Skip to content
TrustedSkillsbeta
Back to all skills

Web Browser

Checked
mitsuhiko·vlatest·frontend·Apache-2.0

Navigates websites, extracts data, and completes online forms based on provided instructions.

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 mitsuhiko/agent-stuff --skill web-browser -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

mitsuhiko

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 passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • 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 undeclared network calls: passed

    Makes no network calls.

    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.

  • 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 mitsuhiko/agent-stuff at 0865c849be.

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

Commit
0865c849be
Manifest
skills/web-browser/SKILL.md
Scanned
19 files, 2,537 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

The web-browser skill enables AI agents to navigate the internet, load specific URLs, and interact with web pages directly. It allows agents to retrieve real-time information, execute JavaScript within a browser context, and handle dynamic content that static tools cannot access.

When to use it

  • Researching live data such as stock prices, weather conditions, or breaking news.
  • Verifying the existence of specific files or pages on external websites.
  • Interacting with web forms, clicking buttons, or extracting content from dynamic Single Page Applications (SPAs).
  • Debugging frontend code by inspecting rendered DOM elements in a real browser environment.

Key capabilities

  • Navigates to arbitrary URLs provided in prompts.
  • Executes JavaScript within the browser context to manipulate the page state.
  • Renders and parses HTML content for extraction or analysis.
  • Handles dynamic content loading typical of modern web applications.

Example prompts

  • "Visit https://example.com and summarize the latest news articles on the homepage."
  • "Go to a specific product page, click the 'Add to Cart' button, and report the current total price."
  • "Load this URL and extract all email addresses found in the contact section using JavaScript."

Tips & gotchas

Ensure the target website is accessible and does not block automated requests via robots.txt or user-agent restrictions. Complex interactions may require explicit instructions on which elements to click or data to extract, as the agent relies on the rendered page structure.