 | 5,961 | -35% | 1 | 1 | 0% | 1,885 | 1,353 | -28% | 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 -100 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Other measured skills in the registry, with their headline benchmark lift.