agent-browser

Automate browser tasks via Bash CLI with refs, sessions, and screenshots.

25|15|Updated Aug 2, 2021
One-click install
npx skills add https://github.com/JesusFilm/core --skill agent-browser-jesusfilm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/JesusFilm/core/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/JesusFilm/core --skill agent-browser-jesusfilm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browser automation enables automated interaction with web pages, form filling, and data extraction using a CLI, removing repetitive manual tasks.

Core Features & Use Cases

  • CLI-driven browser automation for navigating pages, filling forms, taking screenshots, and scraping content.
  • Refs-based interactions to reliably target elements using refs, enabling repeatable automation workflows.
  • Session and authentication support with options for headless/headed modes, profiles, and state persistence for long-running tasks.

Quick Start

Open a URL, snapshot to generate element refs, fill fields, click, wait, and verify results.

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 and web scraping using a CLI?

Browser automation via CLI lets you script web interactions like form filling and data scraping. You can navigate pages, fill fields, click elements, wait for loads, and take screenshots using Bash commands.

What is the best way to reliably target elements for automated form filling?

Element targeting for automated form filling uses a refs-based approach. You snapshot the page to generate element refs, enabling repeatable automation workflows that reliably interact with targeted page components.

Does CLI browser automation support authentication and session state persistence?

Session and authentication support allows state persistence across browser automation workflows. You can use headless or headed modes, maintain profiles, and manage multi-session workflows for long-running authenticated tasks.

Can I use browser automation for single-page apps and traditional websites?

Browser automation handles both single-page apps and traditional sites. It applies consistent web interaction commands to extract data, fill forms, and scrape content across varying web architectures.

How do I start a web scraping workflow with browser automation commands?

To start web scraping, open a URL and snapshot the page to generate element refs. Then use fill, click, wait, and screenshot commands to automate interactions and verify scraping results.

Are there limitations when using Bash-based browser automation for web interactions?

Bash-based browser automation requires the agent-browser CLI to function. While it supports proxy configurations and sessions, complex workflows depend on accurate element refs generated from page snapshots for reliable execution.