Auto-invoked when Claude works on testing tasks — test generation, coverage analysis, or test strategy. Provides test pyramid guidance, AAA structure patterns, naming conventions, mocking guidelines, and coverage targets (>80% overall, >95% critical paths, 100% new code).
From cortexnpx claudepluginhub anthropics/claude-plugins-community --plugin cortexThis skill uses the workspace's default tool permissions.
Dispatches code-reviewer subagent to evaluate code changes via git SHAs after tasks, major features, or before merging, with focused context on implementation and requirements.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Processes code review feedback technically: verify suggestions against codebase, clarify unclear items, push back if questionable, implement after evaluation—not blind agreement.
Best practices for test generation and quality.
/ E2E \ ← Few, slow, high confidence
/----------\
/ Integration\ ← Moderate, medium speed
/--------------\
/ Unit Tests \ ← Many, fast, focused
/==================\
should [expected behavior] when [condition]
// Arrange — Set up test data and mocks
// Act — Execute the function under test
// Assert — Verify the result