An AI-powered video production skill that automates trimming, audio layering, and rendering through natural language commands.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install video-making
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-making 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 Making Skill?
The Video Making skill is designed to eliminate the steep learning curve associated with professional video editing software. By integrating this skill into your workflow, you can simply describe the desired output—such as trim the footage, add background music, and export as a shareable video—and the AI will handle the heavy lifting. This tool is a standout component of the Openclaw Skills library, enabling users to generate polished 1080p MP4 videos in minutes using remote GPU nodes.
Whether you are working with MP4, MOV, or WebM files, the skill streamlines the entire pipeline from upload to final render. It leverages a cloud-based render engine to composite layers, apply compression, and deliver high-quality media without taxing your local machine resources. It is an essential utility for developers and creators who need fast, automated AI video creation.
Video Making Skill Use Cases
- Rapidly editing raw mobile footage into professional-looking product demos.
- Batch processing multiple video clips to add consistent background music and branding.
- Automating the creation of social media content through simple text-based instructions.
- Generating high-quality MP4 exports for presentations without needing manual editing software.
How Video Making Skill Works
- The skill initializes by checking for a NEMO_TOKEN or generating an anonymous session token for the user.
- Raw media files are uploaded to the cloud backend via a multipart POST request.
- Users provide natural language prompts which are routed to specific editing actions like trimming or track placement.
- The skill uses Server-Sent Events (SSE) to communicate with the cloud GPU nodes, managing the timeline state in real-time.
- Upon completion of edits, the export workflow is triggered to render the final composite.
- The system polls the render status every 30 seconds until a permanent download URL for the MP4 is provided.
Video Making Skill Setup
To deploy this skill within the Openclaw Skills ecosystem, follow these configuration steps:
- Ensure the
NEMO_TOKENenvironment variable is available. If not, the skill will attempt to generate an anonymous token automatically. - The skill requires access to
~/.config/nemovideo/for session persistence. - Basic environment setup example:
# Set your API token
export NEMO_TOKEN="your_nemo_token_here"
# The skill will automatically handle session creation on first use
Video Making Skill Data Schema & Taxonomy
The skill organizes video projects using a structured session state and a specific metadata taxonomy for the timeline.
| Component | Type | Description |
|---|---|---|
session_id |
String | Unique identifier for the active editing project |
draft |
JSON | The core timeline data including tracks and segments |
track_type |
Integer | Categorizes tracks: 0 (Video), 1 (Audio), 7 (Text) |
video_infos |
Array | Metadata for all uploaded assets in the session |
output.url |
String | The final rendered file location (MP4 format) |
Video Making Skill Advanced Features
- Support for multi-track editing including synchronized audio, video, and text overlays.
- Intelligent mapping of GUI-based instructions (like 'drag' or 'click') to programmatic API actions.
- Automated credit balance management and anonymous token lifecycle handling.
- Real-time timeline state polling to ensure synchronization after complex edit operations.
- High-performance cloud rendering that supports files up to 500MB and multiple input formats.
SKILL.md
Loading
Related Openclaw Skills
Video Maker Online
An AI-powered video creation skill that transforms raw assets into polished 1080p MP4 videos through natural language commands and cloud rendering.
CN Express Tracker
A streamlined Chinese express delivery assistant that tracks logistics status across multiple carriers without requiring an API key.
CN Hot Trends
A high-performance aggregation tool for real-time trending data across 6 major Chinese social media platforms.
Trimmer Adobe
Trimmer Adobe is a high-speed AI video trimming tool within the Openclaw Skills ecosystem that automates silence removal and clip shortening through natural language commands.
Video Object Ops
A high-performance AI tool for manipulating video objects and exporting professional edits directly via text commands.
Video Script Automaton
An AI-powered video script generation tool that transforms topics and text into professional scripts and rendered 1080p MP4 videos via cloud GPUs.
Featured*
