> ## Documentation Index
> Fetch the complete documentation index at: https://browseruse-0aece648-mintlify-cli-docs-1773354647.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Basics

> Skills are your API for anything. Describe what you need in plain text, and get a production-ready API endpoint you can call repeatedly.

To learn more visit [Skills - Concepts](/cloud/guides/skills).

## Quick Example

Load `['*']` for all skills or specific skill IDs from [cloud.browser-use.com/skills](https://cloud.browser-use.com/skills).

```python theme={null}
from browser_use import Agent, ChatBrowserUse

agent = Agent(
    task='Your task',
    skills=['skill-uuid-1', 'skill-uuid-2'],  # Specific skills (recommended)
    # or
    # skills=['*'],  # All skills
    llm=ChatBrowserUse()
)

await agent.run()
```

<Info>
  Be careful using `*`. Each skill will contribute around 200 tokens to the prompt.
</Info>

Remember to add your API key to `.env`:

```bash .env theme={null}
BROWSER_USE_API_KEY=your-api-key
```

<Note>
  Get your API key on [cloud](https://cloud.browser-use.com/new-api-key) - new signups get \$10 free.
</Note>

## Cookie Handling

Cookies are automatically injected from your browser:

```python theme={null}
agent = Agent(
    task='Post a tweet saying "Hello World"',
    skills=['tweet-poster-skill-id'],
    llm=ChatBrowserUse()
)

# Agent navigates to twitter.com, logs in if needed,
# extracts cookies, and passes them to the skill automatically
await agent.run()
```

If cookies are missing, the LLM sees which cookies are needed and navigates to obtain them.

***

## Full Example

```python theme={null}
from browser_use import Agent, ChatBrowserUse
from dotenv import load_dotenv
import asyncio

load_dotenv()

async def main():
    agent = Agent(
        task='Analyze TikTak and Instegram profiles',
        skills=[
            'a582eb44-e4e2-4c55-acc2-2f5a875e35e9',  # TikTak Profile Scraper
            'f8d91c2a-3b4e-4f7d-9a1e-6c8e2d3f4a5b',  # Instegram Profile Scraper
        ],
        llm=ChatBrowserUse()
    )

    await agent.run()
    await agent.close()

asyncio.run(main())
```

Browse and create skills at [cloud.browser-use.com/skills](https://cloud.browser-use.com/skills).