A cloud-powered AI video editor that turns natural language instructions into fully rendered 1080p video clips without manual sliders.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install in-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 in-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 In Video?
In Video is a sophisticated AI agent skill designed for high-speed content creation. By leveraging remote GPU nodes, this tool allows developers and creators to transform raw footage into polished, social-ready content through conversational commands. Whether you need to remove silence, add background audio, or overlay dynamic text, the In Video skill handles the heavy lifting of video processing without requiring local software installation.
As part of the Openclaw Skills ecosystem, this integration removes the complexity of traditional video editing. Users can upload various formats including MP4, MOV, and WebM, and receive high-quality 1080p exports. It is the ideal solution for those who want to automate the mundane parts of video post-production directly within their AI-driven workflow, ensuring professional results in minutes.
In Video Use Cases
- Removing awkward pauses and silences from interview recordings automatically.
- Adding background music and text overlays to raw social media clips for faster publishing.
- Batch processing multiple video files with consistent styling and branding instructions.
- Generating quick 1080p MP4 exports for rapid prototyping or client feedback cycles.
How In Video Works
- Initialize a session by authenticating with a NEMO_TOKEN or generating a temporary anonymous token via the backend API.
- Upload video assets (up to 500MB) to the cloud rendering pipeline using the multipart upload endpoint.
- Send natural language editing instructions, such as "cut out the pauses" or "add background music," through a Server-Sent Events (SSE) stream.
- The AI agent processes the intent and maps instructions to specific timeline actions like track creation or segment trimming.
- Monitor the session state to track real-time changes to the video, audio, and text layers.
- Trigger a cloud GPU render job to composite the layers and export the final 1080p MP4 file.
- Poll the render status until completion and download the final video via the provided URL.
In Video Setup
To get started with In Video, ensure your environment is configured to handle the necessary authentication tokens within the Openclaw Skills framework.
# Set your environment variable for persistent access
export NEMO_TOKEN="your_private_token"
# The skill looks for configuration in the following directory
mkdir -p ~/.config/nemovideo/
If no token is provided, the skill will automatically attempt to acquire a free starter token (valid for 7 days) by generating a unique client identifier and connecting to the Nemo Video API.
In Video Data Schema & Taxonomy
The skill organizes video projects using a structured session state that tracks the timeline and asset metadata. This data is essential for maintaining consistency across iterative edits.
| Field | Description |
|---|---|
session_id |
Unique identifier for the current editing project and cloud state. |
tracks |
An array of timeline layers (categorized as video, audio, or text). |
segments |
Individual clips, images, or audio assets placed within a track. |
generated_media |
Metadata for assets generated by AI, such as background tracks or overlays. |
draft |
The internal JSON representation of the video timeline (includes duration and metadata). |
Draft Mapping Key:
t: Trackstt: Track Type (0: Video, 1: Audio, 7: Text)d: Duration in milliseconds
In Video Advanced Features
- Multi-track timeline management allowing for complex layering of video, background music, and titles.
- Automated silence detection and removal to streamline vlogs and interview footage.
- Remote GPU-accelerated rendering which offloads heavy processing from your local machine to the cloud.
- Iterative editing support where the session maintains the project state for continuous refining.
- Support for a wide range of media formats including MP4, MOV, AVI, WebM, and various audio codecs.
- Native integration with Openclaw Skills for seamless multi-agent automation workflows.
SKILL.md
Loading
Related Openclaw Skills
Editor Modi: AI-Powered Video Editing & Export
Editor Modi is an AI-driven video editing skill that automates cutting, transitions, and professional exports without requiring local software or GPU power.
In Video Free AI Video Editor
A professional-grade AI video editing skill that transforms raw footage into polished, watermark-free videos via simple text commands.
SkVM JIT Optimize Trigger
A specialized tool to trigger just-in-time optimization for AI agent skills based on real-world task performance and failure logs.
Claimback Radar
An AI-powered scanner that analyzes emails and bills to identify subscription traps, hidden refunds, and savings opportunities.
Video Create AI
An AI-driven video production skill that transforms images, clips, and text prompts into professional rendered videos using remote GPU nodes.
SkVM General Usage
A specialized CLI for profiling model capabilities and AOT-compiling agent skills for optimized cross-model execution.
Featured*
