🎯

core

🎯Skill

from vercel-labs/agent-browser

What it does

Browser automation CLI for AI agents, built as a fast native Rust binary. Supports opening pages, taking snapshots, clicking, typing, and extracting content, with automatic detection of existing Chrome, Brave, Playwright, and Puppeteer installations.

📦

Same repository

vercel-labs/agent-browser(11 items)

core

Installation

Vibe Index InstallInstalls to .claude/skills/

npx vibeindex add vercel-labs/agent-browser --skill core

skills.sh Install⚠ Installs to .agents/skills/

npx skills add vercel-labs/agent-browser --skill core

Manual InstallCopy SKILL.md content and save to the path below

~/.claude/skills/core/SKILL.md

SKILL.md

37Installs

AddedMay 8, 2026

View on GitHub Back to Skills

More from this repository10

🎯

agent-browser🎯Skill

Automates web browsing tasks by navigating websites, extracting content, interacting with elements, and capturing screenshots programmatically

🏪

vercel-labs-agent-browser🏪Marketplace

Headless browser automation for AI agents

🎯

dogfood🎯Skill

Systematically explores and tests web applications to find bugs, UX issues, and other problems.

🎯

electron🎯Skill

Skill for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Connects to running Electron apps and controls them programmatically.

🎯

slack🎯Skill

Skill from agent-browser, a headless browser automation CLI for AI agents with a fast Rust binary and Node.js fallback for cross-platform support.

🔌

agent-browser🔌Plugin

A browser automation CLI for AI agents by Vercel Labs, enabling website navigation, form filling, button clicking, screenshot capture, and data extraction through simple commands.

Skill

A concise, practical guide for creating specialized skills that extend Claude's capabilities with domain-specific knowledge and workflows.

🎯

agentcore🎯Skill

Run agent-browser browser automation on AWS Bedrock AgentCore cloud browser sessions, resolving credentials automatically from environment variables or the AWS CLI. All standard agent-browser commands (open, snapshot, click, screenshot, close) work identically — only the browser runtime changes to a managed AWS-hosted session.

🎯

next🎯Skill

Skill