agent-browser

Automate web page navigation, interaction, and data extraction via Chromium CDP.

Updated Mar 28, 2026
One-click install
npx skills add https://github.com/MisLink/agentry --skill agent-browser-mislink
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/MisLink/agentry/tree/main/agents/.agents/skills/agent-browser
Command: npx skills add https://github.com/MisLink/agentry --skill agent-browser-mislink

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Many AI agents need to interact with web pages but lack a reliable way to control a browser programmatically; developers waste time writing custom scripts for navigation, form submission, and screenshot capture.

Core Features & Use Cases

  • Native Chromium control via CDP without Playwright or Puppeteer.
  • Session management with state saving, authentication vaults, and named sessions.
  • Specialized skills for Electron apps, Slack, Vercel Sandbox, and AWS Bedrock AgentCore.
  • Supports testing workflows such as exploratory QA, bug hunting, and end‑to‑end web app validation.

Quick Start

Use the agent-browser skill to open a webpage and capture a screenshot in a single command.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate web scraping and form filling without Playwright or Puppeteer?

You can automate web scraping and form filling via native Chromium control using CDP. The agent-browser CLI manages page interaction and data extraction directly, bypassing the need for Playwright or Puppeteer.

Can I persist authentication state for browser automation across sessions?

Yes, browser automation supports session management with state saving. You can use authentication vaults and named session files to persist login states across multiple automation runs.

What do I need to run CLI browser automation for AI agents?

To run CLI browser automation, you need a Chromium-based browser and the agent-browser CLI. Optional session state files are recommended for authentication persistence during web page navigation.

Does browser automation work for testing Electron apps and cloud environments?

Yes, browser automation includes specialized skills for testing Electron apps, Slack, Vercel Sandbox, and AWS Bedrock AgentCore. It supports exploratory QA, bug hunting, and end-to-end validation workflows.

How do I capture screenshots during automated website testing?

You can capture screenshots during website testing using a single CLI command. The automation tool opens a webpage and captures the screen directly through native Chromium control.

Why use native CDP control instead of standard web automation frameworks?

Native CDP control removes dependency overhead from frameworks like Playwright. It provides fast, scriptable browser automation directly through Chromium, reducing the time spent writing custom interaction scripts.