Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder
.claude/skills/agent-implementer-sparc-coder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | — | — |
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-13 | ✓→✓ | = Same ✓ | — | — |
| case-17 | ✓→✓ | = Same ✓ | — | — |
| case-15 | ✗→✗ | = Same ✗ | — | — |
This agent specializes in the implementation phases of SPARC methodology, focusing on transforming specifications and designs into high-quality, tested code.
javascript[Parallel Test Creation]: - Write("tests$unit$auth.test.js", authTestSuite) - Write("tests$unit$user.test.js", userTestSuite) - Write("tests$integration$api.test.js", apiTestSuite) - Bash("npm test") // Verify all fail
javascript[Parallel Implementation]: - Write("src$auth$service.js", authImplementation) - Write("src$user$model.js", userModel) - Write("src$api$routes.js", apiRoutes) - Bash("npm test") // Verify all pass
javascript[Parallel Refactoring]: - MultiEdit("src$auth$service.js", optimizations) - MultiEdit("src$user$model.js", improvements) - Edit("src$api$routes.js", cleanup) - Bash("npm test && npm run lint")
javascript// Pattern: Dependency Injection + Error Handling class AuthService { constructor(userRepo, tokenService, logger) { this.userRepo = userRepo; this.tokenService = tokenService; this.logger = logger; } async authenticate(credentials) { try { // Implementation } catch (error) { this.logger.error('Authentication failed', error); throw new AuthError('Invalid credentials'); } } }
javascript// Pattern: Validation + Error Handling router.post('$auth$login', validateRequest(loginSchema), rateLimiter, async (req, res, next) => { try { const result = await authService.authenticate(req.body); res.json({ success: true, data: result }); } catch (error) { next(error); } } );
javascript// Pattern: Comprehensive Test Coverage describe('AuthService', () => { let authService; beforeEach(() => { // Setup with mocks }); describe('authenticate', () => { it('should authenticate valid user', async () => { // Arrange, Act, Assert }); it('should handle invalid credentials', async () => { // Error case testing }); }); });
src/
├── features/ # Feature-based structure
│ ├── auth/
│ │ ├── service.js
│ │ ├── controller.js
│ │ └── auth.test.js
│ └── user/
├── shared/ # Shared utilities
└── infrastructure/ # Technical concernsjavascript// Fallback mechanisms try { return await primaryService.getData(); } catch (error) { logger.warn('Primary service failed, using cache'); return await cacheService.getData(); }
javascript// Retry with exponential backoff async function retryOperation(fn, maxRetries = 3) { for (let i = 0; i < maxRetries; i++) { try { return await fn(); } catch (error) { if (i === maxRetries - 1) throw error; await sleep(Math.pow(2, i) * 1000); } } }
javascript/** * Authenticates user credentials and returns access token * @param {Object} credentials - User credentials * @param {string} credentials.email - User email * @param {string} credentials.password - User password * @returns {Promise<Object>} Authentication result with token * @throws {AuthError} When credentials are invalid */
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
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 +9 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.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.