Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Verify a Skyvern deployment is working correctly by smoke-testing the backend API, frontend rendering, browser session provisioning, and workflow execution. Use when the user says 'is Skyvern working', 'test my deployment', 'verify the installation', 'smoke test', or needs to check that a self-hosted or local Skyvern instance is healthy.
.claude/skills/bilal140202-testing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -6% | 0% |
Comprehensive testing guidance covering:
This skill is automatically injected when working with:
/cc-best:dev — Implementation with teststdd-guide agent — Test-driven development guidancebuild-error-resolver agent — Fixing test failurestest_<feature>_<scenario>_<expected>| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 13,839 | 10,792 | -22% | 1 | 1 | 0% | 3,001 | 2,701 | -10% | 0 | 0 | — |
case-02 | fail→pass | 13,678 | 8,086 | -41% | 1 | 1 | 0% | 2,131 | 1,730 | -19% | 0 | 0 | — |
case-03 | fail→fail | 8,421 | 6,193 | -26% | 1 | 1 | 0% | 1,642 | 1,313 | -20% | 0 | 0 | — |
case-04 | fail→pass | 7,734 | 8,502 | +10% | 1 | 1 | 0% | 1,528 | 1,866 | +22% | 0 | 0 | — |
case-05 | pass→pass | 12,531 | 7,720 | -38% | 1 | 1 | 0% | 1,808 | 1,548 | -14% | 0 | 0 | — |
case-06 | fail→pass | 19,289 | 14,219 | -26% | 1 | 1 | 0% | 2,072 | 2,369 | +14% | 0 | 0 | — |
case-07 | pass→pass | 12,010 | 7,787 | -35% | 1 | 1 | 0% | 1,748 | 1,417 | -19% | 0 | 0 | — |
case-08 | fail→fail | 14,541 | 9,064 | -38% | 1 | 1 | 0% | 2,353 | 1,886 | -20% | 0 | 0 | — |
case-09 | fail→fail | 10,803 | 9,089 | -16% | 1 | 1 | 0% | 1,731 | 1,850 | +7% | 0 | 0 | — |
case-10 | fail→pass | 12,387 | 10,394 | -16% | 1 | 1 | 0% | 1,851 | 1,739 | -6% | 0 | 0 | — |
case-11 | pass→pass | 11,270 | 6,410 | -43% | 1 | 1 | 0% | 2,145 | 1,507 | -30% | 0 | 0 | — |
case-12 | pass→pass | 11,839 | 8,383 | -29% | 1 | 1 | 0% | 2,003 | 1,603 | -20% | 0 | 0 | — |
case-13 | pass→pass | 14,436 | 12,911 | -11% | 1 | 1 | 0% | 2,619 | 2,862 | +9% | 0 | 0 | — |
case-14 | pass→pass | 13,155 | 8,798 | -33% | 1 | 1 | 0% | 2,554 | 1,827 | -28% | 0 | 0 | — |
case-15 | pass→pass | 9,593 | 6,915 | -28% | 1 | 1 | 0% | 1,679 | 1,397 | -17% | 0 | 0 | — |
case-16 | pass→pass | 15,312 | 16,695 | +9% | 1 | 1 | 0% | 2,966 | 3,539 | +19% | 0 | 0 | — |
case-17 | pass→pass | 10,577 | 6,528 | -38% | 1 | 1 | 0% | 2,099 | 1,579 | -25% | 0 | 0 | — |
case-18 | pass→pass | 10,016 | 7,650 | -24% | 1 | 1 | 0% | 1,713 | 1,738 | +1% | 0 | 0 | — |
case-19 | fail→pass | 10,880 | 8,864 | -19% | 1 | 1 | 0% | 1,719 | 1,700 | -1% | 0 | 0 | — |
case-20 | pass→pass | 11,707 | 8,500 | -27% | 1 | 1 | 0% | 2,459 | 1,811 | -26% | 0 | 0 | — |
case-21 | pass→pass | 9,480 | 5,360 | -43% | 1 | 1 | 0% | 1,662 | 1,265 | -24% | 0 | 0 | — |
case-22 | pass→pass | 8,905 | 13,659 | +53% | 1 | 1 | 0% | 1,605 | 1,459 | -9% | 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 +27 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.