agent-browser

The agent-browser CLI provides browser automation for AI agents using Chrome or Chromium via CDP. It supports page navigation, form interaction, data extraction, and testing. The tool utilizes accessibility-tree snapshots and element references for interaction.

506.7K
Installs
5
Use cases
9/10
Quality

Is agent-browser safe to install?

Review the source first

Review the source first: our audit of agent-browser's source files found 9 shell commands, 1 external URL, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The tool executes shell commands, performs network requests, and manages browser sessions, authentication, and state persistence.

How we audit skills: our security review methodology.

Who is this skill for?

AI agents and developers requiring programmatic web interaction, exploratory testing, or automation of Electron desktop applications.

What can you do with it?

  • Navigating websites and filling forms
  • Extracting data from web pages
  • Automating Electron desktop applications like Slack, VS Code, and Discord
  • Performing exploratory testing and QA bug hunts
  • Running browser automation within Vercel Sandbox microVMs or AWS Bedrock AgentCore

How good is this skill?

Quality score: 9/10. The documentation is clear and provides specific commands for discovery and usage. It explicitly defines the tool's scope and dependencies.

What does the skill file contain?

SKILL.md
# agent-browser

Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with accessibility-tree snapshots and compact `@eN` element refs.

Install: `npm i -g agent-browser && agent-browser install`

## Start here

This file is a discovery stub, not the usage guide. Before running any `agent-browser` command, load the actual workflow content from the CLI:

```bash
agent-browser skills get core             # start here — workflows, common patterns, troubleshooting
agent-browser skills get core --full      # include full command reference and templates
```

The CLI serves skill conten...

Frequently asked questions

How does the tool interact with web elements?

It uses accessibility-tree snapshots and compact element references to identify and interact with page elements.

Can this tool automate desktop applications?

Yes, it supports Electron-based desktop applications such as Slack, VS Code, Discord, Figma, Notion, and Spotify.

Where can I find detailed usage instructions?

Run 'agent-browser skills get core' or 'agent-browser skills get core --full' in the CLI to retrieve current workflows and command references.

Data sourced from vercel-labs/agent-browser on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills

find-skills

2.3M

Users seeking to extend agent capabilities with specialized tools, workflows, or knowledge packages

The find-skills skill enables agents to search for, discover, and install modular packages from the open agent skills ecosystem using the Skills CLI.

highclipackage-managervercel-labs

video-edit

338.7K

Users of the RunComfy CLI who need to automate video editing tasks like restyling, background swapping, or motion transfer

The video-edit skill acts as a router for the RunComfy CLI, selecting between Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, and Lucy Edit Restyle models based on user intent to perform video transformations.

highvideo-editingai-agentagentspace-so

agentspace

324.0K

Developers and AI agent users who need to share, monitor, or collaborate on agent-generated files and workspaces in real-time

Agentspace provides a mechanism to share local agent files, logs, and artifacts via a live browser-accessible URL. It enables remote viewing, commenting, and editing of specified local paths through the ascli command-line tool.

highcollaborationfile-sharingagentspace-so

ai-image-generation

229.9K

Developers and AI agents requiring programmatic access to diverse image generation and editing models through a unified CLI

The AI Image Generation skill provides a command-line interface for generating and editing images using the RunComfy platform. It routes requests across 11+ AI models, including FLUX 2, Google Nano Banana, OpenAI GPT Image 2, ByteDance Seedream, Alibaba Qwen, and Wan 2-7. The skill selects the appropriate model based on user intent, such as typography precision, photorealism, or speed, and executes the generation via the runcomfy CLI.

highimage-generationcliruncomfy-com