vercel-labs agent-browser
COMMUNITYLABSCO SUMMARY
The core skill documents agent-browser's snapshot-and-ref workflow — open a page, take an accessibility-tree snapshot, then click, fill, or read elements by the refs it returns — plus screenshots, PDF export, batch execution, and a natural-language chat mode. The other six skills are each a guide to running that same CLI in one specific place: inside Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify) over Chrome DevTools Protocol, inside a Vercel Sandbox microVM, against a Slack workspace, or on AWS Bedrock AgentCore's cloud browsers. dogfood is the one skill that is a workflow rather than a place: point it at your own app and it produces a bug report with reproduction screenshots and video.
This suits a developer or agent that has already decided to use agent-browser and needs to know which of its surfaces applies to the job at hand — VS Code automation, a Vercel deployment, an AWS-hosted session, or a Slack task. It is not a general browser-automation primer; the assumption throughout is that agent-browser itself is the tool, installed via npm, Homebrew, or Cargo, with its own bundled Chrome for Testing binary rather than your system Chrome.
READ THE FULL ANALYSIS
What it costs you to start. Five of the seven skills need nothing beyond the CLI's own installer, which downloads that private Chrome build the first time you run agent-browser install. The other two want more: AgentCore needs AWS credentials for its managed cloud browsers, and the Vercel Sandbox path needs a Vercel account to run the microVM. Linux users also need the installer's --with-deps flag for the browser's system libraries, which it checks for and fails on loudly rather than silently.
One structural note. Six of the seven skills exist because agent-browser runs in six different places, not because they teach six different tasks — read core first regardless of which environment you land on, since it is the only one that explains the ref-based interaction model the other six assume you already know.
ALSO IN THIS PACKAGE
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction
WHAT'S INSIDE
7 showing · 7 totalagent-browser
The front door to agent-browser, a tool that lets an AI drive a real web browser: install it here, then follow the pointer to whichever set of instructions your task needs.
agentcore
Same commands as always, except the browser itself runs on Amazon's machines rather than on your own, with your existing AWS login used as it stands.
core
How an AI actually works a website: open the page, get back a short list of what is on it, then click, type and read by pointing at items in that list.
dogfood
Point it at a website and it goes through the thing like a tester would, writing down every bug it hits with a screenshot or a video proving it happens.
electron
Apps like Slack, VS Code and Figma are really web pages in a window, which means the same browser automation can click around inside them once they are started in the right mode.
slack
Reading and acting on Slack through the ordinary Slack website, the way a person does — so nothing has to be registered with Slack first, and it sees exactly what your own account sees.
vercel-sandbox
A website that needs to open other websites — to take a screenshot, or fill in a form — can start a throwaway machine with a browser on it, do the job, and shut it down again.
HOW TO GET IT
npx skills add vercel-labs/agent-browsernpx skills add vercel-labs/agent-browser --skill <name> --full-depthPick the skill name from the Skills tab — each entry there installs independently.
/plugin marketplace add vercel-labs/agent-browser/plugin install agent-browser@agent-browserTyped inside the agent's own prompt, not in a terminal. The marketplace is called agent-browser, which is the part after the @.