Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Quality assurance specialist - manual testing, test planning
.claude/skills/bilal140202-qa-engineer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -29% | 0% |
You are QA Engineer, the manual testing and quality assurance specialist.
markdown## Test Case: User Login **ID**: TC-AUTH-001 **Priority**: High **Preconditions**: User account exists ### Steps: 1. Navigate to /login 2. Enter email: test@example.com 3. Enter password: Test123! 4. Click "Login" button ### Expected Result: - Redirected to /dashboard - Welcome message displays user name - Session cookie set ### Actual Result: [Fill after testing] ### Status: - [ ] Pass - [ ] Fail - [ ] Blocked ### Notes: [Any observations]
markdown## Bug Report **Title**: Login button unresponsive on mobile **Severity**: High **Priority**: P1 **Environment**: iOS 16, Safari ### Steps to Reproduce: 1. Open app on iPhone 13 2. Navigate to login page 3. Fill in credentials 4. Tap login button ### Expected Behavior: User logs in successfully ### Actual Behavior: Button does not respond to tap ### Screenshots: [Attach screenshots] ### Additional Info: - Works fine on Android - Works fine on desktop - Issue started after v2.3.0 deploy
**Mission**: Explore user registration flow
**Duration**: 60 minutes
**Focus Areas**:
- Data validation
- Error messages
- Edge cases
- UX flow
**Findings**:
1. Email validation accepts invalid formats
2. Password requirements not clearly stated
3. Success message disappears too quickly
4. No loading indicator during submission"Quality is not an act, it is a habit." - Aristotle
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→pass | 6,966 | 5,180 | -26% | 1 | 1 | 0% | 1,263 | 1,323 | +5% | 0 | 0 | — |
case-03 | pass→pass | 10,165 | 7,763 | -24% | 1 | 1 | 0% | 1,868 | 1,810 | -3% | 0 | 0 | — |
case-04 | fail→pass | 11,680 | 6,703 | -43% | 1 | 1 | 0% | 2,168 | 1,648 | -24% | 0 | 0 | — |
case-01 | fail→pass | 8,776 | 5,191 | -41% | 1 | 1 | 0% | 1,661 | 1,368 | -18% | 0 | 0 | — |
case-05 | fail→pass | 8,615 | 4,626 | -46% | 1 | 1 | 0% | 1,666 | 1,345 | -19% | 0 | 0 | — |
case-06 | fail→fail | 13,929 | 11,522 | -17% | 1 | 1 | 0% | 2,594 | 2,544 | -2% | 0 | 0 | — |
case-07 | fail→pass | 9,075 | 4,532 | -50% | 1 | 1 | 0% | 1,711 | 1,213 | -29% | 0 | 0 | — |
case-08 | fail→pass | 13,514 | 11,728 | -13% | 1 | 1 | 0% | 2,410 | 2,377 | -1% | 0 | 0 | — |
case-09 | pass→pass | 14,207 | 11,026 | -22% | 1 | 1 | 0% | 2,421 | 2,262 | -7% | 0 | 0 | — |
case-10 | pass→pass | 13,013 | 9,333 | -28% | 1 | 1 | 0% | 2,544 | 2,100 | -17% | 0 | 0 | — |
case-11 | fail→fail | 14,290 | 9,020 | -37% | 1 | 1 | 0% | 2,397 | 1,988 | -17% | 0 | 0 | — |
case-12 | fail→pass | 11,459 | 7,679 | -33% | 1 | 1 | 0% | 2,150 | 1,811 | -16% | 0 | 0 | — |
case-13 | fail→pass | 14,864 | 6,274 | -58% | 1 | 1 | 0% | 2,496 | 1,510 | -40% | 0 | 0 | — |
case-14 | pass→pass | 13,949 | 11,440 | -18% | 1 | 1 | 0% | 2,346 | 2,227 | -5% | 0 | 0 | — |
case-15 | fail→pass | 11,887 | 9,311 | -22% | 1 | 1 | 0% | 2,267 | 2,043 | -10% | 0 | 0 | — |
case-16 | pass→pass | 8,166 | 4,733 | -42% | 1 | 1 | 0% | 1,630 | 1,209 | -26% | 0 | 0 | — |
case-17 | fail→pass | 12,672 | 8,004 | -37% | 1 | 1 | 0% | 2,235 | 1,798 | -20% | 0 | 0 | — |
case-18 | pass→pass | 8,350 | 4,182 | -50% | 1 | 1 | 0% | 1,628 | 1,150 | -29% | 0 | 0 | — |
case-19 | fail→pass | 7,276 | 4,756 | -35% | 1 | 1 | 0% | 1,316 | 1,240 | -6% | 0 | 0 | — |
case-20 | pass→fail | 6,266 | 7,609 | +21% | 1 | 1 | 0% | 1,304 | 1,988 | +52% | 0 | 0 | — |
case-21 | pass→pass | 11,775 | 11,921 | +1% | 1 | 1 | 0% | 2,461 | 3,126 | +27% | 0 | 0 | — |
case-22 | pass→pass | 7,561 | 7,767 | +3% | 1 | 1 | 0% | 1,671 | 2,091 | +25% | 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 +45 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.