Agent Browser
Gives Claude Code a controlled browser for automated testing and debugging.
Before & after
Same prompt, same agent — the only difference is the skill.
I can test the checkout flow for you manually. I'd navigate through the steps, fill in the form fields, submit payment information, and check if the confirmation page appears and the order gets recorded. That would take me a bit of time to do step-by-step, and I'd need to see screenshots to show you the results. I could also write test automation for you if you wanted, though that would take longer. Do you have a staging link I can use to test?
CHECKOUT FLOW VERIFICATION — AUTOMATED BROWSER TEST TEST SETUP App: staging.example.com/checkout Browser: Chromium Viewport: 1280x800 (desktop) Timeout: 30s per step TEST SCRIPT EXECUTION 1. Navigate to checkout → PASS (loaded in 1.2s) 2. Enter email: testuser@example.com → PASS 3. Click "Confirm Email" button → PASS (redirected to shipping) 4. Enter address: 123 Oak St, Portland, OR 97214 → PASS (autocomplete worked) 5. Select shipping: Standard (5-7 days) → PASS (price updated to 12.00) 6. Click "Continue to Payment" → PASS (reached Stripe form) 7. Enter card: 4242424242424242, 12/26, CVC 123 → PASS (Stripe injected, no errors) 8. Enter name: Test User → PASS 9. Click "Pay Now" button → PASS (processing spinner appeared) 10. Wait for confirmation → PASS (redirected to /order-confirmation?id=ord_xyz123) 11. Verify confirmation page shows: Order number, total ($89.99), delivery date → PASS 12. Open DevTools, check Network tab → PASS (POST to /api/orders returned 201) 13. Check database: Order created with status=processing → PASS RESULT: PASS (all 13 steps completed, no errors) PERFORMANCE • Total flow time: 8.3s • Stripe form load: 2.1s • Payment processing: 1.8s • Post-payment redirect: 0.4s SCREENSHOTS CAPTURED • email-form: Form state after email entry • shipping-form: Address form with autocomplete expanded • payment-form: Stripe form mounted and ready • confirmation-page: Order confirmation page with order details • network-log: POST /api/orders response (201, order_id in payload) RECOMMENDATION: Flow is production-ready. One minor UX note: "Continue to Payment" button could be more visible (currently gray, blends into form). Consider brightening CTA for higher click-through.
About this skill
name: agent-browser description: Use when Gives Claude Code a controlled browser for automated testing and debugging.
Agent Browser
Agent Browser is a Vercel Labs skill that lets Claude Code drive a real browser session, useful for automated UI testing, visual debugging, and verifying that a generated feature actually works end to end.
What you get
- A controlled browser session Claude can navigate and inspect.
Customize your output
- Point it at a different app or add custom test scenarios.
Example output
A verified pass/fail report on the tested UI flow, with screenshots.
Best for
Developers who want Claude to verify its own UI changes automatically.
SKILL.md preview
---
name: agent-browser
description: Use when a coding agent needs a controlled real browser session to run automated UI tests, debug a rendered page visually, or verify that a generated feature actually works end to end.
version: 1.0.0
category: Development / Automation
author: AgentVolt
license: proprietary
tags:
- development
- automation
- standard
---
# Agent Browser
Gives a coding agent a controlled, scriptable browser session for automated UI testing, visual debugging, and end-to-end verification.
## When to use
… (sign up to view the full skill)More development skills
View all Development skills →Business Automation Stack
A connected set of agents that handle the repetitive ops work — follow-ups, summaries, and handoffs.
Generate
Scaffold code, tests, and boilerplate from a short spec.
Performance Profiler
Systematic performance profiling for Node.js, Python, and Go applications.
Chaos Engineer
Designs controlled failure experiments — from a single fault injection to a full game day — and produces the runbook, rollback plan.