Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →vercel-labs/vercel-sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app.
Passed 22 of 22 test cases with the skill, and 10 of 22 without it.
and 15 more in the full report
12 fixed10 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
When taking a screenshot using runAgentBrowserCommand with JSON output enabled, which field in the returned JSON structure holds the image file path?
| Checked | Without skill | With skill |
|---|---|---|
| Extracts path from json.data.path in the response object. | Missed | Passed |
The instructions your model reads when the skill loads.
Run agent-browser + headless Chrome inside ephemeral Vercel Sandbox microVMs. A Linux VM spins up on demand, executes browser commands, and shuts down. Works with any Vercel-deployed framework (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.).
pnpm add @agent-browser/sandbox @vercel/sandbox
The sandbox VM needs system dependencies for Chromium plus agent-browser itself. The @agent-browser/sandbox helpers install them by default for fresh sandboxes and use sandbox snapshots (below) for sub-second startup. Pass installSystemDependencies: false only when the sandbox image already provides Chromium's required libraries.
import {
createAgentBrowserSnapshot,
runAgentBrowserCommand,
withAgentBrowserSandbox,
type VercelSandboxSession,
} from "@agent-browser/sandbox/vercel";
async function withBrowser<T>(
fn: (sandbox: VercelSandboxSession) => Promise<T>,
): Promise<T> {
return withAgentBrowserSandbox(fn);
}
The screenshot --json command saves to a file and returns the path. Read the file back as base64:
export async function screenshotUrl(url: string) {
return withBrowser(async (sandbox) => {
await runAgentBrowserCommand(sandbox, ["open", url]);
const titleResult = await runAgentBrowserCommand<{ data?: { title?: string } }>(sandbox, [
"get", "title",
test cases passed, vs 10 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.