Skip to content
TrustedSkillsbeta
Back to all skills

Browser Tools

Listed
badlogic·vlatest·frontend·MIT

This skill allows you to interact with your browser – navigating, executing JavaScript, and retrieving content – for powerful automation tasks.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add badlogic/pi-skills --skill browser-tools -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

badlogic

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 5 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: en.wikipedia.org, feross.org, news.ycombinator.com, opencollective.com, www.patreon.com.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    en.wikipedia.orgundeclarednews.ycombinator.comundeclaredgithub.comsource hostopencollective.comundeclaredwww.patreon.comundeclaredfeross.orgundeclared

    What it found (3 of 15)

    • browser-tools/browser-content.js:23contacts en.wikipedia.org
      console.log("  browser-content.js https://en.wikipedia.org/wiki/Rust_(programming_language)");
    • browser-tools/browser-hn-scraper.js:18contacts news.ycombinator.com
      const url = 'https://news.ycombinator.com';
    • browser-tools/browser-hn-scraper.js:75contacts news.ycombinator.com
      hnUrl: `https://news.ycombinator.com/item?id=${id}`

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned badlogic/pi-skills at 90bb51cae3.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
90bb51cae3
Manifest
browser-tools/SKILL.md
Scanned
11 files, 3,377 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill provides tools for interacting with a Chrome browser running in remote debugging mode. It allows an AI agent to navigate web pages, execute JavaScript code within those pages, capture screenshots, extract page content, and inspect cookies. The tool connects to Chrome on port :9222, requiring specific setup steps including installing dependencies and launching Chrome with the correct flags.

When to use it

  • When you need an AI agent to interact with a web application, such as clicking buttons or filling out forms.
  • To extract data from websites programmatically when direct API access isn't available.
  • For visually inspecting a webpage state or verifying UI changes using screenshots.
  • When needing to debug authentication issues by examining browser cookies.
  • To allow users to select specific DOM elements on a page through an interactive picker, enabling the agent to then perform actions on those elements.

Key capabilities

  • Navigation: Open URLs in new or existing Chrome tabs.
  • JavaScript Execution: Execute JavaScript code within the active tab for data extraction and DOM manipulation.
  • Screenshot Capture: Capture screenshots of the current viewport.
  • Element Selection (Pick Elements): Interactive element selection via a user interface, returning CSS selectors.
  • Cookie Inspection: Display cookies associated with the current tab.
  • Content Extraction: Extract content from the active webpage.

Example prompts

  • "Navigate to example.com and get the page title."
  • "Execute 'document.querySelectorAll("a").length' on the current page."
  • "Take a screenshot of the current page."
  • "I want to click that button" (This would trigger the interactive element picker).

Tips & gotchas

  • Chrome Setup: Requires Chrome running with remote debugging enabled on port :9222. Use --profile flag when launching Chrome to preserve user authentication state.
  • Dependencies: You must run npm install within the skill's directory before first use.
  • JavaScript Context: JavaScript code runs in an asynchronous context.