Video Builder is an automated AI video creation tool that assembles polished 1080p MP4 videos from raw clips and images using simple text commands.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install video-builder
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-builder 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 Builder?
Video Builder is a sophisticated Openclaw Skills integration designed for marketers and content creators who need professional video results without the steep learning curve of manual editing software. By leveraging a cloud-based GPU rendering pipeline, it allows users to transform raw assets like MP4, MOV, and PNG files into high-quality productions.
The skill acts as a bridge to a powerful backend API that handles complex timeline operations, including layer compositing, text overlays, and audio syncing. Whether you need to combine these clips into a 60-second promo or generate a quick social media edit, this tool manages the heavy lifting of video production through intuitive natural language processing.
Video Builder Use Cases
- Creating 60-second promotional videos from product images and background music.
- Batch processing multiple media files to apply consistent styles across different clips.
- Generating polished 1080p MP4 exports for social media without manual timeline editing.
- Adding professional text overlays and transitions to raw footage via text prompts.
- Quick iterative video drafting where users refine the timeline state through conversation.
How Video Builder Works
- The user provides media files or URLs which are uploaded to the cloud rendering pipeline.
- An editing session is initialized, establishing a unique session ID to track the timeline state.
- User instructions are processed via an SSE (Server-Sent Events) stream that interprets intent for editing, transitions, or effects.
- The backend updates a JSON-based draft representing the tracks, segments, and metadata of the video.
- Upon an export command, a cloud GPU node composites the layers and compresses the video into a 1080p MP4 file.
- The skill monitors the render progress and provides a final download URL to the user.
Video Builder Setup
To initialize the Video Builder within Openclaw Skills, ensure your environment is configured:
# Set your API token
export NEMO_TOKEN="your_token_here"
# The skill will automatically handle session creation on first run
# If no token is found, it can generate an anonymous 7-day token
Ensure that the three required attribution headers (X-Skill-Source, X-Skill-Version, and X-Skill-Platform) are present in your configuration to avoid 402 error blocks during export.
Video Builder Data Schema & Taxonomy
The skill manages data through a structured session state and a compressed JSON timeline format:
| Key | Description |
|---|---|
t |
Tracks (The primary organizational layers) |
tt |
Track Type (0: Video, 1: Audio, 7: Text) |
sg |
Segments (Individual clips or elements within a track) |
d |
Duration (Measured in milliseconds) |
m |
Metadata (Information regarding specific media properties) |
All media processed is subject to a 500MB file size limit and is stored temporarily within the active editing session.
Video Builder Advanced Features
- Multi-track timeline management supporting simultaneous video, audio, and text layers.
- Automated credit balance monitoring and anonymous-to-registered account binding.
- Real-time SSE stream processing for complex, multi-step AI video creation tasks.
- Platform-specific H.264 compression for optimized 1080p MP4 output.
- Session persistence allowing for iterative editing and refining of the video state over multiple interactions.
SKILL.md
Loading
Related Openclaw Skills
URL Shortener Skill
An instructions-based skill that enables AI agents to shorten URLs using public APIs while bypassing anti-bot restrictions.
D&D Character Art Generator
A powerful AI skill that transforms text descriptions into high-quality D&D character artwork via the Neta AI API.
Audio Video To — Merge Audio and Video Files
A high-performance cloud-based skill for merging media tracks and performing AI format conversion via simple natural language commands.
WeChat Auto Post
An automated AI content generation engine designed to create viral-ready WeChat Official Account articles and trending social media content.
Video Editing With AI
A powerful AI-driven video editing tool that converts raw clips into polished, social-ready videos using simple natural language commands.
Highlight Editor AI
Highlight Editor AI automates the process of extracting the best moments from long video recordings and compiling them into high-quality highlight reels using cloud GPU processing.
Featured*
