> ## Documentation Index
> Fetch the complete documentation index at: https://docs.browser-use.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Skills

> Turn any website into a deterministic API endpoint. Create once, call repeatedly.

A skill turns a website interaction into a reusable, reliable API. Describe what you need, Browser Use builds the automation, you call it like a function.

## How skills work

Every skill has two parts:

* **Goal** — the full specification: what parameters it accepts, what data it returns, and the complete scope of work. If you want to extract data from 100 listings, the goal describes extracting from *all* of them.

* **Demonstration** (`agent_prompt`) — shows *how* to perform the task, but only once. Think of it like onboarding a new colleague: you would not walk them through all 100 listings. You would show the first one or two and say "keep going like this for the rest." The demonstration navigates the site, triggers the necessary network requests, and the system builds the actual endpoint logic from that recording.

<Tip>
  The demonstration only needs to trigger the right network requests — it does not need to complete the full task. If extracting from many pages, open the first item and maybe paginate once. The system handles the rest.
</Tip>

## Create a skill

<CodeGroup>
  ```python Python theme={null}
  from browser_use_sdk import AsyncBrowserUse

  client = AsyncBrowserUse()
  skill = await client.skills.create(
      goal="Extract the top X posts from HackerNews. For each post return: title, URL, score, author, comment count, and rank. X is an input parameter.",
      agent_prompt="Go to https://news.ycombinator.com, click on the first post to load its content, go back to the list, and scroll down to trigger loading of additional posts.",
  )
  print(skill.id)
  ```

  ```typescript TypeScript theme={null}
  import { BrowserUse } from "browser-use-sdk";

  const client = new BrowserUse();
  const skill = await client.skills.create({
    goal: "Extract the top X posts from HackerNews. For each post return: title, URL, score, author, comment count, and rank. X is an input parameter.",
    agentPrompt: "Go to https://news.ycombinator.com, click on the first post to load its content, go back to the list, and scroll down to trigger loading of additional posts.",
  });
  console.log(skill.id);
  ```
</CodeGroup>

Skill creation takes \~30 seconds. You can also create skills visually from the [Cloud Dashboard](https://cloud.browser-use.com/skills) — record yourself performing the task, or let the agent demonstrate it.

## Execute a skill

<CodeGroup>
  ```python Python theme={null}
  result = await client.skills.execute(
      skill.id,
      parameters={"X": 10},
  )
  print(result)
  ```

  ```typescript TypeScript theme={null}
  const result = await client.skills.execute(skill.id, {
    parameters: { X: 10 },
  });
  console.log(result);
  ```
</CodeGroup>

## Refine with feedback

If execution is not quite right, iterate for free:

<CodeGroup>
  ```python Python theme={null}
  await client.skills.refine(skill.id, feedback="Also extract the product description and available colors")
  ```

  ```typescript TypeScript theme={null}
  await client.skills.refine(skill.id, {
    feedback: "Also extract the product description and available colors",
  });
  ```
</CodeGroup>

## Marketplace

Browse and use community-created skills.

<CodeGroup>
  ```python Python theme={null}
  skills = await client.marketplace.list()
  my_skill = await client.marketplace.clone(skill_id)
  result = await client.marketplace.execute(skill_id, parameters={...})
  ```

  ```typescript TypeScript theme={null}
  const skills = await client.marketplace.list();
  const mySkill = await client.marketplace.clone(skillId);
  const result = await client.marketplace.execute(skillId, { parameters: { ... } });
  ```
</CodeGroup>

See [Pricing](https://browser-use.com/pricing) for skill costs.