harness-evaluator

You can automate QA scoring by running Playwright-based browser tests to evaluate web applications across Design, Originality, Craft, and Functionality. The process generates a structured feedback.md with actionable improvement recommendations and issue reproduction steps.

Automated web testing evaluates UI quality across four dimensions: Design, Originality, Craft, and Functionality. Each dimension is scored with defined weightings to produce a deterministic evaluation result and a standardized feedback report.

Yes, you can integrate automated web app evaluation into CI pipelines. The evaluator launches a dev environment, runs Playwright tests against dashboards and forms, and outputs structured evaluation data suitable for automated release validation.

Generate a structured feedback report by running Playwright browser tests that assess UI quality. The output feedback.md file includes identified issues, reproduction steps, and actionable improvements based on deterministic design and functionality scoring.

Yes, Playwright is required to run automated QA scoring on web forms and flows. The evaluator relies on Playwright-based browser tests to launch the dev environment and assess functionality across multiple environments.

Automated web testing works for both CI pipelines and manual QA sessions evaluating design proposals. It applies deterministic scoring to assess dashboards, forms, and flows, outputting a standardized feedback.md for targeted evaluations.