Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Implement the minimal code needed to make failing tests pass in the TDD green phase.
.claude/skills/dokhacgiakhoa-tdd-workflows-tdd-green/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 1% | 0% |
def product_list(request): products = Product.objects.all() return JsonResponse({'products': list(products.values())})
class ProductListView(View): def get(self, request): products = Product.objects.all() return JsonResponse({'products': list(products.values())})
class ProductListView(ListView): model = Product context_object_name = 'products'
### Express Patterns
**Inline → Middleware → Service Layer:**// Green Phase: Inline logic app.post('/api/users', (req, res) => { const user = { id: Date.now(), ...req.body }; users.push(user); res.json(user); });
// Refactor: Extract middleware app.post('/api/users', validateUser, (req, res) => { const user = userService.create(req.body); res.json(user); });
// Refactor: Full layering app.post('/api/users', validateUser, asyncHandler(userController.create) );
## Use this skill when
- Moving from red to green in a TDD cycle
- Implementing minimal behavior to satisfy tests
- You want to keep implementation intentionally simple
## Do not use this skill when
- You are refactoring for design or performance
- Tests are already passing and you need new requirements
- You need a full architectural redesign
## Instructions
1. Review failing tests and identify the smallest fix.
2. Implement the minimal change to pass the next test.
3. Run tests after each change to confirm progress.
4. Record shortcuts or debt for the refactor phase.
## Safety
- Avoid bypassing tests to make them pass.
- Keep changes scoped to the failing behavior only.
## Resources
- `resources/implementation-playbook.md` for detailed patterns and examples.
## 🧠 Knowledge Modules (Fractal Skills)
### 1. [implementation-playbook](./sub-skills/implementation-playbook.md)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,048 | 11,108 | -8% | 1 | 1 | 0% | 2,294 | 1,632 | -29% | 0 | 0 | — |
case-02 | pass→pass | 12,867 | 6,394 | -50% | 1 | 1 | 0% | 1,389 | 1,637 | +18% | 0 | 0 | — |
case-03 | fail→pass | 12,541 | 11,482 | -8% | 1 | 1 | 0% | 2,014 | 1,534 | -24% | 0 | 0 | — |
case-04 | pass→pass | 9,440 | 4,330 | -54% | 1 | 1 | 0% | 730 | 1,198 | +64% | 0 | 0 | — |
case-05 | fail→pass | 17,531 | 13,263 | -24% | 1 | 1 | 0% | 1,953 | 1,861 | -5% | 0 | 0 | — |
case-06 | pass→pass | 6,717 | 5,284 | -21% | 1 | 1 | 0% | 1,081 | 1,313 | +21% | 0 | 0 | — |
case-07 | pass→pass | 13,057 | 6,506 | -50% | 1 | 1 | 0% | 1,464 | 1,653 | +13% | 0 | 0 | — |
case-08 | pass→pass | 11,288 | 9,554 | -15% | 1 | 1 | 0% | 976 | 1,231 | +26% | 0 | 0 | — |
case-09 | fail→pass | 18,120 | 6,177 | -66% | 1 | 1 | 0% | 2,049 | 1,483 | -28% | 0 | 0 | — |
case-10 | pass→pass | 16,024 | 6,724 | -58% | 1 | 1 | 0% | 1,825 | 1,652 | -9% | 0 | 0 | — |
case-11 | pass→pass | 16,074 | 11,038 | -31% | 1 | 1 | 0% | 1,850 | 1,478 | -20% | 0 | 0 | — |
case-12 | pass→pass | 8,266 | 5,886 | -29% | 1 | 1 | 0% | 1,526 | 1,611 | +6% | 0 | 0 | — |
case-13 | pass→pass | 13,140 | 6,265 | -52% | 1 | 1 | 0% | 1,386 | 1,480 | +7% | 0 | 0 | — |
case-14 | fail→pass | 11,728 | 5,174 | -56% | 1 | 1 | 0% | 1,385 | 1,392 | +1% | 0 | 0 | — |
case-15 | fail→pass | 12,609 | 10,877 | -14% | 1 | 1 | 0% | 2,327 | 1,499 | -36% | 0 | 0 | — |
case-16 | fail→pass | 10,052 | 9,845 | -2% | 1 | 1 | 0% | 1,664 | 1,296 | -22% | 0 | 0 | — |
case-17 | pass→pass | 18,150 | 9,862 | -46% | 1 | 1 | 0% | 2,134 | 1,353 | -37% | 0 | 0 | — |
case-18 | pass→pass | 10,550 | 9,840 | -7% | 1 | 1 | 0% | 1,782 | 1,357 | -24% | 0 | 0 | — |
case-19 | fail→pass | 11,306 | 10,110 | -11% | 1 | 1 | 0% | 2,251 | 1,394 | -38% | 0 | 0 | — |
case-20 | pass→pass | 16,035 | 5,741 | -64% | 1 | 1 | 0% | 1,953 | 1,488 | -24% | 0 | 0 | — |
case-21 | pass→pass | 16,944 | 12,384 | -27% | 1 | 1 | 0% | 2,073 | 1,713 | -17% | 0 | 0 | — |
case-22 | fail→fail | 9,533 | 8,223 | -14% | 1 | 1 | 0% | 1,555 | 1,789 | +15% | 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 +36 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.