skills.rest
iyaki
iyakiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate Chrome browser interactions for AI agents via CDP.

Updated Sep 25, 2025
Search Tags:#automation#cli#rust#cdp#browser#ai-agents
One-click install
npx skills add https://github.com/iyaki/opencode-base-template --skill agent-browser-iyaki
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/iyaki/opencode-base-template/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/iyaki/opencode-base-template --skill agent-browser-iyaki

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Browsers are essential for testing, data extraction, and interaction with web apps, but automating repetitive browser tasks for AI agents is error-prone and time-consuming. This Skill provides a fast, robust way to drive Chrome/Chromium-based tasks from AI agents, including navigation, form filling, button clicks, screenshots, data scraping, and UI testing.

Core Features & Use Cases

  • Native Rust CLI with CDP support for fast, reliable browser automation.
  • Visual and accessibility-tree snapshots for stable element references.
  • Sessions, authentication vault, state persistence, and video recording for reliable workflows.
  • Specialized workflows for Electron apps (VS Code, Slack, Notion, etc.), Slack interactions, QA, and exploratory testing.
  • Use cases include automated website testing, data extraction from pages, form automation, and UI validation of web apps.

Quick Start

Install agent-browser and run a sample workflow to perform automated browser tasks.

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 interactions for AI agents?▼

You can automate browser interactions for AI agents by using a native Rust CLI with Chrome DevTools Protocol (CDP) support to navigate, fill forms, click buttons, and take screenshots. This approach provides fast, reliable execution for automated workflows.

Can I automate testing for Electron apps like VS Code or Slack?▼

Yes, you can automate testing for Electron apps like VS Code, Slack, or Notion. The automation tool provides specialized workflows to drive desktop-like and cloud environments, enabling UI validation and interaction within these applications.

What is CDP support for browser automation?▼

CDP support for browser automation means using the Chrome DevTools Protocol to directly control Chrome or Chromium. This allows a native Rust CLI to execute fast, reliable instructions like generating accessibility-tree snapshots and recording video sessions.

How do I maintain state and authentication when automating web apps?▼

To maintain state and authentication when automating web apps, you can use built-in sessions, an authentication vault, and state persistence features. These ensure reliable workflows by preserving login credentials and page states across multiple automated interactions.

Does this browser automation tool work for exploratory testing and bug hunts?▼

Yes, this browser automation tool works for exploratory testing, bug hunts, and QA. It utilizes visual and accessibility-tree snapshots for stable element references, applying automated navigation and data scraping to validate web apps effectively.

What's the best way to extract data from web pages using an AI agent?▼

The best way to extract data from web pages using an AI agent is through a native Rust CLI that drives Chrome via CDP. It provides visual snapshots and guardrails for safe automated browsing, ensuring accurate data scraping from targeted web elements.

Related Skills

Explore More Software Engineering Skills→
crbnoscrbnos
2.3k

agent-browser

Automate Chrome/Chromium web interactions via CDP for testing and scraping.

Official
Intermediate
marquesfelipmarquesfelip

customer-offboarding

Automate end-to-end customer offboarding workflows for SaaS platforms.

Community
Advanced
EvanBaconEvanBacon
571

agent-browser

Automate browser interactions for testing, form filling, and data extraction via CLI.

Community
Intermediate
riftzen-bitriftzen-bit

browser-qa

Automate browser-based visual testing and UI interaction verification with Playwright or Puppeteer.

Community
Advanced