Skip to content
TrustedSkillsbeta
Back to all skills

Browser Tools

Checked
yonatangross·vlatest·frontend·MIT

This skill allows you to interact with web pages directly – navigate, extract data, and more – boosting automation and scraping capabilities.

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 yonatangross/orchestkit --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

yonatangross

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 yonatangross/orchestkit at 7784b90c05.

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

Commit
7784b90c05
Manifest
src/skills/browser-tools/SKILL.md
Scanned
2 files, 608 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 provides a security wrapper around the agent-browser tool, enhancing its functionality for interacting with web pages. It enables AI agents to navigate websites, extract data, and perform actions within browser environments. The primary purpose is to add safety guardrails while leveraging the full capabilities of the underlying agent-browser tool.

When to use it

  • When needing to interact with Single Page Applications (SPAs) or interactive web pages that require a browser environment.
  • When login authentication and state management are required for accessing web content.
  • When dynamic web content needs to be handled, utilizing wait commands based on element presence or text content.
  • For tasks involving data extraction from websites where WebFetch or Tavily are insufficient.
  • To discover and install capability packs directly within the agent environment.

Key capabilities

  • Navigation & Interaction: Full command set for web page interaction (refer to upstream agent-browser documentation).
  • Data Extraction: Ability to extract data from web pages.
  • Semantic Locators: Uses accessibility trees (findByRole) for more robust element identification, less reliant on CSS selectors.
  • Debugging Tools: Screenshot annotation with ref IDs and role labels.
  • Skill Discovery & Chat: agent-browser skills list/get to discover and install capability packs; natural language interaction via agent-browser chat.
  • Cloud Provider Integration: Supports AWS Bedrock AgentCore cloud browser (--provider agentcore).
  • Dashboard Access: Embedded dashboard for inspection (accessible via agent-browser dashboard).

Example prompts

  • agent-browser open "http://myapp.localhost:1355" - Opens a specific URL in the browser.
  • agent-browser find button[role="button"] - Locates a button element using semantic role.
  • agent-browser chat "Click the submit button" - Uses natural language to drive actions within the browser.

Tips & gotchas

  • Upstream Documentation: Refer to the agent-browser documentation for the complete command reference and detailed usage patterns. This skill primarily adds security features.
  • Stable URLs: Use Portless (npm i -g portless) for stable local development URLs instead of relying on potentially changing ports.
  • Security Focus: This skill prioritizes safety guardrails; remote providers are treated as egress surfaces with restricted network routing.