agent-browser

Automate Chromium browser navigation, form filling, screenshots, and data extraction.

59|14|Updated Mar 1, 2026
One-click install
npx skills add https://github.com/vobase/vobase --skill agent-browser-vobase
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/vobase/vobase/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/vobase/vobase --skill agent-browser-vobase

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Provides a CLI-driven browser automation interface that lets AI agents and developers perform navigation, form filling, clicking, screenshots, data extraction, and E2E interactions without writing complex Playwright scripts, reducing manual web interaction and brittle selector work.

Core Features & Use Cases

  • Interactive Snapshots & Refs: Compact accessibility-tree snapshots with stable refs (@e1, @e2) for precise element targeting and minimal context usage.
  • Session & State Management: Named isolated sessions, save/load state, and encrypted session persistence for authenticating once and reusing across runs.
  • Full Automation Surface: Navigation, clicks, typing, file downloads, screenshots, PDF export, visual diffing, recording, CDP connectivity, mobile simulator support, and proxy configuration for scraping and testing.
  • Security Controls: Domain allowlists, action policies, content boundaries, and environment-configurable limits to reduce unsafe automation.
  • Use Cases: Automated form submission, authenticated scraping, visual regression and diffing, CI test evidence recording, and reproducing user flows for debugging.

Quick Start

Open the target URL, take an interactive snapshot to obtain refs, then instruct the agent to fill the credential ref and click the submit ref to complete the login flow.

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 without writing complex Playwright scripts?

You can automate web scraping by using a CLI-driven interface to navigate, take interactive accessibility-tree snapshots, and extract structured data without writing complex Playwright scripts. This reduces manual web interaction and brittle selector work.

Can I persist authenticated browser sessions and reuse them across runs?

Yes, you can persist authenticated browser sessions. The tool supports named isolated sessions, save/load state, and encrypted session persistence, allowing you to authenticate once and reuse the state across multiple automation runs.

What is the best way to target specific web elements for form filling and clicking?

The best way to target web elements is using interactive snapshots with stable refs like @e1 or @e2. These compact accessibility-tree refs provide precise element targeting for form filling and clicking while minimizing context usage.

Does this browser automation tool support visual regression testing and screenshots?

Yes, the browser automation tool supports visual regression testing. It can capture screenshots, perform visual diffing, export PDFs, and record CI test evidence across headless or headed Chromium sessions.

How do I configure security boundaries for automated web scraping tasks?

You can configure security boundaries for automated web scraping using domain allowlists, action policies, content boundaries, and environment-configurable limits. These controls reduce unsafe automation during navigation and data extraction.

Can I use CDP connectivity and mobile simulators for end-to-end testing?

Yes, you can use CDP connectivity and mobile simulators for end-to-end testing. The tool supports CDP connectivity, mobile simulator workflows, and proxy configuration for comprehensive scraping and testing scenarios.