A powerful AI video editing skill that automates footage processing, captioning, and background music integration via cloud GPU rendering.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install video-using-ai
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-using-ai 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 Using AI?
Video Using AI is a sophisticated tool designed for content creators who need to transform raw footage into professional, polished videos without manual editing. By leveraging remote GPU nodes, this skill handles heavy lifting like silence removal, text overlays, and audio syncing, producing high-quality 1080p MP4 files in just minutes. It eliminates the need for expensive local hardware by processing everything in the cloud through the Openclaw Skills framework.
This skill supports a wide array of formats including MP4, MOV, and WebM, accommodating files up to 500MB. Whether you are creating social media content or professional presentations, it provides a seamless bridge between raw assets and final exports by interpreting natural language instructions into complex editing actions.
Video Using AI Use Cases
- Turning raw phone recordings into polished social media clips by automatically cutting out silences.
- Enhancing video accessibility by generating automated captions and text overlays.
- Batch processing multiple raw files within a single session to maintain consistent styling across a series.
- Iterative video refinement where creators can preview drafts and tweak background music or timing before final export.
How Video Using AI Works
- The user uploads raw footage (up to 500MB) and provides natural language editing instructions.
- The skill establishes a secure session with the cloud rendering API using a NEMO_TOKEN.
- Editing commands are processed via a Server-Sent Events (SSE) stream, where the AI interprets intent for tracks, transitions, and effects.
- A cloud GPU node composites the video layers, applying H.264 compression and platform-specific formatting.
- The skill polls the render status every 30 seconds until a download URL for the final 1080p MP4 is generated.
Video Using AI Setup
To initialize Video Using AI, ensure your environment is configured with the necessary API credentials. The skill will automatically handle session creation on first use.
# Set your API token
export NEMO_TOKEN="your_token_here"
# The skill will check for config at:
# ~/.config/nemovideo/
If you do not have a token, the skill can generate an anonymous temporary token with 100 credits for Openclaw Skills users.
Video Using AI Data Schema & Taxonomy
The skill organizes video projects using a session-based draft system. Data is mapped according to the following taxonomy:
| Field | Description |
|---|---|
t |
Tracks (The layers of the video timeline) |
tt |
Track Type (0: Video, 1: Audio, 7: Text) |
sg |
Segments (Specific clips or blocks within a track) |
d |
Duration (Measured in milliseconds) |
m |
Metadata (File info and asset properties) |
Video Using AI Advanced Features
- Multi-track timeline management allowing simultaneous editing of video, background music, and titles.
- Support for iterative workflows where session state is preserved for fine-tuning before final rendering.
- Automated GUI instruction translation that maps conversational requests like "add BGM" to complex backend SSE events.
- High-speed cloud rendering pipeline that optimizes processing for clips under 60 seconds.
SKILL.md
Loading
Related Openclaw Skills
To Voice Generator
A professional AI skill that transforms text scripts and documents into natural-sounding voiceover videos with cloud GPU rendering.
Maker Japanese
Maker Japanese automates the creation of Japanese-style videos with text overlays and transitions through a cloud-based rendering pipeline.
Editor Baby
Editor Baby is an automated video editing assistant that transforms raw baby footage into polished highlight reels using simple natural language descriptions.
No Login Video — Edit and Export Videos Instantly
A high-speed AI video editing skill that transforms raw clips into polished 1080p MP4s through a cloud-based GPU pipeline without requiring account registration.
Create a Video
A professional-grade AI video creation skill that transforms raw images and clips into polished 1080p MP4 videos using cloud GPU rendering.
Expeditors Global Logistics Analyzer
An analytical skill providing deep insights into Expeditors' asset-light logistics model and organic growth strategy.
Featured*
