Engineering
testability-scoring avatar

testability-scoring

AI-driven web testability assessment using 10 core principles. Evaluates observability, controllability, and stability via Playwright and Vibium to identify testing bottlenecks and improve quality readiness.

Introduction

The testability-scoring skill provides an automated, rigorous framework for evaluating the intrinsic testability of web applications. Designed for Quality Engineers and SDETs, this agent leverages 10 foundational principles—including Observability, Controllability, Algorithmic Simplicity, Transparency, Stability, Explainability, Unbugginess, Smallness, Decomposability, and Similarity—to quantify how effectively a system can be tested. By performing deep architectural and interface analysis, the agent helps teams transition from reactive bug fixing to proactive quality engineering. The assessment process is deeply integrated with modern browser automation, utilizing Playwright for legacy compatibility and Vibium for modern, high-speed accessibility tree analysis and signal collection.

  • Automated 10-principle scoring: Provides a comprehensive grade (A-F) based on weighted impact analysis of key testability pillars.

  • Dynamic Browser Engine orchestration: Utilizes qe-browser fleet skills and Vibium to perform real-time UI/UX, DOM, and network traffic evaluation.

  • Actionable Reporting: Generates visual HTML radar charts and structured JSON outputs that map technical metrics to specific improvement recommendations.

  • CI/CD integration: Native support for GitHub Actions and pipeline gating, ensuring that testability regressions are identified before deployment.

  • QX Partner synergy: Integrates with holistic Quality Experience (QX) analysis tools to correlate low testability scores with potential user experience and production stability risks.

  • Assessment Workflow: The skill navigates to target URLs, collects metrics on console errors, network request failures, element density, and semantic HTML structure.

  • Inputs/Outputs: Accepts target URLs or existing test suite configurations; outputs raw JSON data and comprehensive HTML reports stored in designated testability-results directories.

  • Operational Constraints: Requires access to a headless browser environment (qe-browser) and is best suited for web applications that have accessible front-end structures.

  • Pro-tip: Use this to prioritize refactoring efforts by identifying components that exhibit low Decomposability or poor Observability, effectively reducing long-term testing debt and flakiness.

Repository Stats

Stars
329
Forks
65
Open Issues
4
Language
TypeScript
Default Branch
main
Sync Status
Idle
Last Synced
Apr 29, 2026, 07:28 AM
View on GitHub