UI Test Wait Strategy Review Skill: Replace Sleeps with Observable Conditions
Replace fixed sleeps with observable UI conditions by reviewing polling, timeout evidence, retries, and asynchronous state.
#AI Testing
How to Test a Chatbot: Five Quality Dimensions and a Practical QA Checklist
A bookstore chatbot example for testing boundaries, security, accuracy, style, and truthfulness, with an automation and regression approach.
Timeout Testing Skill: Connect Budgets, Cancellation, Feedback, and Retries
A bilingual guide to reviewing timeout budgets, cancellation propagation, downstream boundaries, user feedback, and retry interaction.
UI Test Strategy Skill: Map Journeys, States, Platforms, and Risk Before Automation
A bilingual guide to forming evidence-bounded UI test strategy candidates from journeys, states, platforms, accessibility, and defects.
How to Build an AI Testing Strategy: Five Shifts Toward Evidence-Based Confidence
A practical guide to synthetic personas, calibrated LLM judges, human oversight, golden datasets, production tracing, and a four-week AI testing pilot.
Skill Benchmarking: Is the Skill Actually Better Than the Baseline?
Use a controlled with-Skill versus without-Skill comparison to determine whether an Agent Skill creates real uplift instead of treating one PASS as effectiveness evidence.
Retry Testing Skill: Prove Backoff and Idempotency Before Duplicates Multiply
A bilingual guide to retry-testing analysis covering triggers, backoff, idempotency, retry limits, and duplicate side effects.
Test Maintenance Cost Analysis Skill: Make Repair Effort and Flaky Cost Visible
Estimate test maintenance costs from change frequency, repair effort, flaky reruns, ownership, maintainability, and evidence-backed confidence.
Everyday AI Coding for Testers: Skills, Guardrails, and a Human-Reviewed Workflow
A practical guide to focused AI Skills, plugins, MCP, staged QA automation, evaluation, ROI, and organizational governance.
Designing Skill Evals: From Success Criteria to Evidence
Turn Skill success criteria into executable Eval Cases, choose a suitable judge, and preserve run metadata, traces, artifacts, and limitations.
Mock Quality Review Skill: Keep test doubles useful without making the system look healthier than it is
Mock Quality Review field guide: inspect contract fidelity, realism, failure modes, drift, state, and ownership of test doubles.
Test Suite Health Analysis Skill: Diagnose Flakiness, Duplication, and Quarantine Debt
Diagnose test-suite health from run history, duration, flakiness, duplication, isolation, quarantine, maintenance, and defect evidence.