An AI-powered video editing and rendering skill that transforms static images and clips into professional 1080p videos through natural language prompts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install video-canva
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-canva 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 Canva?
Video Canva is a sophisticated tool designed for the Openclaw Skills ecosystem, enabling developers and creators to bridge the gap between static assets and dynamic video content. By leveraging remote cloud-based GPU rendering nodes, this skill allows users to simply describe their vision—such as arranging photos into a 30-second promo with text overlays—and receive a production-ready MP4 file in minutes. It eliminates the need for manual timeline dragging, complex keyframing, or taxing local hardware.
The skill operates via a high-performance cloud pipeline, handling everything from asset uploading to server-side compositing. Whether you are generating social media content or product demos, using Openclaw Skills like Video Canva streamlines the creative workflow by automating technical rendering and encoding tasks through a unified API interface.
Video Canva Use Cases
- Creating professional 30-second product promo videos from static images and logos.
- Automating social media content generation with dynamic text overlays and background music.
- Batch processing multiple assets into cohesive video clips using AI-driven layouts.
- Rapid prototyping of video concepts through iterative natural language refinement.
- Generating 1080p MP4 exports for various platforms without local hardware strain.
How Video Canva Works
- The user provides images or clips and describes the desired video outcome via a natural language prompt.
- The skill performs a token check for NEMO_TOKEN and establishes a secure session with the cloud rendering backend.
- Assets are uploaded to the remote server, and instructions are processed through a Server-Sent Events (SSE) stream for real-time editing logic.
- Cloud GPU nodes composite the layers, apply text overlays, and synchronize audio tracks according to the timeline draft.
- An export job is queued, and the skill polls the render proxy for the final 1080p MP4 download link once completion is detected.
Video Canva Setup
To integrate this capability into your Openclaw Skills environment, you must configure the connection to the cloud processing backend.
# Set your NEMO_TOKEN environment variable
export NEMO_TOKEN="your_api_token_here"
# Ensure configuration paths exist
mkdir -p ~/.config/nemovideo/
If a token is not detected, the skill will attempt to generate an anonymous token with limited credits. All requests must include the mandatory attribution headers: X-Skill-Source, X-Skill-Version, and X-Skill-Platform.
Video Canva Data Schema & Taxonomy
The skill manages video projects using a session-based state and specific draft field mappings for the timeline:
| Field | Description |
|---|---|
| session_id | Unique identifier for the current editing workspace |
| t (tracks) | Organized list of media layers |
| tt (type) | 0: Video, 1: Audio, 7: Text |
| sg (segments) | Individual clips or elements within a track |
| d (duration) | Length of the segment in milliseconds |
Supported file types: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.
Video Canva Advanced Features
- Direct SSE event handling for real-time feedback and state updates during the generation process.
- Automatic GUI instruction translation, mapping natural language prompts like "drag" or "drop" to backend API actions.
- Intelligent credit balance monitoring with automated session recovery for long-running render tasks.
- Support for complex timeline structures including multiple audio tracks, visual transitions, and dynamic text overlays.
- Robust error handling for rate limits, expired session tokens, and unsupported file formats.
SKILL.md
Loading
Related Openclaw Skills
Clip Maker AI — Turn Long Videos Into Clips
An AI-powered video editing skill that automatically converts long-form recordings into viral social media clips using natural language commands.
Editor InShot
Editor InShot is a cloud-based AI video editing skill that transforms raw smartphone footage into polished, social-media-ready 1080p videos via simple text commands.
Video Maker from Photo
An AI-powered video generation skill that transforms static images into high-quality animated videos with music and transitions through a cloud rendering pipeline.
Clip Skill — Edit and Export Video Clips
A cloud-powered AI video editing skill that transforms raw footage into polished 1080p clips through simple text instructions.
Editor Highlights
Editor Highlights is an AI-powered video processing skill that automatically extracts key moments from raw footage and compiles them into professional highlight reels.
grep-tool
A high-performance pattern search utility designed to filter text files and analyze logs using advanced regular expressions.
Featured*
