agent-browserby VercelOfficialAutomationGitHub stars: 43.4k
Agent Browser skill: what it does and how to install it
A browser automation CLI for AI agents: navigate pages, fill forms, click buttons, take screenshots and extract data.
Install
$ npx skills add vercel-labs/agent-browserRun it in a terminal. If your agent is already running, start a new session so it picks the skill up.
About this skill
What it does. Points the agent at agent-browser, a browser automation CLI built for AI agents. It drives Chrome over CDP with accessibility-tree snapshots and compact element refs. This skill is a discovery stub: the usage guide is loaded from the CLI itself (agent-browser skills get core), so the instructions always match the installed version.
When to use it. When the agent needs to navigate pages, fill forms, click buttons, take screenshots, extract data or test a web app.
Similar skills
- PlaywrightAutomates a real browser from the terminal with playwright-cli: navigation, forms, snapshots, screenshots and data extraction.
- Firecrawl InteractDrives a live browser on a scraped page with Firecrawl: click, fill forms, log in and paginate.
- Browser UseControls a browser directly over CDP for automation, scraping, testing and screenshots.