Skip to content
TrustedSkillsbeta
Back to all skills

Agent Browser

Checked
shanraisshan·vlatest·agents·MIT

Automates web browsing tasks like data extraction, form filling, and navigation 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 shanraisshan/claude-code-best-practice --skill agent-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

shanraisshan

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 shanraisshan/claude-code-best-practice at bfcf0b5abc.

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

Commit
bfcf0b5abc
Manifest
.claude/skills/agent-browser/SKILL.md
Scanned
1 file, 194 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 shanraisshan-agent-browser skill enables AI agents to interact with web pages. It allows the agent to browse websites, extract specific information from them (like text or data), and potentially automate tasks that would normally require manual interaction with a browser. This skill provides access to content behind login forms and dynamically generated content.

When to use it

  • Research: Gathering information from multiple web pages for reports or analysis.
  • Data Extraction: Scraping product details, pricing, or other data from e-commerce sites.
  • Automated Form Filling: Submitting forms on websites that require user input.
  • Content Monitoring: Tracking changes to specific webpages and alerting you to updates.

Key capabilities

  • Web page browsing
  • Data extraction from web pages
  • Form submission
  • Accessing content behind login walls

Example prompts

  • "Browse https://example.com and extract all the product names and prices."
  • "Log in to https://mybank.com with username 'user' and password 'password', then check my account balance."
  • "Fill out the registration form on https://signup.example.com using these details: name=John Doe, email=[email protected]"

Tips & gotchas

  • The agent will require valid login credentials if accessing pages behind a login wall.
  • Websites frequently change their structure, which may break the agent's ability to extract data; periodic updates or adjustments to prompts might be necessary.