debug-tests

You can automate debugging failing Playwright tests by orchestrating fresh sub-agent workers for each fix attempt. This Skill automatically analyzes failures, proposes fixes, and runs independent failures in parallel while handling coupled failures sequentially.

Sub-agent debugging handles multiple test failures by assigning a fresh sub-agent to each fix attempt. It executes independent failures in parallel for faster resolution and processes coupled failures sequentially to maintain test stability.

Yes, you need Playwright as your test runner. The automated sub-agent debugging process requires Playwright for test execution and relies on parsing JSON output to identify and orchestrate fixes for the failing tests.

Yes, you can preview the debugging plan using the dry-run mode. This provides visibility into the proposed execution strategy and plan before any actual fixes are applied to your failing Playwright tests.

The best way to get detailed logs is by using the debug mode. This mode provides deep visibility into the execution details and generates summaries of the fixes applied by the sub-agents to your failing tests.

You should avoid parallel execution when dealing with coupled failures. The automated debugging system correctly identifies these interdependent test failures and processes them sequentially to prevent conflicting fix attempts.