Agent skill
browser-use
You are an expert in Browser Use, the Python library that lets AI agents control a web browser. You help developers build agents that can navigate websites, fill forms, click buttons, extract data, and complete multi-step web tasks — using vision and DOM understanding to interact with any website like a human would.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/browser-use-terminalskills-skills
Metadata
Additional technical details for this skill
- tags
-
browser automation agent web scraping ai playwright
- author
- terminal-skills
- version
- 1.0.0
- category
- AI & Machine Learning
SKILL.md
Browser Use — AI Browser Automation Agent
You are an expert in Browser Use, the Python library that lets AI agents control a web browser. You help developers build agents that can navigate websites, fill forms, click buttons, extract data, and complete multi-step web tasks — using vision and DOM understanding to interact with any website like a human would.
Core Capabilities
from browser_use import Agent
from langchain_openai import ChatOpenAI
agent = Agent(
task="Go to amazon.com, search for 'mechanical keyboard', and find the best-rated one under $100",
llm=ChatOpenAI(model="gpt-4o"),
)
result = await agent.run()
print(result) # "The best-rated mechanical keyboard under $100 is..."
# Multi-step tasks
agent = Agent(
task="""
1. Go to github.com/myorg/myrepo
2. Click on Issues tab
3. Create a new issue with title 'Update dependencies' and body 'Run npm audit fix'
4. Add the label 'maintenance'
""",
llm=ChatOpenAI(model="gpt-4o"),
)
await agent.run()
# With custom browser config
from browser_use import BrowserConfig
config = BrowserConfig(
headless=True,
proxy="http://proxy:8080",
cookies=[{"name": "session", "value": "abc123", "domain": ".example.com"}],
)
agent = Agent(task="...", llm=llm, browser_config=config)
# Extract structured data
from pydantic import BaseModel
class Product(BaseModel):
name: str
price: float
rating: float
agent = Agent(
task="Go to bestbuy.com and find the top 5 laptops. Return structured data.",
llm=ChatOpenAI(model="gpt-4o"),
output_model=list[Product],
)
result = await agent.run()
# result is list[Product] — validated Pydantic objects
Installation
pip install browser-use
playwright install
Best Practices
- Vision model — Use GPT-4o or Claude for best browser understanding; sees screenshots + DOM
- Structured output — Pass
output_modelfor typed extraction; Pydantic validation on results - Headless mode — Use
headless=Truefor server/CI;Falsefor debugging to watch the agent - Cookies/auth — Pre-set cookies for authenticated sessions; agent operates as logged-in user
- Task decomposition — Write tasks as numbered steps for complex flows; agent follows the sequence
- Proxy support — Use proxies for scraping at scale; rotate IPs to avoid blocks
- Retry on failure — Browser Use auto-retries failed interactions; configure max attempts
- Combine with APIs — Use browser for sites without APIs; prefer APIs when available (faster, cheaper)
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?