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.
What this skill does
# 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
```python
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
```bash
pip install browser-use
playwright install
```
## Best Practices
1. **Vision model** — Use GPT-4o or Claude for best browser understanding; sees screenshots + DOM
2. **Structured output** — Pass `output_model` for typed extraction; Pydantic validation on results
3. **Headless mode** — Use `headless=True` for server/CI; `False` for debugging to watch the agent
4. **Cookies/auth** — Pre-set cookies for authenticated sessions; agent operates as logged-in user
5. **Task decomposition** — Write tasks as numbered steps for complex flows; agent follows the sequence
6. **Proxy support** — Use proxies for scraping at scale; rotate IPs to avoid blocks
7. **Retry on failure** — Browser Use auto-retries failed interactions; configure max attempts
8. **Combine with APIs** — Use browser for sites without APIs; prefer APIs when available (faster, cheaper)
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.