Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes. Use when writing QA test cases, creating test plans, defining acceptance tests, or preparing for feature validation.
.claude/skills/phuryn-test-scenarios/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 24 |
| gemini-3.1-pro-preview | 100% | 2 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | -15% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 18% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 1% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 12% | 0% |
Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step test actions, and expected outcomes.
Use when: Writing QA test cases, creating test plans, defining acceptance test scenarios, or validating user story implementations.
Arguments:
$PRODUCT: The product or system name$USER_STORY: The user story to test (title and acceptance criteria)$CONTEXT: Additional testing context or constraintsTest Scenario: Clear scenario name]
Test Objective: What this test validates]
Starting Conditions:
User Role: Who performs the test]
Test Steps:
Expected Outcomes:
Test Scenario: View Recently Viewed Products on Product Page
Test Objective: Verify that the 'Recently viewed' section displays correctly and excludes the current product.
Starting Conditions:
User Role: Online Shopper
Test Steps:
Expected Outcomes:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 20,826 | 14,446 | -31% | 1 | 1 | 0% | 3,932 | 3,323 | -15% | 0 | 0 | — |
case-02 | pass→pass | 21,149 | 16,563 | -22% | 1 | 1 | 0% | 3,395 | 4,009 | +18% | 0 | 0 | — |
case-03 | pass→pass | 26,057 | 18,468 | -29% | 1 | 1 | 0% | 4,107 | 4,155 | +1% | 0 | 0 | — |
case-04 | pass→pass | 14,553 | 12,746 | -12% | 1 | 1 | 0% | 2,902 | 3,255 | +12% | 0 | 0 | — |
case-05 | pass→pass | 16,583 | 17,872 | +8% | 1 | 1 | 0% | 3,341 | 3,248 | -3% | 0 | 0 | — |
case-06 | fail→pass | 17,718 | 13,201 | -25% | 1 | 1 | 0% | 3,378 | 3,123 | -8% | 0 | 0 | — |
case-07 | pass→pass | 16,499 | 12,486 | -24% | 1 | 1 | 0% | 3,015 | 3,063 | +2% | 0 | 0 | — |
case-08 | pass→pass | 22,196 | 22,190 | -0% | 1 | 1 | 0% | 3,000 | 3,668 | +22% | 0 | 0 | — |
case-09 | pass→pass | 18,042 | 16,813 | -7% | 1 | 1 | 0% | 2,794 | 3,360 | +20% | 0 | 0 | — |
case-10 | pass→pass | 15,924 | 20,864 | +31% | 1 | 1 | 0% | 2,901 | 3,695 | +27% | 0 | 0 | — |
case-11 | pass→pass | 31,337 | 13,823 | -56% | 1 | 1 | 0% | 2,883 | 3,485 | +21% | 0 | 0 | — |
case-12 | pass→pass | 15,907 | 15,834 | -0% | 1 | 1 | 0% | 2,943 | 3,946 | +34% | 0 | 0 | — |
case-13 | pass→pass | 13,757 | 15,998 | +16% | 1 | 1 | 0% | 2,597 | 3,520 | +36% | 0 | 0 | — |
case-14 | pass→pass | 17,097 | 23,387 | +37% | 1 | 1 | 0% | 3,153 | 3,536 | +12% | 0 | 0 | — |
case-15 | pass→pass | 15,909 | 17,337 | +9% | 1 | 1 | 0% | 2,796 | 3,752 | +34% | 0 | 0 | — |
case-16 | pass→pass | 24,200 | 18,136 | -25% | 1 | 1 | 0% | 3,559 | 3,417 | -4% | 0 | 0 | — |
case-17 | pass→pass | 15,925 | 16,059 | +1% | 1 | 1 | 0% | 2,795 | 3,441 | +23% | 0 | 0 | — |
case-18 | pass→pass | 16,222 | 17,001 | +5% | 1 | 1 | 0% | 3,103 | 3,820 | +23% | 0 | 0 | — |
case-19 | pass→pass | 15,321 | 18,421 | +20% | 1 | 1 | 0% | 2,821 | 3,338 | +18% | 0 | 0 | — |
case-20 | pass→pass | 7,932 | 10,116 | +28% | 1 | 1 | 0% | 2,037 | 2,408 | +18% | 0 | 0 | — |
case-21 | pass→pass | 13,489 | 12,422 | -8% | 1 | 1 | 0% | 2,442 | 3,033 | +24% | 0 | 0 | — |
case-22 | pass→pass | 15,503 | 28,550 | +84% | 1 | 1 | 0% | 2,759 | 5,005 | +81% | 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 +5 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.