agent-browser

Name: agent-browser
Availability: InStock
Author: Mitch

Automates browser tasks via CLI for opening pages, interacting with elements, and extracting data.

1|Updated Mar 22, 2026

Search Tags:#automation #debugging #authentication #cli #multi-session #browser #web-scraping

Ready to run

npx skills add https://github.com/mitchdowd/skills --skill agent-browser-mitchdowd

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/mitchdowd/skills/tree/main/agent-browser
Command: npx skills add https://github.com/mitchdowd/skills --skill agent-browser-mitchdowd

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a deterministic browser automation CLI that enables AI agents to interact with websites by opening pages, filling forms, clicking controls, taking screenshots, and extracting data without manual scripting.

Core Features & Use Cases

Navigate, snapshot with interactive element refs, and perform multi-step workflows across single or multi-session contexts.
Support authentication patterns, data extraction, testing, and visual debugging with streaming and recordings for documentation.
Use cases include form automation, data scraping, and end-to-end web app testing for AI-powered agents and teams.

Quick Start

Open a URL, snapshot interactive elements, fill a form using the discovered refs, and capture a screenshot for verification.

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 tasks for an AI agent without writing manual scripts?▼

Automate browser tasks using a deterministic command layer that lets AI agents open pages, fill forms, click elements, and extract data. It provides reliable command execution with safe defaults and extensible templates instead of manual scripting.

Can I handle authentication workflows and multi-session contexts with browser automation?▼

Multi-session browser automation supports isolated contexts, allowing concurrent interactions across different pages. This enables parallel authentication workflows, data scraping, and testing.

How do I extract data and fill forms from web pages using an AI-ready CLI?▼

Extract data and fill forms by taking snapshots of web pages to get interactive element references, then using those refs to target inputs and controls. Capture screenshots to verify the visual state after each action.

What's the best way to test web apps end-to-end with an AI command layer?▼

Test web apps end-to-end by navigating pages, snapshotting interactive elements, and performing multi-step workflows. The command layer supports streaming and recordings for visual debugging and documentation.

Does browser automation support visual debugging and streaming for documentation?▼

Yes, browser automation supports visual debugging with streaming and recordings. Capture screenshots during workflows to verify actions and generate documentation of the automated steps.

Do I need any dependencies to run browser-based automation scripts?▼

No external dependencies are required. The browser automation CLI operates independently with safe defaults and extensible templates, providing a reliable command layer for AI agents.