← Back to Skills

Agent Browser

🌐Community
by m1heng · vlatest · Repository

Automates web browsing tasks like data extraction, form filling, and navigation using intelligent scripting.

Install on your platform

We auto-selected Claude Code based on this skill’s supported platforms.

1

Run in terminal (recommended)

terminal
claude mcp add m1heng-agent-browser npx -- -y @trustedskills/m1heng-agent-browser
2

Or manually add to ~/.claude/settings.json

~/.claude/settings.json
{
  "mcpServers": {
    "m1heng-agent-browser": {
      "command": "npx",
      "args": [
        "-y",
        "@trustedskills/m1heng-agent-browser"
      ]
    }
  }
}

Requires Claude Code (claude CLI). Run claude --version to verify your install.

About This Skill

What it does

The Agent Browser skill enables AI agents to automate web browsing tasks. It allows an agent to navigate websites, interact with page elements (like clicking buttons or filling forms), and extract information from webpages using intelligent scripting based on a snapshot of the current DOM. This facilitates data extraction, form submission, and other repetitive online actions.

When to use it

  • Automating data entry into web forms.
  • Extracting specific data points from multiple web pages.
  • Navigating complex websites with many steps.
  • Simulating user interactions on a website for testing purposes.
  • Downloading files or generating PDFs of webpages.

Key capabilities

  • Navigation: Open URLs, go back/forward, reload pages, and close the browser window.
  • Snapshotting: Capture the page's accessibility tree (full or interactive elements only) to identify elements for interaction.
  • Element Interaction: Click, double-click, focus on, fill in, type into, check/uncheck checkboxes, select dropdown options, and drag & drop elements using references obtained from snapshots.
  • Information Extraction: Retrieve text content, HTML, input values, attributes, page titles, URLs, bounding boxes, and computed styles of elements.
  • State Checking: Verify if an element is visible, enabled, or checked.
  • Screenshots & PDF Generation: Capture screenshots of the current webpage.

Example prompts

  • "agent-browser open https://www.example.com"
  • "agent-browser snapshot -i; agent-browser fill @e2 'my_username'; agent-browser click @e1"
  • "agent-browser get title"

Tips & gotchas

  • The skill relies on "snapshots" to identify elements. Significant DOM changes after a snapshot may require another snapshot to be taken.
  • Element references (like @e1, @e2) are obtained from the output of agent-browser snapshot -i.
  • Supports various URL protocols: https://, http://, file://, about:, and data://. If no protocol is provided, it will assume https://.
View Repository →

Tags

🛡️

TrustedSkills Verification

Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.

Security Audits

Gen Agent Trust HubPass
SocketPass
SnykPass

Details

Version
vlatest
License
Author
m1heng
Installs
41
Repository (canonical source) →

🌐 Community

Passed automated security scans.