agentleFS
ai-workspace-labai-workspace-lab/xworkspace-core-skills/skills/marketplace/browser-automation/SKILL.md

Browser Automation

Skill8 starsChanged 5 months agoMITView on GitHub

This skill should be used when the user needs to interact with web pages, browse websites, take screenshots, fill forms, click elements, extract web content, or perform any browser automation tasks. Trigger phrases include "open webpage", "visit website", "browse", "screenshot page", "fill form", "click button", "extract from website", "web scraping", "automate browser".

  • Installs packages

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use agent-browser CLI tool for all browser automation tasks.

    line 9
  2. Very specific:

    Check help for more options: Run agent-browser <command> --help for detailed options

    line 82
  3. Distinctive:

    Close when done: Always close the browser to free resources

    line 83
  4. Very specific:

    If agent-browser command not found:

    line 93
  5. Distinctive:

    If browser fails to launch on Linux:

    line 99

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Browser Automation with agent-browser

Use agent-browser CLI tool for all browser automation tasks. This is the preferred method for web interactions.

Important: Command Sequence

Always follow this sequence:

  1. agent-browser launch - Start the browser first
  2. agent-browser open <url> - Navigate to a URL
  3. Perform operations (snapshot, click, type, etc.)
  4. agent-browser close - Close when done

Quick Reference

First, run agent-browser without arguments to see full help:

agent-browser

Essential Commands

CommandDescription
agent-browser launchStart browser (required before open)
agent-browser open <url>Navigate to URL
agent-browser snapshotGet page content as text
agent-browser snapshot -iGet page content with element IDs for interaction
agent-browser screenshotTake screenshot
agent-browser click <selector>Click an element
agent-browser type <selector> <text>Type text into input
agent-browser closeClose browser

Common Workflows

View webpage content:

agent-browser launch
agent-browser open https://example.com
agent-browser snapshot
agent-browser close

Take screenshot:

agent-browser launch
agent-browser open https://example.com
agent-browser screenshot
agent-browser close

Fill form and submit:

agent-browser launch
agent-browser open https://example.com/login
agent-browser snapshot -i  # Get element IDs
agent-browser type "#username" "myuser"
agent-browser type "#password" "mypass"
agent-browser click "#submit"
agent-browser close

Extract data from page:

agent-browser launch
agent-browser open https://example.com/data
agent-browser snapshot  # Returns structured text content
agent-browser close

Tips

  1. Always launch first: agent-browser open will fail if browser isn't launched
  2. Use snapshot -i for interactions: The -i flag shows element IDs needed for click/type
  3. Check help for more options: Run agent-browser <command> --help for detailed options
  4. Close when done: Always close the browser to free resources

When NOT to Use

  • For simple HTTP requests without JavaScript rendering, use curl or WebFetch
  • For API calls, use appropriate HTTP tools
  • agent-browser is for full browser automation with JavaScript support

Troubleshooting

If agent-browser command not found:

npm install -g agent-browser
agent-browser install

If browser fails to launch on Linux:

agent-browser install --with-deps

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.