browser-testing

Features and purpose

Browser automation for testing and verification. Use after building or modifying web UI to verify changes work. Uses Playwright's accessibility tree, not pixel-based input. LLM-friendly: no vision models needed, operates purely on structured data. Deterministic tool application avoids ambiguity common with screenshot-based approaches. Triggers: testing localhost, verifying UI changes, checking if a feature works, taking screenshots, debugging console errors, testing form submission, end-to-end verification, "does it work", "let me check the browser", "test the app", browser automation, web testing.

Quick start

Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.