A powerful AI skill that automates side-by-side video composition using cloud GPU rendering for high-quality MP4 exports.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install split-screen-video
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 split-screen-video 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 Split Screen Video: Side-by-Side Video Combiner?
The Split Screen Video skill enables developers and content creators to transform multiple video files into professional side-by-side layouts without requiring local processing power. By leveraging a high-performance cloud-based GPU pipeline, it supports a variety of formats including MP4, MOV, AVI, and WebM for files up to 500MB. As a core part of the Openclaw Skills library, it simplifies the complex task of video compositing into a few natural language commands, delivering 1080p resolution results optimized for modern social media platforms.
This skill is designed for efficiency, typically processing exports within 30 to 60 seconds. It handles the heavy lifting of layer composition, synchronization, and H.264 compression in the cloud. Whether you are building an automated content pipeline or using an AI agent for quick edits, this tool provides a robust interface for high-quality video production.
Split Screen Video: Side-by-Side Video Combiner Use Cases
- Create 50/50 side-by-side reaction videos for TikTok and YouTube Shorts.
- Combine two different camera angles for product demonstrations or walkthroughs.
- Synchronize before-and-after clips for fitness, coding, or design showcases.
- Batch process multiple video pairs into standardized split-screen layouts for social media marketing.
How Split Screen Video: Side-by-Side Video Combiner Works
- Authentication: The skill checks for a NEMO_TOKEN or automatically generates an anonymous token to authenticate with the cloud backend.
- Session Initialization: A unique session ID is created to maintain the state of the video timeline and project metadata.
- Media Upload: Source video clips are uploaded to the cloud storage via multipart POST requests or external URLs.
- Intent Processing: The agent parses user instructions (e.g., "place two videos side by side") and sends layout commands via a Server-Sent Events (SSE) stream.
- Rendering: The project is queued on a cloud GPU node which composites the video layers and applies specified text or audio overlays.
- Export: Once the render is complete, the skill provides a direct download URL for the final 1080p MP4 file.
Split Screen Video: Side-by-Side Video Combiner Setup
To use this skill within the Openclaw Skills ecosystem, ensure your environment is properly configured to communicate with the rendering API.
# Set your environment variable for authenticated access
export NEMO_TOKEN="your_nemo_api_token"
# If no token is provided, the skill will attempt to
# generate an anonymous token automatically.
The skill requires access to https://mega-api-prod.nemovideo.ai. Ensure your firewall allows outbound requests to this domain for media uploads and SSE stream processing.
Split Screen Video: Side-by-Side Video Combiner Data Schema & Taxonomy
The skill manages video projects using a structured session state that tracks media layers and segments.
| Key | Description | Type |
|---|---|---|
t (tracks) |
Collection of video, audio, and text layers | Array |
tt (track type) |
Identifier for content (0=video, 1=audio, 7=text) | Integer |
sg (segments) |
Timing data for when clips appear in the timeline | Object |
d (duration) |
Total length of the project in milliseconds | Long |
m (metadata) |
Technical specs like resolution, bitrate, and aspect ratio | Object |
session_id |
Unique project identifier for iterative editing | String |
Split Screen Video: Side-by-Side Video Combiner Advanced Features
- Cloud GPU Rendering: Offload heavy video processing tasks to remote nodes to save local CPU/GPU resources.
- Real-time SSE Feedback: Receive immediate updates on editing operations and project state changes.
- Multi-format Support: Seamlessly work with MP4, MOV, AVI, WebM, MKV, and various image/audio formats.
- Stateful Iteration: Modify layouts, add background music, or change text overlays within the same session without re-uploading source files.
- Platform Optimization: Automatic H.264 compression and 1080p scaling tailored for high-quality web distribution.
SKILL.md
Loading
Related Openclaw Skills
Skill to Openclaw
A specialized migration tool designed to transform foreign agent skill directories into standardized, secure Openclaw compatible structures.
Synapse Layer
Synapse Layer is a high-security persistent memory infrastructure designed to give AI agents long-term recall through an encrypted 4-layer Cognitive Security Pipeline.
Image to Video Bot
An AI-powered video rendering agent that transforms static image files into animated 1080p MP4 clips with transitions and background music.
Script Generator Intl
A powerful tool for transforming topics or briefs into multilingual video scripts and high-quality 1080p MP4 exports using cloud-based GPU processing.
Slideshow Automation
An AI-powered skill that transforms image collections and video clips into polished 1080p slideshows via cloud GPU rendering.
Trident Memory System
Trident is a sophisticated three-tier memory architecture designed to give Openclaw agents genuine continuity, identity, and semantic recall across multiple sessions.
Featured*
