A high-performance CLI-based AI agent skill for controlling smart cameras, processing video streams, and performing vision-language analysis.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install cinmoore-skill-devices
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 cinmoore-skill-devices 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 Cinmoore Intelligent Device Control?
Cinmoore Intelligent Device Control is a specialized skill designed for AI coding agents to interact seamlessly with smart hardware. It provides a robust set of atomic capabilities, including device management, PTZ rotation, and real-time video processing. By leveraging Openclaw Skills, developers can integrate complex camera workflows—from human detection toggling to automated video recording—directly into their AI-driven automation pipelines. This skill operates as a standalone binary, ensuring high efficiency and security without the need for a local Python environment.
Cinmoore Intelligent Device Control Use Cases
- Automating home or office security monitoring by querying alarm events through Openclaw Skills commands.
- Controlling camera movement (PTZ) through natural language commands like "look left."
- Extracting video frames for AI-driven visual analysis (VLM) to identify specific objects or actions.
- Building complex automation scripts that trigger video recording based on sensor events.
- Managing device algorithm settings, such as enabling or disabling person detection, via simple CLI flags.
How Cinmoore Intelligent Device Control Works
- The AI agent initializes the skill by loading authentication credentials from the .env configuration.
- Users provide instructions via natural language or direct CLI commands through the Openclaw Skills interface.
- The skill executes the request by calling the compiled Cinmoore binary with specific parameters.
- For visual tasks, the skill utilizes FFmpeg to extract frames and sends them to a Vision-Language Model for analysis.
- The results, whether device statuses or AI-generated visual insights, are returned to the agent for further action.
Cinmoore Intelligent Device Control Setup
To get started with these Openclaw Skills, download the binary for your platform and configure the environment variables.
echo "🚀 Downloading independent executable (Linux)..."
curl -L -o cinmoore-skill-devices https://super-acme-shoot-sh.oss-cn-shanghai.aliyuncs.com/skill-tools/exe/cinmoore-skill-devices-ubuntu
curl -L -o .env.cinmoore_skill_devices https://super-acme-shoot-sh.oss-cn-shanghai.aliyuncs.com/skill-tools/env/env.cinmoore_skill_devices
mkdir -p tools/linux
curl -L -o tools/linux/ffmpeg https://super-acme-shoot-sh.oss-cn-shanghai.aliyuncs.com/skill-tools/ffmpeg/linux/ffmpeg
chmod +x cinmoore-skill-devices
Note: Ensure you update the .env.cinmoore_skill_devices file with your actual app-key and authentication details before running any commands.
Cinmoore Intelligent Device Control Data Schema & Taxonomy
| Data Type | Description | Key Metadata |
|---|---|---|
| Device Info | JSON object containing serial numbers and group IDs. | device_name, sn |
| Video Frames | JPEG/PNG images extracted from recorded streams. | fps, frame_count |
| Alarm Events | Log of historical triggers with timestamps. | begin, end |
| AI Analysis | Textual output from VLM analysis of video content. | prompt, analysis_result |
Cinmoore Intelligent Device Control Advanced Features
- Natural Language Intent Resolution: Convert human phrases like "I don't want to see people" into specific algorithm configuration calls using Openclaw Skills intelligence.
- Multi-Action Chaining: Execute complex sequences like
ptz-recordwhich combines movement and recording in one atomic command. - Vision-Language Integration: Built-in
see-analyzecommand to perform multi-image visual reasoning on extracted video frames. - Cross-Platform Support: Pre-compiled binaries available for both Ubuntu/Linux and Windows environments for seamless deployment.
SKILL.md
Loading
Related Openclaw Skills
Web3 AI Agent Screener
A professional assessment tool that evaluates Web3 AI Agent projects using a rigorous 11-dimension framework for long-term investment analysis.
Geode On-device Transcribe & Summary
A privacy-first macOS skill for asynchronous, on-device audio transcription and AI-powered summarization.
IHG Brand Profile
A comprehensive brand intelligence skill providing deep technical and market insights into the InterContinental Hotels Group (IHG).
Lufthansa Intelligence Hub
A specialized AI agent skill for retrieving comprehensive business intelligence, historical data, and operational insights for Lufthansa.
SEO
A performance-driven SEO skill that helps developers implement technical search optimizations and crawlability fixes directly in their code.
Senior Backend Developer
A production-grade backend engineering skill for implementing secure APIs, database architectures, and robust server-side logic.
Featured*
