agent-browser

Automate browser inspection, navigation, interaction, and screenshot capture via Chrome DevTools Protocol.

13|2|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/quan2005/journal-claw --skill agent-browser-quan2005
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/quan2005/journal-claw/tree/main/.od-skills/agent-browser-ff76ddd73c
Command: npx skills add https://github.com/quan2005/journal-claw --skill agent-browser-quan2005

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you reliably inspect, test, and automate browser behavior when you need evidence from a live web page instead of guesswork. It is especially useful for validating local previews, checking the current browser tab, and gathering structured findings like screenshots, page metadata, or accessibility signals.

Core Features & Use Cases

  • Browser-driven QA and validation: Open pages, confirm titles and URLs, capture snapshots, and document visible UI state for product reviews or bug hunts.
  • Structured page inspection: Extract design and content evidence such as logos, fonts, colors, images, OG metadata, and accessibility details from the DOM and browser context.
  • Safe local-first automation: Connects through Chrome DevTools Protocol, prefers local Open Design preview URLs, and includes guardrails against unsafe actions like submitting forms or changing account state without confirmation.

Quick Start

Ask the agent to use the agent-browser skill to open your local preview, inspect the current page, and save a screenshot with the title, URL, and key visible findings.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate browser inspection and capture screenshots for QA validation?

Browser inspection and screenshot capture for QA validation is automated by connecting to a Chrome DevTools Protocol endpoint, navigating pages, and capturing page metadata and visible UI state evidence.

What is the best way to test local preview URLs for accessibility review?

Accessibility review for local preview URLs is performed by opening the local pages via browser automation, extracting accessibility signals from the DOM, and documenting structured findings without guesswork.

How does form interaction and web inspection work with Chrome DevTools Protocol?

Form interaction and web inspection via Chrome DevTools Protocol works by taking DOM snapshots to target elements, applying safety checks, and executing state-changing browser actions only after confirmation.

Can I extract design elements like fonts and colors from a live web page?

Extracting design elements like fonts, colors, logos, images, and OG metadata from a live web page is possible by inspecting the DOM and browser context to gather structured content evidence.

Does browser automation prevent unsafe actions like submitting forms automatically?

Browser automation includes guardrails against unsafe actions by requiring safety checks and explicit confirmation before executing state-changing browser actions like form submissions or account state modifications.

When should I use snapshot-based element targeting for web inspection?

Snapshot-based element targeting for web inspection should be used when you need reliable element identification for bug reproduction, QA testing, and capturing structured evidence from live web pages.