fix-next-test

To fix multiple failing Playwright tests sharing a root cause, this Skill triages recent test failures into ranked root-cause groups and iteratively fixes the next highest-priority group together to streamline regression debugging.

Automating Playwright test triage in CI verification involves delegating failure analysis to a triager agent that ranks failing specs by root-cause confidence, then selecting and fixing the highest-priority group deterministically.

Test-driven verification for Playwright regressions works by using the project's test runner to re-run only the relevant affected spec, deploying the code change only after the targeted test passes successfully.

Yes, you can auto-pick the next failing Playwright test by instructing your agent to run the workflow with auto-picking, which triages the latest failures, selects the next group, and verifies the result automatically.

You need a triager agent to analyze Playwright test failures because this Skill reads triager outputs to select affected specs and rank failing tests by root-cause groups and confidence before applying fixes.