ui-test

Diff-aware adversarial QA: it reads the git diff and tests only what changed, across correctness, accessibility, layout and UX.

Score 0(?)VerifiedCodeby BrowserbaseSourceDocs
Verified for:

Install

$ npx skills add browserbase/skills

Needs the browse CLI. BROWSERBASE_API_KEY only for testing deployed sites; localhost testing runs locally. Ships an HTML report template.

Best for

QA on a pull request, where testing the whole app is too slow and testing nothing is what actually happens.

Not ideal for

Deterministic regression suites. It explores and spawns sub-agents with step budgets, so results vary between runs — use it alongside a fixed suite, not instead of one.

About this skill

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).

QAAccessibilityDiff-aware

Score breakdown

Score breakdown

rubric 1.0
Install count
0/20
Provenance
12.8/15
GitHub stars
10.1/15
Recency
10/10
Compatibility
2/10
Documentation depth
10/10
Install ergonomics
10/10
License
4.3/5
Verification freshness
0.5/5

Composite 0–100 score derived from 9 verifiable signals. See the rubric →

Deterministic web control. ref-based clicks/fills, no flaky selectors, parallel sessions.

BrowserAutomationAction-taking
Code
Medium4 min

Test local webapps with Playwright. Generation, run, report — end-to-end.

PlaywrightE2ETesting
Code
Medium3 min

Playwright patterns: clicks, fills, waits, retries. The do-it-right defaults.

PlaywrightAutomation
Code
Low2 min

Ranked #2 in Testing

Publish the ranking in your README. The badge reads the live score, so it updates when the ranking does.

ui-test — ranked #2 in Testing on Top Agent Skills
Markdown
[![ui-test — ranked #2 in Testing on Top Agent Skills](https://top-agent-skills.com/badge/browserbase-ui-test.svg)](https://top-agent-skills.com/skill/browserbase-ui-test)
HTML
<a href="https://top-agent-skills.com/skill/browserbase-ui-test"><img src="https://top-agent-skills.com/badge/browserbase-ui-test.svg" alt="ui-test — ranked #2 in Testing on Top Agent Skills"></a>

Skill FAQ

About ui-test

What is the ui-test skill?

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).

Which agents does ui-test work with?

Claude Code.

How do I install ui-test?

Run `npx skills add browserbase/skills` for Claude Code. See the install panel for per-agent commands.

Is ui-test free to use?

Yes — ui-test is open source (MIT (declared in SKILL.md frontmatter; no repo LICENSE file)).

Who maintains ui-test?

ui-test is published by Browserbase and was last updated on 2026-08-18.

What is ui-test best for?

QA on a pull request, where testing the whole app is too slow and testing nothing is what actually happens.