skills.rest
tomrford
tomrfordCOMMUNITY
Explore all skills by this author →
Website𝕏@tomrfordGitHub

agent-browser

Automate browser navigation, form filling, and data extraction via CLI.

Updated Aug 23, 2026
Search Tags:#cli#scripting#headless#web-automation#browser-automation#agent-browser#ref-based-selection
One-click install
npx skills add https://github.com/tomrford/dotfiles --skill agent-browser-tomrford
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/tomrford/dotfiles/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/tomrford/dotfiles --skill agent-browser-tomrford

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI agents often require reliable browser automation to perform tasks like navigation, form filling, data extraction, and page interactions. Traditional manual work or brittle scrapers slow down workflows; this skill provides a robust CLI-driven approach that yields repeatable results.

Core Features & Use Cases

  • Navigate to URLs, snapshot the accessibility tree for stable element refs, and interact with web pages using ref-based selectors.
  • Capture screenshots, extract data, and automate common tasks such as clicking, typing, and form submission.
  • Support multiple sessions and parallel workflows to scale automation across tasks and sites.

Quick Start

Open a URL, snapshot interactive elements to obtain refs, then interact with elements 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 browser interactions for AI agents using a CLI tool?▼

Browser automation for AI agents uses a CLI-driven tool to navigate URLs, snapshot interactive elements, and perform interactions like clicking and typing via ref-based selectors to ensure repeatable web task execution.

How does ref-based selection work for web page automation?▼

Ref-based selection captures the accessibility tree snapshot to obtain stable element refs, allowing web automation scripts to interact with page elements like buttons and forms using those persistent references.

Can I run parallel workflows and multiple sessions for web automation?▼

Parallel workflows and multiple sessions are supported, allowing you to scale browser automation across different tasks and sites simultaneously by managing distinct CLI-driven browser instances.

What is the best way to extract data and fill forms on web dashboards?▼

Extracting data and filling forms on web dashboards is best handled by CLI browser automation, which navigates to URLs, uses ref-based selectors to target form fields, and executes data extraction or submission tasks reliably.

Do I need any external dependencies to run headless browser automation scripts?▼

No external dependencies are required to run headless browser automation scripts; the skill operates independently using a CLI-based tool and supports optional scripts and assets directories for extended operations.

Related Skills

Explore More Software Engineering Skills→
t0labt0lab
2

playwright

Automate browser interactions and UI verification via Playwright CLI snapshots.

Official
Intermediate
viably-labsviably-labs

playwright-screenshot-inspector

Analyze Playwright screenshots to validate UI rendering accuracy semantically.

Official
Advanced
sigitpoerwosigitpoerwo

agent-browser

Automate deterministic browser interactions via headless CLI with ref-based element selection.

Community
Advanced
Zhow01Zhow01
52

agent-browser

Automate browser interactions using accessibility-tree snapshots and ref-based element selection.

Community
Advanced