Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Page Object Model patterns for Playwright — when to use POM, how to structure page objects, and when fixtures or helpers are a better fit.
.claude/skills/asymmetric-al-playwright-pom/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-11 | ✓→✗ | ▼ Worse | -8% | 0% |
| case-17 | ✓→✓ | ＝ Same ✓ | 12% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | -9% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 20% | 0% |
> Structure your test code for maintainability — know when POM helps and when simpler patterns win.
2 guides covering Page Object Model implementation and the decision framework for choosing between POM, fixtures, and helpers.
| Topic | Guide | |---|---| | Page Object Model patterns | page-object-model.md | | POM vs fixtures vs helpers | pom-vs-fixtures-vs-helpers.md |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-17 | pass→pass | 12,249 | 12,352 | +1% | 1 | 1 | 0% | 1,916 | 2,149 | +12% | 0 | 0 | — |
case-01 | pass→pass | 11,789 | 10,495 | -11% | 1 | 1 | 0% | 2,003 | 1,815 | -9% | 0 | 0 | — |
case-02 | pass→pass | 11,092 | 13,246 | +19% | 1 | 1 | 0% | 1,905 | 2,286 | +20% | 0 | 0 | — |
case-03 | pass→pass | 12,986 | 14,347 | +10% | 1 | 1 | 0% | 2,090 | 2,420 | +16% | 0 | 0 | — |
case-04 | pass→pass | 4,006 | 3,692 | -8% | 1 | 1 | 0% | 632 | 689 | +9% | 0 | 0 | — |
case-05 | pass→pass | 11,796 | 11,629 | -1% | 1 | 1 | 0% | 2,021 | 2,072 | +3% | 0 | 0 | — |
case-06 | pass→pass | 14,939 | 15,540 | +4% | 1 | 1 | 0% | 2,353 | 2,862 | +22% | 0 | 0 | — |
case-07 | fail→pass | 14,847 | 16,627 | +12% | 1 | 1 | 0% | 2,181 | 3,056 | +40% | 0 | 0 | — |
case-08 | pass→pass | 11,344 | 13,165 | +16% | 1 | 1 | 0% | 1,891 | 2,363 | +25% | 0 | 0 | — |
case-09 | pass→pass | 9,456 | 7,063 | -25% | 1 | 1 | 0% | 1,731 | 1,378 | -20% | 0 | 0 | — |
case-10 | pass→pass | 12,761 | 11,097 | -13% | 1 | 1 | 0% | 1,928 | 1,733 | -10% | 0 | 0 | — |
case-11 | pass→fail | 14,971 | 13,355 | -11% | 1 | 1 | 0% | 2,398 | 2,207 | -8% | 0 | 0 | — |
case-12 | pass→pass | 9,203 | 5,822 | -37% | 1 | 1 | 0% | 1,348 | 1,013 | -25% | 0 | 0 | — |
case-13 | pass→pass | 13,723 | 13,455 | -2% | 1 | 1 | 0% | 2,392 | 2,431 | +2% | 0 | 0 | — |
case-14 | pass→pass | 12,951 | 10,588 | -18% | 1 | 1 | 0% | 2,075 | 1,927 | -7% | 0 | 0 | — |
case-15 | pass→pass | 13,103 | 9,969 | -24% | 1 | 1 | 0% | 2,164 | 1,668 | -23% | 0 | 0 | — |
case-16 | pass→pass | 10,899 | 5,510 | -49% | 1 | 1 | 0% | 1,850 | 1,042 | -44% | 0 | 0 | — |
case-18 | pass→pass | 11,898 | 9,468 | -20% | 1 | 1 | 0% | 2,000 | 1,651 | -17% | 0 | 0 | — |
case-19 | pass→pass | 16,163 | 15,369 | -5% | 1 | 1 | 0% | 2,438 | 2,798 | +15% | 0 | 0 | — |
case-20 | pass→pass | 11,551 | 11,352 | -2% | 1 | 1 | 0% | 1,991 | 2,171 | +9% | 0 | 0 | — |
case-21 | pass→pass | 4,207 | 2,593 | -38% | 1 | 1 | 0% | 728 | 560 | -23% | 0 | 0 | — |
case-22 | pass→pass | 7,359 | 5,809 | -21% | 1 | 1 | 0% | 1,318 | 1,134 | -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. 22 cases were attempted. The headline lift of 0 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.
Other measured skills in the registry, with their headline benchmark lift.