Skip to content
TrustedSkillsbeta
Back to all skills

Agent Browser

Checked
andrelandgraf·vlatest·agents

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 andrelandgraf/fullstackrecipes --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

andrelandgraf

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 andrelandgraf/fullstackrecipes at 4449331ed5.

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

Commit
4449331ed5
Manifest
.agents/skills/agent-browser/SKILL.md
Scanned
2 files, 278 lines
Copies in repo
2 — all of them scanned
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 enables AI agents to interact directly with web browsers, allowing them to browse the internet, navigate websites, and execute user interface actions autonomously. It bridges the gap between static text responses and dynamic web interaction by providing a functional browser environment for the agent.

When to use it

  • Research and Data Gathering: Instruct an agent to search for current news, compare product prices across multiple retailers, or extract specific data points from public websites.
  • Web Automation Tasks: Delegate repetitive tasks like filling out forms, checking account balances, or monitoring stock tickers without manual intervention.
  • Interactive Debugging: Allow agents to inspect live web pages, click through error flows, and verify that website updates are functioning correctly in real-time.
  • Content Synthesis: Have an agent read multiple articles on a specific topic to synthesize a comprehensive summary or generate a report based on live sources.

Key capabilities

  • Autonomous navigation across different websites and domains.
  • Execution of click, scroll, and form-filling actions within the browser context.
  • Real-time rendering and interaction with dynamic web content.
  • Integration with standard web protocols to access public information.

Example prompts

  • "Browse the latest tech news sites and summarize the top three stories about AI advancements from the last 24 hours."
  • "Visit my email inbox, find any unread messages from 'Support', and read the subject lines."
  • "Navigate to a specific product page on an e-commerce site, check the current price, and compare it with the price listed on two other competitor sites."

Tips & gotchas

Ensure the AI agent has access to live internet connectivity, as this skill relies on external web resources rather than internal knowledge bases. Be aware that some websites may have anti-bot protections or CAPTCHAs that could interrupt the agent's browsing session.