skills.rest
idan-rubin
idan-rubinCOMMUNITY
Explore all skills by this author →
GitHub

browserclaw

Automate browser interactions via text snapshots and numbered refs.

41|3|Updated Feb 8, 2026
Search Tags:#playwright#web-testing#snapshot#browser-automation#ref-based#automation-patterns#interactive-browsing
One-click install
npx skills add https://github.com/idan-rubin/browserclaw --skill browserclaw
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browserclaw
Source: https://github.com/idan-rubin/browserclaw/tree/main/.claude/skills/browserclaw
Command: npx skills add https://github.com/idan-rubin/browserclaw --skill browserclaw

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Browsers are hard for AI agents to control directly; BrowserClaw provides a deterministic, snapshot-driven interface that lets automation agents perceive page content through text snapshots and act via numbered refs.

Core Features & Use Cases

  • Snapshot-based element targeting with numbered refs
  • Navigate, click, type, select, and extract data from dynamic sites
  • Re-snapshot after each action to maintain accurate context for decision-making

Quick Start

Launch a live browser, take an initial snapshot with interactive mode, and use the returned refs to drive actions.

Frequently Asked Questions about browserclaw

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

FAQPage Schema
How do I automate browser interactions on dynamic JavaScript sites without brittle CSS selectors?▼

Browser automation on dynamic JavaScript sites is managed by generating a text snapshot of the page and using numbered refs to drive actions like click, type, and select, avoiding brittle selectors entirely.

What is a snapshot-guided browser control loop for AI agents?▼

A snapshot-guided control loop provides AI agents with a text representation of page content, allowing them to perceive elements and execute actions via numbered refs before re-snapshotting to maintain accurate context.

How do I extract data from JS-heavy web pages using browser automation?▼

Data extraction from JS-heavy pages is accomplished by navigating the site with ref-based actions and taking a fresh snapshot after each interaction to accurately capture and extract dynamically loaded content across sessions.

Does this browser automation approach work for multi-session navigation and form interaction?▼

Yes, snapshot-driven browser automation supports navigation, form interaction, and data extraction across multiple sessions by maintaining a deterministic ref-based control loop for dynamic sites.

Why should I use ref-based element targeting instead of traditional selectors for web testing?▼

Ref-based targeting is used because it provides a deterministic interface for AI agents to interact with live pages, avoiding the brittleness and maintenance overhead of traditional CSS or XPath selectors.

Related Skills

Explore More Software Engineering Skills→
dawei12138dawei12138
23

playwright-cli

Automate browser actions and generate Playwright code via the CLI.

Community
Intermediate
quanngynxquanngynx

agent-browser

Automate Chrome browser interactions via CDP with snapshot-based element refs.

Community
Advanced
dpalferydpalfery

browser-testing

Automate web UI testing and end-to-end validation with Playwright MCP.

Community
Advanced
alexgorbatchevalexgorbatchev
1

agent-browser

Automate browser navigation, form filling, and login flows via CLI.

Community
Advanced