Skip to content
TrustedSkillsbeta
Back to all skills

Claude Browser

Checked
cleanexpo·vlatest·ai-ml·MIT

Claude Browser allows you to seamlessly access and integrate web content into your Claude conversations, boosting research & creative output.

Repository

Install on your platform

This skill no longer installs under the name claude-browser. cleanexpo/nodejs-starter-v1 is deleted or private, so it cannot be installed from.

We check each listing against its upstream repository with the rules the skills CLI uses, last on 2026-10-22. We don't show a command we know will fail.

Repository install instructions

What we know about this skill

Publisher

cleanexpo

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 cleanexpo/nodejs-starter-v1 at 7b45925bd4.

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

Commit
7b45925bd4
Manifest
.skills/custom/claude-browser/SKILL.md
Scanned
1 file, 129 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

The claude-browser skill allows an AI agent to access and interact with web pages. It leverages Claude's browsing capabilities, enabling agents to retrieve information from URLs provided by the user or discovered during task execution. This facilitates tasks requiring real-time data, research, or interaction with online services.

When to use it

  • Research: Gathering information on a specific topic from multiple websites.
  • Data Extraction: Scraping data (e.g., product prices, news headlines) from web pages.
  • Web Interaction: Filling out forms or interacting with elements on a website.
  • Real-time Updates: Accessing the latest information from dynamic websites like news sites or stock trackers.

Key capabilities

  • Accesses and retrieves content from URLs.
  • Utilizes Claude's browsing functionality.
  • Supports interaction with web pages.

Example prompts

  • "Browse to https://www.example.com and summarize the main points."
  • "Find me the current price of Bitcoin on a reputable financial website."
  • "Go to this URL: https://forms.example/contact and fill out the form with these details..."

Tips & gotchas

  • Ensure the URLs provided are accessible and valid for Claude's browsing capabilities.
  • Be mindful of potential rate limits or terms of service restrictions when scraping data from websites.