Quality

Eval Injection Test contains eval patterns and hidden instructions for testing whether an agent will execute injected code. Use it in a controlled environment to evaluate skill security.

Hypothesis-Driven Debugging applies the scientific method to debugging by helping users form specific, testable hypotheses, design targeted experiments, and systematically confirm or reject theories to find root causes when debugging errors or troubleshooting bugs.

Parallel Investigation coordinates parallel debugging threads to explore multiple hypotheses across different system areas simultaneously. Use it when debugging production incidents, slow API performance, multi-system integration failures, or complex bugs where serial troubleshooting is too slow.

Red-Green-Refactor guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, or do test-driven development.

Root Cause Analysis performs structured investigation to identify the true source of bugs, errors, and unexpected behavior. Use when a bug is reported and you need to debug, troubleshoot, or find why something is broken.

Structured Code Review performs a five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance. Use it when asked for code review, PR feedback, or pull request review, with categorized feedback (Blocker, Major, Minor, Nit) and actionable suggestions.

Test Patterns applies proven testing patterns like Arrange-Act-Assert, Given-When-Then, Test Data Builders, Object Mother, parameterized tests, fixtures, spies, and test doubles to help write maintainable, reliable, and readable test suites. Use when writing unit, integration, or end-to-end tests, applying TDD/BDD, or working with mocks, stubs, spies, or fakes.

Testing Anti-Patterns reviews test code to identify and fix common testing anti-patterns including flaky tests, over-mocking, brittle assertions, test interdependency, and hidden test logic. Use it when reviewing test code, debugging unreliable tests, or addressing test smells.

Trace and Isolate applies systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code. Use it when errors have unclear causes, regressions appear between commits, or you need to narrow down a faulty component.

TypeScript Best Practices enforces modern TypeScript patterns and best practices when writing new code, reviewing pull requests, or refactoring JavaScript to TypeScript. It ensures const usage, explicit return types, interface preference, and avoidance of any, var, and @ts-ignore.

Verification Gates creates explicit validation checkpoints between project phases to catch errors early and ensure quality before proceeding. Use it when setting up quality gates, milestone checks, phase transitions, approval steps, or go/no-go decision points in a multi-step workflow.

Minutes Lint checks meeting records for decision conflicts and stale commitments using a consistency command, then formats the results as readable markdown. Use it when asked to lint meetings, check for contradictions, or audit decision history.