Find the perfect skill

Testing

Run systematic QA on a web application: find bugs, commit atomic fixes, and re-verify. Supports quick, standard, and exhaustive tiers, producing a health score report.

Testing

Retroactively audit an executed AI phase's evaluation coverage. Scores each dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation plan.

Testing

Verifies if a Home Assistant integration complies with a specific quality scale rule (e.g., config-flow, unique-id). Analyzes code, fetches rule docs, and reports issues.

Testing

Master pytest mocking strategy: when to use autospec=True vs manual mocks, AsyncMock patterns for async code, and what should never be mocked.

Testing

Use Hypothesis for property-based testing to automatically generate test cases, find edge cases, and write robust tests with minimal example shrinking.

Testing

Expert AI code review specialist combining static analysis, pattern recognition, and DevOps to identify bugs, vulnerabilities, and performance issues.

Testing

Run the E2E QA test suite against the live application using Playwright MCP and nREPL. Use when testing the app end-to-end.

Testing

Audit only recently changed code for regressions and new bugs. Dispatches to specialized subsystem audit skills for fast feedback.

Testing

Run QA validation on a pull request: boots local environment, tests acceptance criteria, and optionally posts the report as a PR comment.

Testing

Run QA validation on a pull request: boots the local environment, tests acceptance criteria, and optionally posts the report as a PR comment. Standalone entry point for the qa-engineer agent.

Testing

Systematically test a web application and fix bugs with atomic commits. Supports three tiers: Quick, Standard, Exhaustive.

Testing

Use this skill to run performance benchmarks, compare language implementations, or test compute-average-income implementations.