# Agent Skills

Oxylabs Agent Skills (`skills.md`) teach LLMs and AI coding assistants how to configure and interact with Oxylabs products.

Agent Skills for Oxylabs Headless Browser will help your model control remote headless browser sessions via Chrome DevTools Protocol (CDP), configure browser fingerprints, handle proxy rotation, and manage Playwright or Puppeteer automation without syntax or parameter hallucinations.

## Installation

### Claude Code (plugin marketplace)

Inside Claude Code, run the following commands:

```
/plugin marketplace add oxylabs/agent-skills
/plugin install oxylabs@oxylabs-agent-skills
```

This installs all 5 skills as a single plugin:

* [`skills/proxies`](https://github.com/oxylabs/agent-skills/blob/main/skills/proxies/SKILL.md)
* [`skills/web-unblocker`](https://github.com/oxylabs/agent-skills/blob/main/skills/web-unblocker/SKILL.md)
* [`skills/web-scraper-api`](https://github.com/oxylabs/agent-skills/blob/main/skills/web-scraper-api/SKILL.md)
* [`skills/headless-browser`](https://github.com/oxylabs/agent-skills/blob/main/skills/headless-browser/SKILL.md)
* [`skills/video-data`](https://github.com/oxylabs/agent-skills/blob/main/skills/video-data/SKILL.md)

To update skills, run this command:

```
/plugin marketplace update oxylabs-agent-skills
```

### Other agents (generic)

For other agents and custom environments, load the repository into your project workspace via the standard skills CLI:

```
npx skills add https://github.com/oxylabs/agent-skills.git
```

## Configuration

All Oxylabs Agent Skills authenticate via environment variables defined in a `.env` file. To use Headless Browser skills, add these keys to your `.env` file:

| Variable          | Description                            |
| ----------------- | -------------------------------------- |
| `OXY_HB_USERNAME` | Your Headless Browser user `username`. |
| `OXY_HB_PASSWORD` | Your Headless Browser user `password`. |

## How to use

Once the skill is active in your workspace, you can prompt your AI assistant to build automated browser interactions using Oxylabs Headless Browser.

* **Example 1:** "Write a Python script using `playwright` to connect via CDP to Oxylabs Headless Browser, navigate to a dynamic JavaScript site, and extract the rendered HTML."
* **Example 2:** "Create a Node.js script using `puppeteer` that initializes a stealth Firefox browser session via Oxylabs Headless Browser from `US` geo-location."
* **Example 3:** "Generate a browser automation routine that opens `example.com`, interacts with dynamic elements on the page, and saves a full-page screenshot."

## More Oxylabs Agent Skills

Learn more about Agent Skills for other Oxylabs solutions:

* [Proxies](/products/proxies/residential-proxies/agent-skills.md)
* [Web Scraper API](/products/web-scraper-api/solutions-for-ai-workflows/agent-skills.md)
* [Web Unblocker](/products/web-unblocker/agent-skills.md)
* [Video Data](/products/proxies/high-bandwidth-proxies.md#agent-skills)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://developers.oxylabs.io/products/headless-browser/ai-workflows/agent-skills.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.