Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate failing tests for the TDD red phase to define expected behavior and edge cases.
.claude/skills/dokhacgiakhoa-tdd-workflows-tdd-red/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | 197% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 199% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 98% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 83% | 0% |
| case-15 | ✓→✓ | = Same ✓ | 189% | 0% |
Write comprehensive failing tests following TDD red phase principles.
Extended thinking: Generates failing tests that properly define expected behavior using test-automator agent.]
Generate failing tests using Task tool with subagent_type="unit-testing::test-automator".
"Generate comprehensive FAILING tests for: $ARGUMENTS
JavaScript/TypeScript (Jest/Vitest)
vi.fn() or jest.fn()@testing-library for React componentsfast-checkPython (pytest)
Go
t.Parallel() for parallel executiontestify/assert for cleaner assertionsRuby (RSpec)
let for lazy loading, let! for eagerAfter generation:
typescript// auth.service.test.ts describe('AuthService', () => { let authService: AuthService; let mockUserRepo: jest.Mocked<UserRepository>; beforeEach(() => { mockUserRepo = { findByEmail: jest.fn() } as any; authService = new AuthService(mockUserRepo); }); it('should_return_token_when_valid_credentials', async () => { const user = { id: '1', email: 'test@example.com', passwordHash: 'hashed' }; mockUserRepo.findByEmail.mockResolvedValue(user); const result = await authService.authenticate('test@example.com', 'pass'); expect(result.success).toBe(true); expect(result.token).toBeDefined(); }); it('should_fail_when_user_not_found', async () => { mockUserRepo.findByEmail.mockResolvedValue(null); const result = await authService.authenticate('none@example.com', 'pass'); expect(result.success).toBe(false); expect(result.error).toBe('INVALID_CREDENTIALS'); }); });
Test requirements: $ARGUMENTS
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 29,486 | 31,748 | +8% | 1 | 1 | 0% | 4,168 | 6,443 | +55% | 0 | 0 | — |
case-02 | fail→fail | 26,231 | 38,887 | +48% | 1 | 1 | 0% | 4,540 | 6,665 | +47% | 0 | 0 | — |
case-03 | fail→fail | 55,400 | 55,762 | +1% | 1 | 1 | 0% | 8,266 | 9,348 | +13% | 0 | 0 | — |
case-04 | fail→fail | 27,265 | 48,270 | +77% | 1 | 1 | 0% | 4,618 | 6,271 | +36% | 0 | 0 | — |
case-05 | fail→fail | 25,882 | 20,475 | -21% | 1 | 1 | 0% | 3,672 | 1,792 | -51% | 0 | 0 | — |
case-06 | fail→fail | 14,531 | 40,110 | +176% | 1 | 1 | 0% | 1,875 | 4,669 | +149% | 0 | 0 | — |
case-07 | fail→fail | 16,209 | 21,395 | +32% | 1 | 1 | 0% | 2,154 | 1,771 | -18% | 0 | 0 | — |
case-08 | fail→fail | 19,204 | 23,591 | +23% | 1 | 1 | 0% | 2,832 | 2,011 | -29% | 0 | 0 | — |
case-09 | fail→fail | 12,251 | 14,384 | +17% | 1 | 1 | 0% | 2,516 | 1,837 | -27% | 0 | 0 | — |
case-10 | fail→fail | 12,777 | 35,964 | +181% | 1 | 1 | 0% | 1,450 | 4,406 | +204% | 0 | 0 | — |
case-11 | fail→fail | 24,023 | 27,147 | +13% | 1 | 1 | 0% | 3,985 | 2,070 | -48% | 0 | 0 | — |
case-12 | fail→pass | 14,232 | 35,845 | +152% | 1 | 1 | 0% | 1,859 | 5,526 | +197% | 0 | 0 | — |
case-13 | fail→fail | 14,800 | 23,802 | +61% | 1 | 1 | 0% | 1,934 | 1,975 | +2% | 0 | 0 | — |
case-14 | fail→fail | 16,679 | 26,814 | +61% | 1 | 1 | 0% | 2,338 | 1,814 | -22% | 0 | 0 | — |
case-15 | pass→pass | 21,088 | 51,766 | +145% | 1 | 1 | 0% | 2,404 | 6,943 | +189% | 0 | 0 | — |
case-16 | fail→fail | 19,044 | 18,270 | -4% | 1 | 1 | 0% | 2,350 | 3,701 | +57% | 0 | 0 | — |
case-17 | fail→fail | 19,255 | 22,909 | +19% | 1 | 1 | 0% | 2,958 | 4,688 | +58% | 0 | 0 | — |
case-18 | fail→pass | 17,014 | 30,665 | +80% | 1 | 1 | 0% | 1,800 | 5,384 | +199% | 0 | 0 | — |
case-19 | pass→pass | 19,113 | 48,038 | +151% | 1 | 1 | 0% | 2,801 | 5,818 | +108% | 0 | 0 | — |
case-20 | pass→fail | 20,962 | 43,304 | +107% | 1 | 1 | 0% | 2,635 | 4,829 | +83% | 0 | 0 | — |
case-21 | pass→pass | 22,878 | 27,837 | +22% | 1 | 1 | 0% | 3,392 | 5,285 | +56% | 0 | 0 | — |
case-22 | fail→pass | 16,813 | 27,291 | +62% | 1 | 1 | 0% | 2,319 | 4,594 | +98% | 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, and 14 counted toward the lift figure. The other 8 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +9 percentage points is the difference between those two pass rates over the 14 comparable cases. 2 cases got worse with the skill loaded, and they are 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.