← ClaudeAtlas

browser-uselisted

AI browser automation agent — navigate websites, fill forms, extract data, click elements, search the web, take screenshots, download files, and automate any browser task using natural language. Uses anthropic/claude-sonnet-4.6 via OpenRouter with Playwright Chromium. Use when asked to browse websites, scrape data, fill web forms, automate repetitive browser tasks, search and extract information from web pages, or interact with any web application programmatically.
DrOlu/agent-skills · ★ 0 · AI & Automation · score 60
Install: claude install-skill DrOlu/agent-skills
# Browser-Use AI-powered browser automation. The agent sees the page, decides what to do, and acts — all from a natural language task description. ## Architecture ``` Task (natural language) → LLM (anthropic/claude-sonnet-4.6 via OpenRouter) → Action Plan → Playwright Chromium (headless) → DOM snapshot → LLM evaluates → Next action → ... → Done ``` ## Quick Usage ### Basic agent (one-liner in Python) ```python import asyncio from langchain_openai import ChatOpenAI from browser_use import Agent, Browser llm = ChatOpenAI( model='anthropic/claude-sonnet-4.6', base_url='https://openrouter.ai/api/v1', api_key=os.getenv('OPENROUTER_API_KEY'), ) agent = Agent( task='Go to hackernews and find the top 5 stories', llm=llm, use_vision=True, # claude-sonnet-4.6 supports vision ) agent.run_sync() ``` ### With explicit browser config ```python from browser_use import Agent, Browser, BrowserConfig browser = Browser(config=BrowserConfig( headless=True, disable_security=True, )) agent = Agent( task='Login to example.com with user x and pass y', llm=llm, browser=browser, use_vision=True, ) await agent.run(max_steps=25) ``` ## Model Configuration The skill is pre-configured for **anthropic/claude-sonnet-4.6** via **OpenRouter**: ```python from langchain_openai import ChatOpenAI import os llm = ChatOpenAI( model='anthropic/claude-sonnet-4.6', base_url='https://openrouter.ai/api/v1', api_key=os.getenv('OPENROUTER_API_KEY