Remote Dispatch bridges mobile messaging and desktop automation, allowing users to remotely control their computer via QQBot and computer-use scripts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install remote-dispatch
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install remote-dispatch using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Remote Dispatch?
Remote Dispatch is an innovative AI agent skill inspired by Claude Dispatch. It transforms your mobile phone into a remote control interface by routing instructions sent through QQBot directly to your desktop. By functioning as a dedicated input channel, it translates natural language requests into concrete desktop actions execution layers.
This skill coordinates seamlessly with computer-use functionalities to operate your machine at a distance. Whether you need to check on an ongoing background process, fetch text from your desktop clipboard, or pull up a web page, Remote Dispatch handles the pipeline safely and efficiently, feeding visual or textual confirmation right back to your chat application.
Remote Dispatch Use Cases
- On-the-go Monitoring: Request immediate desktop screenshots to check the status of active rendering, long-running scripts, or downloads while away from your desk.
- Remote Web Assistance: Command your browser to open specific URLs or perform search queries and receive visual confirmation of the search results on your mobile device.
- Cross-Device Clipboard Management: Fetch text contents currently held on your PC's clipboard or write new text snippets to it remotely.
- Desktop Application Control: Focus, minimize, or close specific active windows, or open files and folders located at deep system paths via simple chat commands.
How Remote Dispatch Works
- Message Reception: The user sends a natural language command (e.g., "Help me take a screenshot") from their mobile device through QQ.
- Command Analysis: QQBot receives the incoming message and filters it. Standard chat prompts are answered immediately, while structural remote instructions are forwarded to the Remote Dispatch engine.
- Instruction Translation: The core parser maps the text command to its respective Python automation script execution command.
- Execution Layer: The matching
computer-useautomation subroutine triggers (e.g., taking a screen snapshot, manipulating the clipboard, or focusing a window). - Feedback Loop: Visual results (like a cropped screenshot) or text confirmations are gathered and pushed back to QQBot, which replies directly to the user's mobile interface.
Remote Dispatch Setup
To deploy this skill, you must ensure that python3 is accessible within your environment path and that the companion computer-use skill configuration is complete.
Activate the skill environment and test the underlying execution scripts directly:
# Verify your python installation
python3 --version
# Remote Dispatch coordinates with screen subroutines
python screen.py screenshot --output /tmp/remote.png
Remote Dispatch Data Schema & Taxonomy
The skill manages instructions using a centralized map inside dispatch.py that links natural language intents to physical system calls.
| Command Key | Shell Mapping | Expected Output Media |
|---|---|---|
screenshot |
python screen.py screenshot --output /tmp/remote.png |
PNG Image File |
search |
python screen.py open --target https://baidu.com |
PNG Image File via Browser View |
clipboard |
python screen.py clipboard |
Plain Text String |
window |
Focus, minimize, or close target application nodes | Boolean Confirmation String |
Remote Dispatch Advanced Features
- Granular Privacy Safe Areas: Supports targeted region cropping during visual screenshot feedback loops to safeguard personal desktop information.
- Two-Factor Action Confirmation: Critical or destructive tasks, such as closing application windows or modifying localized files, trigger secondary confirmation checks before running.
- Seamless Protocol Routing: Intelligently distinguishes standard conversational requests from active system-level execution payloads directly from the messaging webhook stream.
SKILL.md
Loading
Related Openclaw Skills
Codebase Index
A repository scanning and symbol mapping tool that builds a fast, searchable JSON index of classes, functions, and variables using Python AST and ripgrep.
Agent Harness Builder
Design, structure, and deploy complex multi-agent orchestrations with a complete blueprint and document handoff system.
Foresea
An AI agent forecasting skill that integrates Polymarket and Kalshi predictive analysis, model-vs-market edge tracking, and calibrated probability intelligence into your OpenClaw setup.
AI Test Engineer
An expert AI testing assistant transforming junior engineers into masters by implementing a 7-phase, 48-module full-lifecycle QA framework.
Google Flow Video Automation
An automation tool that leverages Chrome CDP to programmatically generate, optimize, and download AI videos on Google Flow.
mcpglue
A standardized Model Context Protocol (MCP) bridge that lets AI agents dynamically interface with custom servers, APIs, and file systems.
Featured*
