Agent skill · Browserbase

Adversarial UI Test skill for Claude Code, Codex and Cursor

Tests what changed in a git diff through a browser: functionality, accessibility, layout, UX.

Officialname: ui-test★ 3.7k (repo)pushed 2026-09-29MITSKILL.md on GitHubchecked 2026-11-07

What it does, in the publisher's words

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).

The description field of the SKILL.md. The agent reads only this at startup and decides from it when to load the full skill.

Install Adversarial UI Test

The skills CLI copies the skill into the folder of each agent you pick (Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCode, Windsurf...). Add -g for all projects. Needs Node.js 22.20+. docs

npx skills add browserbase/skills --skill ui-test

This repo is a plugin marketplace. Inside Claude Code, add it and install the plugin that holds the skill (browse, functions, browser-trace, safe-browser...), or copy only this skill into ~/.claude/skills. docs

/plugin marketplace add browserbase/skills
/plugin install <plugin>@browserbase

# or only this skill:
npx skills add browserbase/skills --skill ui-test -a claude-code

Download the skill folder, zip it, then Customize > Skills > + > Create skill > Upload a skill. Code execution must be on (Settings > Capabilities). docs

git clone --depth 1 https://github.com/browserbase/skills.git /tmp/ui-test-src
cp -r /tmp/ui-test-src/skills/ui-test ./ui-test
zip -r ui-test.zip ui-test

Codex reads skills from .agents/skills in the repo or ~/.agents/skills. Type $ in Codex to use one. docs

npx skills add browserbase/skills --skill ui-test -a codex

gh skill (GitHub CLI 2.90+, preview) installs it for Copilot in VS Code, the CLI and the cloud agent. Copilot also reads .github/skills and ~/.copilot/skills. docs

gh skill install browserbase/skills ui-test

Cursor reads .cursor/skills, .agents/skills and ~/.cursor/skills (and .claude/skills). It does not install loose skills from a GitHub URL, so copy it in. docs

npx skills add browserbase/skills --skill ui-test -a cursor

Installs from the GitHub repo; --path picks this skill out of the repo. Default scope is user (all projects). docs

gemini skills install https://github.com/browserbase/skills.git --path skills/ui-test

OpenCode reads .opencode/skills, ~/.config/opencode/skills and the Claude and .agents folders. docs

npx skills add browserbase/skills --skill ui-test -a opencode

Windsurf (now Devin Desktop) reads .devin/skills, .windsurf/skills and ~/.codeium/windsurf/skills. docs

npx skills add browserbase/skills --skill ui-test -a windsurf

Works with

Claude Code, Claude.ai and Claude Desktop, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode, Windsurf and other agents that read the open Agent Skills format.

The SKILL.md says: "Requires the browse CLI (`npm install -g browse`). For remote testing: BROWSERBASE_API_KEY and cookie-sync skill."
Pre-approves these tools (allowed-tools, experimental in the spec): Bash Read Glob Grep Agent.

What's in the SKILL.md

34 sections

How Testing Works
Planning: multiple angles, then execute once
Principles for splitting work
Giving sub-agents a step budget
Reporting
Testing Philosophy
Assertion Protocol
Step markers
Screenshot Capture for Failures
How to verify (in order of rigor)
Before/after comparison pattern
Setup
Avoid permission fatigue
Mode Selection
Local Mode (default for localhost)
Remote Mode (deployed sites via cookie-sync)
Workflow A: Diff-Driven Testing
Phase 1: Analyze the diff
Phase 2: Map files to URLs
Phase 3: Ensure the right code is running
Phase 4: Generate test plan
Phase 5: Execute tests
Phase 6: Report results
Phase 7: Generate HTML report
+ 10 more

Bundled files

EXAMPLES.md
LICENSE.txt
README.md
references/adversarial-patterns.md
references/browser-recipes.md
references/design-consistency.md
references/design-system.example.md
references/exploratory-testing.md
references/parallel-testing.md
references/report-template.html
references/ux-heuristics.md

Loaded only when the instructions point to them.

Facts

Skill name: ui-test
Publisher: Browserbase (official)
Repo: browserbase/skills
License: MIT
Version: 0.4.0
SKILL.md size: 3,022 words, 594 lines
Bundled files: 11, 9 docs
Repo stars: 3.7k (as of 2026-10-24)
SKILL.md checked: 2026-11-07

More skills from browserbase/skills

Browserbase Browser: Controls a browser through CLI commands to browse sites, fill forms and extract data.
Browserbase Fetch: Retrieves a URL's HTML or JSON, headers and redirects without opening a full browser.

Related testing & qa skills

Web App Testing · Anthropic
Agent Browser · Vercel
Playwright Browser Automation · OpenAI
Playwright CLI · Microsoft (Playwright)
Property-Based Testing · Trail of Bits
Analyze .NET Performance · Microsoft (.NET)
Find Bugs · Sentry
k6 Load Testing · Grafana Labs

FAQ

What does the ui-test skill do?+

Tests what changed in a git diff through a browser: functionality, accessibility, layout, UX. In its own SKILL.md, Browserbase describes it as: "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."

How do I install the ui-test skill?+

Run npx skills add browserbase/skills --skill ui-test and pick your agents, or use the tab for your agent above. In Claude Code the skill ends up in ~/.claude/skills/ui-test/SKILL.md; in Codex and Cursor in .agents/skills/ui-test/.

Does Adversarial UI Test work in Codex, Cursor and Copilot, or only Claude?+

It's a standard SKILL.md, so any agent that reads the Agent Skills format can use it: Claude Code, the Claude apps, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode, Windsurf and more. The SKILL.md notes: Requires the browse CLI (`npm install -g browse`). For remote testing: BROWSERBASE_API_KEY and cookie-sync skill.

Who maintains Adversarial UI Test?+

Browserbase, the company or project behind it, in the browserbase/skills repo on GitHub, last pushed 2026-09-29. License: MIT.

Read a skill's SKILL.md and scripts before you install it: skills aren't verified by any agent vendor. Claude skills marketplace · How to install skills · MCP servers