agent-browser

Automate browser clicks, form fills, and screenshots via the agent-browser Bash CLI.

Updated Nov 11, 2025
One-click install
npx skills add https://github.com/codexyzdev/codexyz --skill agent-browser-codexyzdev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/codexyzdev/codexyz/tree/main/.trae/skills/agent-browser
Command: npx skills add https://github.com/codexyzdev/codexyz --skill agent-browser-codexyzdev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates repetitive browser interactions to reduce manual testing and data collection work.

Core Features & Use Cases

  • Navigation, form filling, element interaction, and data extraction across websites and web apps.
  • Quick demonstrations and QA workflows.
  • Use Case: For example, automatically fill and submit a login form to verify authentication flows.

Quick Start

  • Open a URL: agent-browser open https://example.com
  • Snapshot to create element refs: agent-browser snapshot -i
  • Interact using refs: agent-browser click @e1; agent-browser fill @e2 "sample"
  • Take a screenshot: agent-browser screenshot ./sample.png

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 form filling and web testing without manual clicking?

Automate browser form filling and web testing by using the agent-browser CLI to open URLs, snapshot interactive elements into refs, and programmatically execute click and fill actions for reliable QA workflows.

How does snapshot-based element interaction work for data extraction?

Snapshot-based element interaction works by running a snapshot command to capture page elements as reference IDs, then using those refs to target specific elements for click, fill, and data extraction actions across websites.

Can I use agent-browser for repetitive web testing in automation pipelines?

Yes, you can use agent-browser for repetitive web testing in automation pipelines because it is designed for QA teams and developers who need reliable, repeatable browser tasks and demonstrations without manual intervention.

What's the best way to extract data from websites using a CLI?

The best way to extract data from websites using a CLI is to navigate to the target URL, generate a snapshot to identify elements, and interact with those elements to retrieve and capture the needed data via screenshots or direct extraction.

Do I need any specific dependencies to run browser automation tasks?

You need the agent-browser Bash CLI installed in your environment to run browser automation tasks, but no additional software dependencies are required to perform navigation, form filling, and element interaction.