Ui Test

Adversarial UI testing that actually tries to break your app instead of just confirming buttons exist. Point it at a git diff and it tests only what changed, or let it explore your whole app to find edge cases you didn't think about. Plans tests across functional, adversarial, and accessibility angles before spinning up parallel browser sessions to execute them. Every failure gets a screenshot. Built on Browserbase's browse CLI, works with localhost or deployed sites. The step budget system keeps agents from running forever, and the main coordinator merges results from sub-agents into a single pass/fail report. Useful for PR reviews, accessibility audits, or when you want actual QA coverage without writing test files.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.: 13
skills.sh installs: 3.1K
GitHub stars: 3.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add browserbase/skills --skill ui-test --agent claude-code

Installs into .claude/skills of the current project.

Files

UI Test — Agentic UI Testing Skill

Test UI changes in a real browser. Your job is to try to break things, not confirm they work.

Three workflows:

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

How Testing Works

The main agent coordinates — it plans test strategy, delegates to sub-agents, and merges results. Sub-agents do the actual browser testing.

Planning: multiple angles, then execute once

You MUST complete all three planning rounds yourself and output them before launching any sub-agents. Planning happens in your own response — it is NOT delegated to sub-agents. Do not skip ahead to execution.

Round 1 — Functional: What are the core user flows? What should work? Write out each test as: action → expected result.

Round 2 — Adversarial: Re-read Round 1. What did you miss? Think about: different user types/roles, error paths, empty states, race conditions, edge inputs (empty, huge, special chars, rapid clicks).

SKILL.md on GitHub