Skip to content
TrustedSkillsbeta
Back to all skills

Agent Browser

Listed
m1heng·vlatest·frontend·MIT

Automates web browsing tasks like data extraction, form filling, and navigation using intelligent scripting.

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 m1heng/clawdbot-feishu --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

m1heng

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 failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 3 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: corpproxy.company.com, httpbin.org, proxy.com.

    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.

    Hosts contacted

    proxy.comundeclaredcorpproxy.company.comundeclaredhttpbin.orgundeclared

    What it found (3 of 4)

    • .agents/skills/agent-browser/SKILL.md:241contacts proxy.com
      agent-browser --proxy http://proxy.com:8080 open example.com
    • .agents/skills/agent-browser/references/proxy-support.md:121contacts corpproxy.company.com
      export HTTP_PROXY="http://corpproxy.company.com:8080"
    • .agents/skills/agent-browser/references/proxy-support.md:122contacts corpproxy.company.com
      export HTTPS_PROXY="http://corpproxy.company.com:8080"

  • 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 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 m1heng/clawdbot-feishu at b07885b756.

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

Commit
b07885b756
Manifest
.agents/skills/agent-browser/SKILL.md
Scanned
9 files, 1,304 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 Agent Browser skill enables AI agents to automate web browsing tasks. It allows an agent to navigate websites, interact with page elements (like clicking buttons or filling forms), and extract information from webpages using intelligent scripting based on a snapshot of the current DOM. This facilitates data extraction, form submission, and other repetitive online actions.

When to use it

  • Automating data entry into web forms.
  • Extracting specific data points from multiple web pages.
  • Navigating complex websites with many steps.
  • Simulating user interactions on a website for testing purposes.
  • Downloading files or generating PDFs of webpages.

Key capabilities

  • Navigation: Open URLs, go back/forward, reload pages, and close the browser window.
  • Snapshotting: Capture the page's accessibility tree (full or interactive elements only) to identify elements for interaction.
  • Element Interaction: Click, double-click, focus on, fill in, type into, check/uncheck checkboxes, select dropdown options, and drag & drop elements using references obtained from snapshots.
  • Information Extraction: Retrieve text content, HTML, input values, attributes, page titles, URLs, bounding boxes, and computed styles of elements.
  • State Checking: Verify if an element is visible, enabled, or checked.
  • Screenshots & PDF Generation: Capture screenshots of the current webpage.

Example prompts

  • "agent-browser open https://www.example.com"
  • "agent-browser snapshot -i; agent-browser fill @e2 'my_username'; agent-browser click @e1"
  • "agent-browser get title"

Tips & gotchas

  • The skill relies on "snapshots" to identify elements. Significant DOM changes after a snapshot may require another snapshot to be taken.
  • Element references (like @e1, @e2) are obtained from the output of agent-browser snapshot -i.
  • Supports various URL protocols: https://, http://, file://, about:, and data://. If no protocol is provided, it will assume https://.