agent-browser

Automate browser interactions via CLI to open URLs, fill forms, and extract data.

Updated Feb 11, 2016
One-click install
npx skills add https://github.com/Ehrax/dotfiles --skill agent-browser-ehrax
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Ehrax/dotfiles/tree/main/configs/agents/skills/agent-browser
Command: npx skills add https://github.com/Ehrax/dotfiles --skill agent-browser-ehrax

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Browser automation CLI for AI agents enables programmatic control of a browser to open URLs, interact with elements, take snapshots, and extract data.

Core Features & Use Cases

  • CLI-based browser automation with commands to open URLs, snapshot element refs, fill inputs, click controls, wait for page states, and capture screenshots or PDFs.
  • Supports multi-session isolation, state persistence, and authentication patterns for robust workflows, including reusing login states and proxies.
  • Use cases include automated testing, data extraction, form submission, and monitoring across single or multiple sites in production or CI environments.

Quick Start

Open a target website, snapshot to discover element refs, perform interactions such as filling a form and submitting, then verify the result.

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 like form filling and data extraction programmatically?

Automate browser tasks by using a CLI to open URLs, snapshot element references, fill inputs, click controls, and extract data. This enables programmatic control for automated form filling, authentication flows, and data extraction workflows.

Can I maintain login states and authentication across multiple browser automation sessions?

Yes, browser automation supports multi-session isolation and state persistence. You can reuse login states and authentication patterns across different environments, enabling robust workflows that require maintaining authenticated sessions.

What's the best way to discover and interact with web elements during UI testing?

Use the snapshot command to discover element references, then interact with them by filling inputs and clicking controls. This approach allows precise UI testing by programmatically targeting elements after capturing their references.

Does browser automation support waiting for specific page states before extracting data?

Yes, the CLI includes commands to wait for page states before proceeding. This ensures data extraction and interactions occur only after the page reaches the desired state, improving reliability in dynamic web environments.

Can I run automated browser workflows across multiple sites in CI environments?

Browser automation supports monitoring and testing across single or multiple sites in production or CI environments. Multi-session workflows enable concurrent operations across different domains with session isolation.

What security considerations exist when automating browser interactions with sensitive sites?

Browser automation includes security considerations like content boundaries and domain allowlists. These features restrict automation to approved domains, protecting sensitive sites from unauthorized programmatic access during workflows.