Get the FREE Ultimate OpenClaw Setup Guide →
p

Functions

Scanned

@peytoncasper

npx machina-cli add skill @peytoncasper/functions --openclaw
Files (1)
SKILL.md
6.7 KB

Browserbase Functions Skill

Guide Claude through deploying serverless browser automation using the official bb CLI.

When to Use

Use this skill when:

  • User wants to deploy automation to run on a schedule
  • User needs a webhook endpoint for browser automation
  • User wants to run automation in the cloud (not locally)
  • User asks about Browserbase Functions

Prerequisites

1. Get Credentials

Get API key and Project ID from: https://browserbase.com/settings

2. Set Environment Variables

Set directly:

export BROWSERBASE_API_KEY="your_api_key"
export BROWSERBASE_PROJECT_ID="your_project_id"

Creating a Function Project

1. Initialize with Official CLI

pnpm dlx @browserbasehq/sdk-functions init my-function
cd my-function

This creates:

my-function/
├── package.json
├── index.ts        # Your function code
└── .env            # Add credentials here

2. Add Credentials to .env

# Copy from stored credentials
echo "BROWSERBASE_API_KEY=$BROWSERBASE_API_KEY" >> .env
echo "BROWSERBASE_PROJECT_ID=$BROWSERBASE_PROJECT_ID" >> .env

Or manually edit .env:

BROWSERBASE_API_KEY=your_api_key
BROWSERBASE_PROJECT_ID=your_project_id

3. Install Dependencies

pnpm install

Function Structure

import { defineFn } from "@browserbasehq/sdk-functions";
import { chromium } from "playwright-core";

defineFn("my-function", async (context) => {
  const { session, params } = context;
  
  // Connect to browser
  const browser = await chromium.connectOverCDP(session.connectUrl);
  const page = browser.contexts()[0]!.pages()[0]!;
  
  // Your automation
  await page.goto(params.url || "https://example.com");
  const title = await page.title();
  
  // Return JSON-serializable result
  return { success: true, title };
});

Key objects:

  • context.session.connectUrl - CDP endpoint to connect Playwright
  • context.params - Input parameters from invocation

Development Workflow

1. Start Dev Server

pnpm bb dev index.ts

Server runs at http://127.0.0.1:14113

2. Test Locally

curl -X POST http://127.0.0.1:14113/v1/functions/my-function/invoke \
  -H "Content-Type: application/json" \
  -d '{"params": {"url": "https://news.ycombinator.com"}}'

3. Iterate

The dev server auto-reloads on file changes. Use console.log() for debugging - output appears in the terminal.

Deploying

Publish to Browserbase

pnpm bb publish index.ts

Output:

Function published successfully
Build ID: xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
Function ID: xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx

Save the Function ID - you need it to invoke.

Invoking Deployed Functions

Via curl

# Start invocation
curl -X POST "https://api.browserbase.com/v1/functions/FUNCTION_ID/invoke" \
  -H "Content-Type: application/json" \
  -H "x-bb-api-key: $BROWSERBASE_API_KEY" \
  -d '{"params": {"url": "https://example.com"}}'

# Response: {"id": "INVOCATION_ID"}

# Poll for result
curl "https://api.browserbase.com/v1/functions/invocations/INVOCATION_ID" \
  -H "x-bb-api-key: $BROWSERBASE_API_KEY"

Via Code

async function invokeFunction(functionId: string, params: object) {
  // Start invocation
  const invokeRes = await fetch(
    `https://api.browserbase.com/v1/functions/${functionId}/invoke`,
    {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'x-bb-api-key': process.env.BROWSERBASE_API_KEY!,
      },
      body: JSON.stringify({ params }),
    }
  );
  const { id: invocationId } = await invokeRes.json();

  // Poll until complete
  while (true) {
    await new Promise(r => setTimeout(r, 5000));
    
    const statusRes = await fetch(
      `https://api.browserbase.com/v1/functions/invocations/${invocationId}`,
      { headers: { 'x-bb-api-key': process.env.BROWSERBASE_API_KEY! } }
    );
    const result = await statusRes.json();
    
    if (result.status === 'COMPLETED') return result.results;
    if (result.status === 'FAILED') throw new Error(result.error);
  }
}

