skills.rest
sigitpoerwo
sigitpoerwoCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

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

Updated Mar 29, 2026
Search Tags:#headless#browser-automation#agent-browser#automation-cli#ref-based-selection#accessibility-tree
One-click install
npx skills add https://github.com/sigitpoerwo/repoworkspace_zahra --skill agent-browser-sigitpoerwo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/sigitpoerwo/repoworkspace_zahra/tree/main/skills/01-SIAP-PAKAI/automation/agent-browser-clawdbot-0.1.0
Command: npx skills add https://github.com/sigitpoerwo/repoworkspace_zahra --skill agent-browser-sigitpoerwo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser tasks for AI agents, enabling deterministic interactions using refs and accessibility-tree snapshots.

Core Features & Use Cases

  • Ref-based element targeting for deterministic interactions
  • Headless browser operation with accessibility-tree snapshots
  • CLI-driven automation for multi-step workflows across complex SPAs

Quick Start

Open a URL with agent-browser and generate an interactive JSON snapshot to start automating deterministic interactions.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate deterministic browser interactions for AI agents?▼

You can automate multi-step workflows across complex SPAs using a CLI-driven headless browser. It handles complex single-page applications by generating interactive JSON snapshots for reliable step execution.

What is ref-based element selection in headless browser automation?▼

Headless browser automation provides session isolation for complex SPAs. Each automation run operates in an isolated headless environment, ensuring repeatable element refs and preventing state collision across multi-step workflows.

How do I start headless browser automation using a CLI?▼

To start headless browser automation, open a URL with the CLI to generate an interactive JSON snapshot. This accessibility-tree snapshot maps the page state for subsequent deterministic interactions.

Does headless browser automation work with complex single-page applications?▼

Yes, headless browser automation works with complex SPAs by utilizing accessibility-tree snapshots and ref-based element targeting. This combination ensures deterministic interactions even during dynamic page updates.

Why use accessibility-tree snapshots for browser automation instead of standard selectors?▼

Accessibility-tree snapshots provide deterministic element refs that remain stable across dynamic SPA updates. Standard DOM selectors often break during multi-step workflows, whereas accessibility-tree references ensure robust error handling and repeatable targeting.

Related Skills

Explore More Software Engineering Skills→
EvanBaconEvanBacon
571

agent-browser

Automate browser interactions for testing, form filling, and data extraction via CLI.

Community
Intermediate
pynbj1001pynbj1001
2

Smart Browser

Extract JavaScript-rendered web page agendas and session data to Markdown and JSON.

Community
Intermediate
xingxingstars123xingxingstars123

agent-browser

Automate browser interactions with ref-based element targeting and JSON snapshots.

Community
Advanced
joneqianjoneqian

agent-browser

Control a headless browser using accessibility-tree snapshots and ref-based element targeting.

Community
Advanced