ui-test

ui test

browserbase 3.7k ↓ 2.5k updated 27d ago

Claude Code

View source ↗

What it does

Diff-driven — analyze a git diff, test only what changed
Exploratory — navigate the app, find bugs the developer didn't think about
Parallel — fan out independent test groups across multiple Browserbase browsers
The bottleneck is the slowest agent — split work so no single agent has a disproportionate share. Many small agents > few large ones.
No early stopping on failures — find as many bugs as possible within the assigned tests.
STEPPASS/STEPFAIL for every test you completed
STEPSKIP|<test-id>|budget reached for every test you didn't get to

Requirements & configuration

Size the effort to the change — a single component fix doesn't need many agents or many steps. A full-page redesign does. Let the scope of the diff drive the plan.
browse open <url> --auto-connect — auto-discover an existing debuggable local Chrome. Use this only when the test explicitly needs existing local login/cookies/state.
For worked examples with exact commands, read EXAMPLES.md if you need to see the assertion protocol in action.
2. Every assertion needs evidence — snapshot ref, eval result, or before/after diff

Configuration: BROWSE_SESSIONSESSION_JSONCONNECT_URLSESSION_ID

Derived from the skill's own SKILL.md documentation · extracted 2026-07-23

ui test

Source

Repository: https://github.com/browserbase/skills

ui-test FAQ

What does the ui-test skill do?

AI-powered adversarial UI testing via the browse CLI. Analyzes git diffs to test only what changed, or explores the full app to find bugs. Tests functional correctness, accessibility, responsive layout, and UX heuristics. Use when the user asks to test UI changes, QA a pull request, audit accessibility, or run exploratory testing. Supports local browser (localhost) and remote Browserbase (deployed sites). Diff-driven — analyze a git diff, test only what changed Exploratory — navigate the app, find bugs the developer didn't think about

What does ui-test require?

Size the effort to the change — a single component fix doesn't need many agents or many steps. A full-page redesign does. Let the scope of the diff drive the plan. browse open <url> --auto-connect — auto-discover an existing debuggable local Chrome. Use this only when the test explicitly needs existing local login/cookies/state. For worked examples with exact commands, read EXAMPLES.md if you need to see the assertion protocol in action. 2. Every assertion needs evidence — snapshot ref, eval result, or before/after diff Configuration keys: BROWSE_SESSION, SESSION_JSON, CONNECT_URL, SESSION_ID.

How do I install ui-test?

Run: npx -y skills add https://github.com/browserbase/skills --skill ui-test --agent claude-code — the source lives at github.com/browserbase/skills.

Maintain ui-test?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[ui-test on getagentictools](https://getagentictools.com/skills/browserbase-skills-ui-test?ref=badge)

npx agentictools info skills/browserbase-skills-ui-test

The second line is the CLI lookup for this page — handy in READMEs and docs.