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

# Recording a Skill with the No-Code Browser Recorder

> The fastest way to build a Skill on Valendata is to record a live session. Enable the Record Skill toggle in the chat input area, walk through the task yourself in the managed browser, and Valendata captures your actions as a reusable Config — which you then publish as a callable API endpoint.

## Before you start

* A Valendata account at [app.valendata.com](http://app.valendata.com)
* The URL of the site you want to automate
* Any login credentials the task requires

## Recording walkthrough

<Steps>
  <Step title="Enable recording">
    Open a new session from the main dashboard. In the chat input area, find the **Record Skill** toggle and switch it on. It will show **Recording...** to confirm it is active.
  </Step>

  <Step title="Walk through the workflow">
    Type your task or navigate the browser yourself. Perform every action that makes up the workflow — logging in, navigating, filling forms, clicking through pagination, and reaching the data you want extracted. Valendata records every interaction in real time.

    <Note>
      If the site uses CAPTCHA or 2FA, Valendata handles both natively during recording and on every subsequent run.
    </Note>
  </Step>

  <Step title="End the session">
    When you have completed the full workflow, stop the session. Valendata saves your recording as a **Config** automatically.
  </Step>

  <Step title="Publish the Config as a Skill">
    Navigate to **Configs** in the sidebar and open the Config you just recorded. Click **Publish as skill**, give your Skill a name and description, set visibility, and click **Publish Skill**. Your Skill is now live as a versioned API endpoint.
  </Step>

  <Step title="Review parameters and output schema">
    Open the published Skill and go to the **Workspace** tab. Use the **Suggest** button to auto-detect input parameters and output fields from the recording. Review, rename, and adjust them as needed before making your first API call.
  </Step>
</Steps>

## Calling your Skill via API

```bash theme={null}
curl -X POST https://api.valendata.com/v1/skills/run \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"skill_id": "YOUR_SKILL_ID", "parameters": {"query": "standing desk"}}'
```

Find your API key under **Settings → API Keys**.

## After publishing

<CardGroup cols={2}>
  <Card title="Schedule it" icon="clock">
    Run the Skill automatically on a cron — hourly, daily, weekly, or a custom expression.
  </Card>

  <Card title="Chain it in a Workflow" icon="diagram-project">
    Compose your Skill with HTTP steps, transforms, and other Skills to build end-to-end data pipelines.
  </Card>

  <Card title="Attach a Chrome Profile" icon="user-shield">
    Save your logged-in browser session so every run starts already authenticated.
  </Card>

  <Card title="Share to Marketplace" icon="store">
    Publish your Skill to the public Marketplace so others can clone and build on it.
  </Card>
</CardGroup>