Video Compose is a cloud-based AI tool that automates complex video editing by merging multiple clips into a polished MP4 with transitions and background music.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install video-compose
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 video-compose 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 Video Compose?
Video Compose is a powerful addition to the Openclaw Skills ecosystem designed to eliminate the steep learning curve of professional editing software. By leveraging a high-performance cloud rendering pipeline, this skill allows users to transform raw footage into professional-grade content simply by describing their desired outcome. It handles everything from simple clip stitching to complex tasks like adding text overlays, background audio, and smooth transitions.
The skill is built for speed and efficiency, typically delivering a rendered 1080p MP4 file within 1-2 minutes. It supports a wide array of formats including MP4, MOV, AVI, and WebM for video, along with various audio and image formats. Whether you are a content creator looking for a quick rough cut or an automated workflow, this skill provides a seamless interface between AI intent and high-fidelity video production.
Video Compose Use Cases
- Combining multiple short clips into a single continuous video for social media.
- Automatically adding background music and transitions to raw footage.
- Creating 1080p MP4 exports from mixed media like images and video segments.
- Batch processing multiple video files within a single project session.
- Iterative video editing where users refine the timeline through natural language commands.
How Video Compose Works
- The user uploads video, audio, or image files (up to 500MB) to the secure cloud rendering pipeline.
- A session is initialized with a unique token, establishing a persistent project environment.
- The user provides natural language instructions, which are parsed to identify intents like 'combine all clips into one video with transitions and background music'.
- The AI generates a timeline draft, organizing tracks for video, audio, and text elements.
- A cloud GPU node processes the render job, applying compression and effects.
- The system monitors the render status and provides a final download URL for the composed MP4 file.
Video Compose Setup
To get started with this skill, ensure you have your environment variables configured. On first use, the system can automatically generate an anonymous token if needed.
# Set your API token
export NEMO_TOKEN="your_token_here"
# The skill will automatically initialize a session
# and store configuration in ~/.config/nemovideo/
Video Compose Data Schema & Taxonomy
The skill manages data through a session-based state, organizing the timeline into specific track types and metadata.
| Track Type | ID | Description |
|---|---|---|
| Video | 0 | Primary visual layer and segments |
| Audio | 1 | Background music and voiceovers |
| Text | 7 | Overlays, titles, and captions |
All project data is stored in a JSON draft format using shorthand keys (t for tracks, sg for segments) to ensure low-latency communication with the SSE stream.
Video Compose Advanced Features
- Multi-track support allowing simultaneous management of video, BGM, and title layers.
- Real-time SSE (Server-Sent Events) streaming for live updates on editing progress.
- Automatic resolution matching and platform-specific H.264 compression for high-quality 1080p output.
- Session persistence enabling users to return to a draft and make further refinements without re-uploading files.
- Intelligent error handling for credit management and automatic re-authentication.
SKILL.md
Loading
Related Openclaw Skills
AI Clothes Changer (WeShop OpenAPI)
A high-performance AI skill that programmatically swaps clothing from a garment image onto a person in a source image.
context-guardian
A proactive session monitoring skill that automates context summarization and memory persistence to prevent AI context overflow errors.
Browser File Upload
A high-reliability automation protocol for uploading files to web interfaces using the agent-browser CLI and Python-based fallback strategies.
Adaptive Reasoning
An intelligent preprocessing skill that evaluates request complexity to dynamically adjust an agent's reasoning depth and token usage.
Free Motion Video Skill
An AI-powered video enhancement tool that adds cinematic camera movement and motion to static video clips via cloud GPU processing.
Photo to Video AI Online
A professional AI-powered tool that converts photo collections into high-quality, shareable 1080p MP4 videos via cloud GPU processing.
Featured*
