skills.rest
escotilha
escotilhaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser navigation and interaction for QA evidence collection.

Updated Aug 27, 2026
Search Tags:#browser automation#cdp#visual regression#network interception#batch execution#qa testing#accessibility tree
One-click install
npx skills add https://github.com/escotilha/claude-public --skill agent-browser-escotilha
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/escotilha/claude-public/tree/main/skills/agent-browser
Command: npx skills add https://github.com/escotilha/claude-public --skill agent-browser-escotilha

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes brittle, manual browser testing and data collection by providing deterministic automation for real user interactions, page capture, and regression checks.

Core Features & Use Cases

  • Multi-step browser automation: navigate, click elements, fill inputs (including keyboard-real type), and drive complex flows across pages.
  • Rich page capture for QA: generate accessibility tree snapshots with structured references plus screenshots and PDFs.
  • Visual and state regression: run visual diff against baselines and compare snapshot states to detect UI and DOM/accessibility changes.
  • Network-aware execution: intercept, inspect, and manage network requests while keeping session persistence for auth-heavy flows.
  • Batch execution for sub-agents: process multi-command workflows efficiently via stdin JSON.

Quick Start

Load the current command reference, then run the browser to open the target URL by asking the AI to execute: agent-browser open <url>.

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 navigation and capture screenshots for QA testing?▼

Browser automation for QA testing is handled by navigating URLs, clicking elements, filling inputs, and generating screenshots or PDFs to collect deterministic regression evidence.

What is visual regression testing and how does network interception work?▼

Visual regression testing compares page captures against baselines to detect UI changes, while network interception inspects and manages network requests during automated browser execution.

Can I run batch browser automation workflows via stdin JSON?▼

Batch execution processes multi-command browser automation workflows efficiently via stdin JSON, enabling sub-agents to drive complex navigation and interaction sequences.

Does this browser automation tool support accessibility tree snapshots?▼

Accessibility tree snapshots are supported alongside screenshots and PDFs, providing structured references for page state comparison and DOM regression checks.

Do I need a Rust CDP CLI runtime to run browser automation commands?▼

A Rust CDP CLI runtime is required to execute browser automation commands, and the current skill command reference must be loaded via agent-browser skills get before running operations.

What's the best way to maintain session persistence for auth-heavy browser flows?▼

Session persistence for auth-heavy browser flows is maintained during network-aware execution, allowing automated multi-step scenarios to intercept requests while keeping authentication state active.

Related Skills

Explore More Software Engineering Skills→
8b-is8b-is

agent-browser

Automate browser navigation, element interaction, and data extraction via CLI.

Official
Advanced
alvarettoalvaretto
1

Comparación Visual Inteligente

Compare generated images against originals and report visual differences.

Community
Advanced
reececoakes99reececoakes99

playwrights

Automate multi-browser testing and web scraping with Python Playwright.

Community
Intermediate
abhishekdutta18abhishekdutta18

browser-qa

Automate visual, functional, and accessibility testing of web pages.

Community
Intermediate