Browser Test

Combines browser-record and browser-replay so every UI test produces a replayable RVF artifact instead of disappearing when the run finishes. You open a browser, click and fill forms, wait for elements, assert on text or values, and take screenshots. All of that gets stored in a session container you can diff against later or replay in CI. The honest benefit is you're not re-authoring tests when something breaks, you're just re-running the stored session. It wires in aidefence_is_safe to quarantine injection attempts before they hit findings.md, and it indexes selectors by embedding similarity so future tests can locate elements without brittle XPath. If you're doing any kind of regression testing on web UIs, the replayability alone makes it worth trying.

skills.sh installs: 756
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill browser-test --agent claude-code

Installs into .claude/skills of the current project.

Files

Browser Test

Automated UI testing. Now backed by a recorded RVF session container instead of an ephemeral run, so every test produces a replayable artifact.

When to use

Verifying UI functionality, user flows, or that frontend changes work in a real browser.
Producing a baseline session that future regressions can diff against.
Re-running a stored test session when CI fails (no need to re-author the test).