browse

Controls a persistent headless Chromium browser for QA testing, screenshots, and page state verification.

Updated May 15, 2026
One-click install
npx skills add https://github.com/tgmarinho/canetaco --skill browse-tgmarinho
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/tgmarinho/canetaco/tree/main/.claude/skills/browse
Command: npx skills add https://github.com/tgmarinho/canetaco --skill browse-tgmarinho

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bun.

What problem does it solve? Manually verifying that a web page loads correctly, a form submits, or a deployment looks right is slow and error-prone. This Skill gives you a fast headless browser (~100ms per command after startup) to navigate pages, interact with elements, capture evidence, and assert page state without writing test scripts. ## Core Features & Use Cases - Page Verification: Navigate any URL, read page text, inspect console errors and network failures, and assert element states (visible, enabled, checked, focused). - Interactive Flow Testing: Fill forms, click elements, upload files, handle dialogs, and diff page state before and after actions with unified snapshots. - Visual Evidence: Take annotated or plain screenshots, capture responsive layouts across mobile/tablet/desktop viewports, and render retina-scale images for bug reports. - Use Case: After deploying a new login flow, navigate to the page, fill credentials, submit, diff the resulting DOM, and capture an annotated screenshot proving the dashboard renders — all in seconds. ## Quick Start Ask the AI to open your staging site in the browser, fill in the login form, and take a screenshot of the dashboard to verify the deploy worked.

Frequently Asked Questions about browse

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I test a website with a headless browser?

Navigate to the URL with the goto command, then inspect page text, console errors, and network failures. Use snapshot to list interactive elements, fill and click to drive flows, and assert states like visibility or enabled to confirm behavior.

How do I take a screenshot of a web page from the command line?

Run the screenshot command with an output path after navigating to the page; full-page capture is the default. You can target a specific element with a selector, clip a region, or use responsive mode to capture mobile, tablet, and desktop viewports at once.

Can I use this instead of Puppeteer for browser automation?

Yes, common Puppeteer operations map directly: goto replaces page.goto, load-html replaces setContent, viewport replaces setViewport, and screenshot supports selectors and clips. State persists between commands, so cookies and login sessions carry across calls.

Does headless browsing work on sites with CAPTCHAs or MFA?

Headless automation cannot solve CAPTCHAs or multi-factor prompts. Use the handoff command to open a visible Chrome window at the current page, let the user complete the challenge, then resume with all cookies and state preserved.

Why do headless browsers get blocked by some websites?

Some sites fingerprint headless browsers or Playwright defaults. Running in headed mode with a visible window, optionally routed through an HTTP or authenticated SOCKS5 proxy, avoids most anti-bot detection.