skills.rest
Zhow01
Zhow01COMMUNITY
Explore all skills by this author →
GitHub

agent-browser

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

52|3|Updated Apr 3, 2026
Search Tags:#automation#browser#headless#ai-agents#ref-based#accessible-tree
One-click install
npx skills add https://github.com/Zhow01/SkillAttack --skill agent-browser-zhow01
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Zhow01/SkillAttack/tree/main/data/hot100skills/009_matrixy_agent-browser-clawdbot
Command: npx skills add https://github.com/Zhow01/SkillAttack --skill agent-browser-zhow01

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automate browser automation for AI agents by providing a reliable mechanism to interact with web pages using accessibility snapshots and ref-based element selection, reducing flaky interactions.

Core Features & Use Cases

  • Headless Browser Automation: Run deterministic browser tasks in isolated sessions for AI agents.
  • Accessibility Tree Snapshots: Capture and reuse element references for stable interactions across navigations.
  • Ref-based Interactions: Use stable refs to click, fill, and extract data from dynamic SPAs.
  • Use Case: Automate login flows, form submissions, and data extraction on complex web apps.

Quick Start

Open a site, snapshot the accessibility tree with JSON refs, and interact using ref identifiers.

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 on dynamic SPAs without flaky selectors?▼

Automate browser interactions on dynamic SPAs by capturing accessibility tree snapshots and using stable ref-based element selection to click, fill, and extract data without flaky selectors.

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

Ref-based element selection uses accessibility tree snapshots to generate stable JSON references, allowing deterministic browser interactions across complex multi-step navigations and modern single-page applications.

How do I extract data from web apps using accessibility tree snapshots?▼

Extract data from web apps by capturing an accessibility tree snapshot with JSON refs and using those stable ref identifiers to interact with elements across dynamic page updates and navigations.

Does headless browser automation support isolated sessions for multi-step navigation?▼

Headless browser automation supports multi-step navigation by running deterministic tasks in isolated sessions, ensuring stable interactions across complex login flows and form submissions.

Why does my AI agent's browser automation fail on modern web apps?▼

Browser automation fails on modern web apps due to unstable selectors, which can be resolved by using accessibility tree snapshots and ref-based element selection for deterministic interactions.

Can I use accessibility tree snapshots for form completion on single-page applications?▼

Accessibility tree snapshots provide stable ref identifiers for completing forms on single-page applications, enabling deterministic click and fill actions across dynamic DOM updates.

Related Skills

Explore More Software Engineering Skills→
ronakpjainronakpjain
10

playwright-firefox

Automate Firefox browser sessions for live, headless, and multi-profile testing.

Community
Intermediate
archibatearchibate
6

slack

Automate Slack web workspace interactions to read messages and extract channel metadata.

Community
Intermediate
aresbitaresbit
46

agent-browser

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

Community
Intermediate
pierregueroultpierregueroult

agent-browser

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

Community
Intermediate