Common Patterns

Parameterized Scraping

defineFn("scrape", async ({ session, params }) => {
  const browser = await chromium.connectOverCDP(session.connectUrl);
  const page = browser.contexts()[0]!.pages()[0]!;
  
  await page.goto(params.url);
  await page.waitForSelector(params.selector);
  
  const items = await page.$$eval(params.selector, els => 
    els.map(el => el.textContent?.trim())
  );
  
  return { url: params.url, items };
});

With Authentication

defineFn("authenticated-action", async ({ session, params }) => {
  const browser = await chromium.connectOverCDP(session.connectUrl);
  const page = browser.contexts()[0]!.pages()[0]!;
  
  // Login
  await page.goto("https://example.com/login");
  await page.fill('[name="email"]', params.email);
  await page.fill('[name="password"]', params.password);
  await page.click('button[type="submit"]');
  await page.waitForURL('**/dashboard');
  
  // Do authenticated work
  const data = await page.textContent('.user-data');
  return { data };
});

Error Handling

defineFn("safe-scrape", async ({ session, params }) => {
  const browser = await chromium.connectOverCDP(session.connectUrl);
  const page = browser.contexts()[0]!.pages()[0]!;
  
  try {
    await page.goto(params.url, { timeout: 30000 });
    await page.waitForSelector(params.selector, { timeout: 10000 });
    
    const data = await page.textContent(params.selector);
    return { success: true, data };
  } catch (error) {
    return { 
      success: false, 
      error: error instanceof Error ? error.message : 'Unknown error' 
    };
  }
});

CLI Reference

CommandDescription
pnpm dlx @browserbasehq/sdk-functions init <name>Create new project
pnpm bb dev <file>Start local dev server
pnpm bb publish <file>Deploy to Browserbase

Troubleshooting

"Missing API key"

# Check .env file has credentials
cat .env

# Or set for current shell
export BROWSERBASE_API_KEY="your_key"
export BROWSERBASE_PROJECT_ID="your_project"

Dev server won't start

# Make sure SDK is installed
pnpm add @browserbasehq/sdk-functions

# Or use npx
npx @browserbasehq/sdk-functions dev index.ts

Function times out

  • Max execution time is 15 minutes
  • Add specific timeouts to page operations
  • Use waitForSelector instead of sleep

Can't connect to browser

  • Check session.connectUrl is being used correctly
  • Ensure you're using chromium.connectOverCDP() not chromium.launch()

Source

git clone https://clawhub.ai/peytoncasper/functionsView on GitHub

Overview

The Browserbase Functions skill guides you to deploy serverless browser automation using the official bb CLI. It covers initializing a function project, wiring credentials, running a dev server, and publishing or invoking the function in the cloud. This enables cloud-based browser tasks, webhook endpoints, and scheduled runs without local execution.

How This Skill Works

You create a function with defineFn from the Browserbase SDK, connect a Playwright session over CDP using context.session.connectUrl, perform browser actions, and return a JSON-serializable result. The bb CLI handles packaging, deployment, and remote invocation, while you test locally with the dev server and invoke the deployed function via API or curl using the function ID.

When to Use It

  • Deploy automation to run on a schedule
  • Provide a webhook endpoint for browser automation
  • Run automation in the cloud (not locally)
  • Developers want to understand Browserbase Functions
  • Need a reusable browser automation function accessible via API

Quick Start

  1. Step 1: Initialize with Official CLI: pnpm dlx @browserbasehq/sdk-functions init my-function; cd my-function
  2. Step 2: Add credentials to .env (or export BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID)
  3. Step 3: Install dependencies and start local dev: pnpm install && pnpm bb dev index.ts

Best Practices

  • Store credentials in a secure .env file or environment variables (BROWSERBASE_API_KEY, BROWSERBASE_PROJECT_ID) and do not hard-code them
  • Test locally with the dev server before publishing to catch issues early
  • Limit permissions and rotate API keys; protect your function IDs and endpoints
  • Validate and sanitize input params, add timeouts, and implement robust error handling
  • Add meaningful logging and monitor invocations to diagnose failures quickly

Example Use Cases

  • Schedule a daily page title fetch for a target site and log results
  • Webhook-triggered page interaction (e.g., fill and submit a form) via an HTTP request
  • Cloud-based rendering for SEO previews of dynamic pages
  • On-demand data extraction from a dynamic page and return structured data
  • Periodic health checks of a live page with status reporting

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers