skills.rest
Rysnz
RysnzCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser interactions for AI agents using the agent-browser CLI.

1|Updated Apr 10, 2026
Search Tags:#automation#testing#agent#scripting#browser#web#data-extraction
One-click install
npx skills add https://github.com/Rysnz/OpenHarness --skill agent-browser-rysnz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Rysnz/OpenHarness/tree/main/src/crates/core/builtin_skills/agent-browser
Command: npx skills add https://github.com/Rysnz/OpenHarness --skill agent-browser-rysnz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Enables AI agents to autonomously drive browser-based tasks, eliminating manual web interactions by letting AI open pages, fill forms, click controls, and extract data.

Core Features & Use Cases

  • Automates common web tasks such as navigation, form submission, data extraction, visual verification, and basic testing across websites and web apps.
  • Supports multi-session workspaces, element references via snapshots, and on-demand resources through references for deeper guidance.

Quick Start

Open a URL with agent-browser open <url> and snapshot to discover element references, then instruct the agent to perform actions using those refs.

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 form filling and clicking using an AI agent?▼

To automate web form filling and clicking, this Skill uses the agent-browser CLI to open pages, snapshot element references, and execute actions like text input and button clicks autonomously.

What is the best way to extract data from websites with AI browser automation?▼

AI browser automation handles data extraction by navigating local or remote sites, taking snapshots of element references, and pulling specific content from web pages without manual interaction.

Do I need a specific browser installed to run agent-browser automation tasks?▼

Yes, agent-browser requires a compatible Chromium-based browser and the agent-browser CLI installed to perform automation tasks like navigating pages and taking screenshots.

Can I automate web app testing across multiple sessions?▼

Yes, browser automation supports basic web app testing across multiple sessions, allowing AI agents to navigate, fill forms, and verify visual states using multi-session workspaces.

How does an AI agent locate page elements for browser automation tasks?▼

The agent locates page elements by taking a snapshot of the current page, which generates element references that the agent uses to perform on-demand actions like clicking or typing.

What are the limitations of using browser automation for web scraping?▼

Limitations include relying on a Chromium-based environment and needing explicit element references from snapshots, meaning complex dynamic sites may require additional reference resources for accurate navigation.

Related Skills

Explore More Software Engineering Skills→
hemoryhemory

agent-browser

Displays a list of available commands for the specified tool.

Community
Intermediate
bendruckerbendrucker
16

json

Process JSON data with jq filters for parsing, filtering, and transforming.

Community
Basic
softmgsoftmg

browser

Automate web browsing and UI interactions using accessibility-tree snapshots with stable element refs.

Official
Intermediate
obulaiobulai
1

obul-notte

Start headless browser sessions and scrape web pages via the Obul proxy.

Official
Intermediate