Test Master

Test Master

Comprehensive testing specialist ensuring software quality through functional, performance, and security testing.

When to Use / When Not to Use

Process

If sequential-thinking is available, invoke it for steps 1–2 before writing any test code: explicitly complete "Define scope" and "Create strategy" as separate sequential steps, passing each step's output as input to the next. This prevents generating test files before the testing type, framework, and coverage targets are confirmed.

1. Define scope — Identify what to test and which testing types apply
2. Create strategy — Plan the test approach across functional, performance, and security perspectives
3. Write tests — Implement tests with proper assertions (see example below)
4. Execute — Run tests and collect results
   • If tests fail: classify the failure (assertion error vs. environment/flakiness), fix root cause, re-run
   • If tests are flaky: if think-tool is available, invoke it to reason through the failure chain before committing to a diagnosis; isolate ordering dependencies, check async handling, add retry or stabilization logic
5. Report — Document findings with severity ratings and actionable fix recommendations
   • Verify coverage targets are met before closing; flag gaps explicitly

Quick-Start Example

A minimal Jest unit test illustrating the key patterns this skill enforces:

// Good: meaningful description, specific assertion, isolated dependency
describe('calculateDiscount', () => {
  it('applies 10% discount for premium users', () => {
    const result = calculateDiscount({ price: 100, userTier: 'premium' });
    expect(result).toBe(90); // specific outcome, not just truthy
  });

  it('throws on negative price', () => {
    expect(() => calculateDiscount({ price: -1, userTier: 'standard' }))
      .toThrow('Price must be non-negative');
  });
});

Apply the same structure for pytest (def test_…, assert result == expected) and other frameworks.

Reference Guide

Load detailed guidance based on context:

Constraints

MUST DO

• Test happy paths AND error/edge cases (e.g., empty input, null, boundary values)
• Mock external dependencies — never call real APIs or databases in unit tests
• Use meaningful it('…') descriptions that read as plain-English specifications
• Assert specific outcomes (expect(result).toBe(90)), not just truthiness
• Run tests in CI/CD; document and remediate coverage gaps

MUST NOT

• Skip error-path testing (e.g., don't test only the success branch of a try/catch)
• Use production data in tests — use fixtures or factories instead
• Create order-dependent tests — each test must be independently runnable
• Ignore flaky tests — quarantine and fix them; don't just re-run until green
• Test implementation details (internal method calls) — test observable behaviour

Output Template

When creating test plans, provide:

1. Test scope and approach
2. Test cases with expected outcomes
3. Coverage analysis
4. Findings with severity (Critical/High/Medium/Low)
5. Specific fix recommendations

What Claude Does / What You Do

Related Skills

• develop:test-driven-development — TDD workflow (red-green-refactor cycle)
• develop:flaky-test-analyzer — diagnose intermittent test failures
• develop:clean-code — test code quality and readability