Opens the running application in a browser to verify UI functionality.

Install

mkdir -p .claude/skills/go-laguagu && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18061" && unzip -o skill.zip -d .claude/skills/go-laguagu && rm skill.zip

Installs to .claude/skills/go-laguagu

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Opens the running app in a browser and verifies recent UI changes actually work. Use whenever the user wants a quick smoke test or sanity check of recent work, or says "go", "open in browser", "check in browser", "test your work", "make sure it works", "smoke test", "verify", "did it actually work", "make sure the form/page works", "check the form submits", "works on mobile" — even when they don't explicitly ask for browser testing. Also activates implicitly when the user appends "...and make sure it works" to a UI request. Skips design critique; for that, use go-ui.
573 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Beginner

Key capabilities

  • Open the running application in a browser
  • Verify recent UI changes
  • Check for functional verification, such as search results
  • Inspect console for JavaScript errors
  • Monitor network status for 4xx/5xx errors
  • Reload and re-verify after a fix

How it works

The skill opens the current application in a browser, using available browser tools like Chrome extension or Playwright, to verify UI changes and functional outcomes. It checks for console errors, network status, and expected page content.

Inputs & outputs

You give it
A URL or route, or an implicit UI request
You get back
The running app opened in a browser with verification of UI changes

When to use go

  • Verify form submission works
  • Check recent UI visual updates
  • Confirm page loads without JS errors
  • Test mobile responsiveness

About this skill

/go — Browser check

Verify your work in the browser instead of trusting that code compiles. Use whatever browser tools the environment offers (Chrome extension, next-devtools MCP, chrome-devtools MCP, Playwright — whichever is reachable). If chrome-devtools MCP is available and you need console errors, network status, or computed styles to confirm the fix, prefer it over a blind reload. If login is needed, credentials usually live in .env.local or the project's secrets manager.

Two things are easy to miss:

  • Functional verification — did the page actually return what was expected? Searching for "X" should show results containing X, not just render without errors.
  • Console and network — JS errors and 4xx/5xx are silent killers.

If something is broken, fix → reload → verify again. Don't thrash on the same issue — ask for direction instead.

When not to use it

  • When the user asks for design critique
  • When the user does not explicitly ask for browser testing

Limitations

  • It skips design critique
  • It does not address issues that require asking for direction

How it compares

This skill automates the process of opening a browser and performing checks, unlike manually navigating to the application and inspecting elements.

Compared to similar skills

go side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
go (this skill)02moReviewBeginner
webapp-testing3533moReviewIntermediate
ui-ux-expert-skill919moReviewAdvanced
accessibility425moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

webapp-testing

anthropics

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

353585

ui-ux-expert-skill

fercracix33

Technical workflow for implementing accessible React user interfaces with shadcn/ui, Tailwind CSS, and TanStack Query. Includes 6-phase process with mandatory Style Guide compliance, Context7 best practices consultation, Chrome DevTools validation, and WCAG 2.1 AA accessibility standards. Use after Test Agent, Implementer, and Supabase agents complete their work.

91244

accessibility

tech-leads-club

Audit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

42174

playwright-browser-automation

lackeyjb

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

29146

svelte-expert

Raudbjorn

Expert Svelte/SvelteKit development assistant for building components, utilities, and applications. Use when creating Svelte components, SvelteKit applications, implementing reactive patterns, handling state management, working with stores, transitions, animations, or any Svelte/SvelteKit development task. Includes comprehensive documentation access, code validation with svelte-autofixer, and playground link generation.

11107

browser-daemon

noiv

Persistent browser automation via Playwright daemon. Keep a browser window open and send it commands (navigate, execute JS, inspect console). Perfect for interactive debugging, development, and testing web applications. Use when you need to interact with a browser repeatedly without opening/closing it.

587

Search skills

Search the agent skills registry