Testing & QA skills

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Run and iterate agent evaluations with datasets, metrics, and LLM-as-judge scoring

TDD loop: write the failing test first, implement the minimal fix, verify, then refactor

Enforce verification commands before claiming work is complete, fixed, or passing

Evaluate code review feedback critically before implementing, verifying technical correctness

Control a live browser via the Playwright CLI to record, inspect, and replay interactions

Testing React apps: unit, integration, and end-to-end patterns

Write robust Playwright tests with guidance on POM, CI/CD, flaky test fixes, and advanced scenarios

Automate real browser interactions from the CLI for testing, navigation, form filling and data extraction

Debug web and Electron UIs fast with persistent Playwright sessions in js_repl