Skip to content
TrustedSkillsbeta
Back to all skills

Clawdcursor

Checked
AmrDab·v0.6.3·ai-ml·MIT

>

Repository

Install on your platform

Showing OpenClaw.

  1. 1

    Run this in your terminal

    terminal
    $ openclaw skills install clawdcursor

What we know about this skill

Publisher

AmrDab

Taken from the source listing. We haven't verified who controls this account.

Install target

Pinned to abf959ae

Installs fetch a stored snapshot of that commit, so the code can't change after the fact.

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

    Only contacts known or declared hosts: 127.0.0.1.

    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

    127.0.0.1local

  • 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 amrdab/clawd-cursor at b95c80b895.

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

Commit
b95c80b895
Manifest
skills/clawdcursor/SKILL.md
Scanned
1 file, 469 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

Clawd Cursor provides an OS-level desktop automation server, giving AI models the ability to interact with a real computer. It allows any AI model – including Claude, GPT, Gemini, and Llama – to perform tasks like moving the mouse, capturing screenshots, and interacting with applications. This is achieved through a model-agnostic architecture that works seamlessly with tool-calling models, even when using local models.

When to use it

  • Automated data extraction: Have an AI agent extract specific information from web pages or documents displayed on your screen.
  • Application control: Allow an AI to automate repetitive tasks within software applications like spreadsheets or design tools.
  • Remote assistance: Enable an AI to remotely interact with a user's computer for troubleshooting or support purposes.
  • Screen recording and analysis: Use the AI to capture screen recordings and analyze them for specific events or patterns.

Key capabilities

  • Model-agnostic compatibility (Claude, GPT, Gemini, Llama)
  • Desktop automation via mouse movement and clicks
  • Screenshot capturing functionality
  • Works with local AI models
  • macOS native host app for simplified permissions management
  • Localhost IPC architecture for enhanced security

Example prompts

  • "Move the mouse to the top-left corner of the screen and click."
  • "Capture a screenshot of the current window and save it as 'screenshot.png'."
  • “Drag the mouse from this coordinate (x, y) to that coordinate (a, b).”

Tips & gotchas

  • On macOS, you'll need to grant Accessibility and Screen Recording permissions to the Clawd Cursor host application for full functionality.
  • The system utilizes a token-based authentication method via ~/.clawdcursor/host-token which should be kept secure (mode 0600).