systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Python testing best practices with pytest. Covers unit, integration, async tests, mocking, fixtures. Triggers: "write tests", "add tests", "test coverage", "pytest", "tests"
ๆฃๆฅAcceptance Criteriaๆ ผๅผๅๅฎๆดๆง๏ผ้ช่ฏๆฏๅฆ็ฌฆๅGiven-When-Then็ปๆใ่ฆ็ๆญฃๅธธๆต็จ/่พน็ๆกไปถ/ๅผๅธธๅบๆฏใ้ๅๅจไธบUser Story็ผๅACๅใๅๅคๆต่ฏ็จไพๅไฝฟ็จ๏ผๅฝ้่ฆ้ชๆถAC่ดจ้ๆถใๅธฎๅฉไธ็ๆBDD็PM/BA็กฎไฟACๆ็กฎใๅฏๆต่ฏใ่ฆ็ๅฎๆด๏ผ้ฟๅ ้ๆผๅ ณ้ฎๅบๆฏใ
Autonomously performs the TDD loop (Red-Green-Refactor) for a single plan item.
Write the test first, watch it fail, write minimal code to pass
Execute test_cases.json against educational demos. Systematic testing via Chrome E2E. Single tab, sequential agents. Output: agent_X_tests.json with PASS/FAIL/PARTIAL results. Captures screenshots and identifies bugs/blockers.
Run test_local.sh and analyze results including PNG outputs, execution logs, memory usage CSV, and performance metrics. Identifies issues like missing data points, memory spikes, or performance problems. Use after code changes to verify functionality.
Provides unit testing patterns for .NET applications using EF Core In-Memory Provider, AAA structure, test data helpers, and TDD workflows. Use when writing unit tests for services, repositories, or domain logic.
Test writing patterns and TDD workflows. Use when writing tests, creating mocks, following TDD, or debugging test failures.
Comprehensive pytest testing strategies with fixtures, mocking, and TDD patterns. WHEN: Writing pytest tests, creating fixtures, mocking with unittest.mock/pytest-mock, implementing TDD, setting up test configuration (conftest.py, pytest.ini). WHEN NOT: JavaScript tests (use Jest), PHP tests (use PHPUnit), running existing tests without modification.
Use immediately when user mentions: "ใในใ", "test", "BDD", "feature", "ใใฃใผใใฃใผ", "scenario", "ใทใใชใช", "Given", "When", "Then", "ใซใใฌใใธ", "coverage", "pytest-bdd", "Gherkin". MUST USE this skill for: - Creating BDD feature files with Gherkin syntax - Implementing step definitions with pytest-bdd - Designing test scenarios and fixtures - Any work in tests/ directory
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
End-to-end testing with Playwright. Use when writing E2E tests, implementing page objects, setting up test fixtures, handling authentication in tests, adding visual regression testing, or configuring E2E tests for CI. Covers when to use E2E vs integration tests, critical path identification, page object pattern, test isolation, and CI considerations.
Write comprehensive test coverage across unit, integration, regression, end-to-end, and manual tests. Watch for deprecation warnings in test output and address them immediately. Use when writing tests, implementing features, or before creating pull requests.
Debug EUX/EESSI mock issues in melosys E2E tests. Use when: - E2E tests fail with 404 errors from /eux/... endpoints - melosys-api logs show "Kall mot eessi feilet" errors - melosys-eessi logs show NotFoundException for eux endpoints - Adding new EESSI/EUX functionality that requires mock support - Tracing data flow: melosys-api โ melosys-eessi โ melosys-mock
Review pages visually and test accessibility using agent-browser CLI
Test DE variants, run integration tests, and benchmark performance. Use for testing variants (best, rand, pbest, current-to-best), integration tests across store backends, and DE algorithm benchmarks.
ๆฃๆฅๆฏไธชUSๆฏๅฆๆๅฏนๅบ็VS๏ผ็ๆ่ฆ็็ๆฅๅๅไฟฎๅคๅปบ่ฎฎใๅฝ่ฎพ่ฎกๆๆกฃๅๅปบๅใCONSTRAINT้ชๆถๅไฝฟ็จ๏ผ้ฟๅ USโVS่ฆ็็<100%ๅฏผ่ด้ชๆถๅคฑ่ดฅใ
Maintain BDD-style Playwright E2E tests and a human-readable scenario catalog for the Progress Tracker repo. Use when adding/updating scenarios in e2e/SCENARIOS.md, implementing them in e2e/bdd.spec.ts, or fixing flaky selectors across desktop + mobile Playwright projects.