agent-browser

Name: agent-browser
Availability: InStock
Author: InternLM

Automate headless browser navigation, interaction, and data extraction with Puppeteer.

501|56|Updated Mar 23, 2026

Search Tags:#automation #accessibility #scraping #browser #headless #webdriver

Ready to run

npx skills add https://github.com/InternLM/WildClawBench --skill agent-browser-internlm

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/InternLM/WildClawBench/tree/main/skills/agent-browser
Command: npx skills add https://github.com/InternLM/WildClawBench --skill agent-browser-internlm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires puppeteer, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Automates browser interactions with deterministic element selection and accessibility snapshots, streamlining complex web workflows.

Core Features & Use Cases

Headless Browser Automation: Perform navigation, interaction, and data extraction on websites.
Deterministic Element Selection: Use refs and accessibility trees for reliable element targeting.
Use Case: Automate login, form submission, and data scraping tasks on dynamic SPAs or large web applications for testing or data collection.

Quick Start

Use agent-browser to open a webpage, take a snapshot, and click a button identified by a ref.

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 navigation and data scraping on dynamic SPAs?▼

You can automate web navigation and data scraping on dynamic SPAs using headless browser automation, which employs deterministic element selection and accessibility snapshots to reliably interact with complex web applications.

Can I use Puppeteer for headless browser automation with AI agents?▼

Yes, you can use Puppeteer for headless browser automation with AI agents, as it provides the necessary Chromium-based dependencies to execute navigation, interaction, and data extraction tasks.

What is deterministic element selection and how does it work for web testing?▼

Deterministic element selection uses refs and accessibility trees to target elements reliably during web testing, ensuring accurate element identification for automating login, form submission, and data scraping tasks.

Does headless browser automation support session management on complex sites?▼

Yes, headless browser automation supports session management on complex or dynamic sites by handling navigation, interaction, and data retrieval, making it suitable for managing automated workflows on large web applications.

Do I need Chromium-based dependencies to perform browser automation tasks?▼

Yes, Chromium-based dependencies or Puppeteer are required to perform browser automation tasks, as they provide the underlying engine necessary for the Skill to execute headless browser operations like navigation and element interaction.