An AI-powered video processing skill that automates batch editing and cloud rendering for multiple video clips via simple text prompts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ai-batch-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 ai-batch-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 AI Batch Video?
AI Batch Video is a powerful automation tool designed for developers and content creators who need to process multiple video clips simultaneously without manual timeline editing. By leveraging a high-performance cloud rendering pipeline, this skill allows users to describe desired edits—such as color correction, watermarking, or format conversion—and receive processed 1080p MP4 files in minutes. As part of the Openclaw Skills ecosystem, it bridges the gap between complex video production and simple, intent-based AI commands.
The skill connects to a specialized backend API that manages GPU-accelerated compositing and platform-specific compression. It is particularly effective for high-volume tasks where traditional video editors would be too time-consuming, offering a streamlined workflow from bulk upload to final download.
AI Batch Video Use Cases
- Automating the application of brand watermarks across dozens of product demo clips.
- Batch-applying color correction to multiple short-form social media videos.
- Rapidly converting various video formats (MOV, AVI, WebM) into optimized 1080p MP4 files.
- Adding background music or text overlays to a series of clips using natural language.
- Generating quick rough cuts and iterative edits without opening a traditional NLE.
How AI Batch Video Works
- The skill establishes a secure connection using a NEMO_TOKEN or generates an anonymous session for the user.
- Users upload multiple video files or provide URLs which are then registered to a unique session ID.
- The user provides a natural language prompt describing the batch edits required for the clips.
- Intent classification routes the request to the Server-Sent Events (SSE) stream or specific API endpoints for processing.
- A cloud GPU node manages the rendering pipeline, compositing layers and applying compression according to the instructions.
- The skill polls the rendering status every 30 seconds until the job is completed.
- A final download URL is provided to the user for the processed 1080p MP4 output.
AI Batch Video Setup
To use this Openclaw Skills entry, ensure your environment is configured with the necessary API credentials.
# Export your Nemo Video token
export NEMO_TOKEN="your_token_here"
# The skill will automatically detect configuration at:
# ~/.config/nemovideo/
If you do not have a token, the skill will automatically attempt to acquire a free starter token with 100 credits by generating a unique Client ID and authenticating with the backend.
AI Batch Video Data Schema & Taxonomy
The skill organizes video data through a structured session state, mapping tracks and segments for the cloud renderer.
| Field | Description | Mapping/Type |
|---|---|---|
t |
Tracks | Array of media layers |
tt |
Track Type | 0: Video, 1: Audio, 7: Text |
sg |
Segments | Specific clips within a track |
d |
Duration | Length in milliseconds (ms) |
m |
Metadata | Technical file properties |
Supported input formats include mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, and aac.
AI Batch Video Advanced Features
- Multi-track compositing: Supports simultaneous video, audio, and text overlay tracks.
- Automated GUI Translation: Maps backend interface instructions (like 'drag' or 'click') directly into executable API actions.
- Session Persistence: Maintains the timeline state across multiple prompts for iterative refining.
- Proxy Rendering: Utilizes Lambda-based proxy rendering for efficient, credit-free exports on supported tiers.
- Heartbeat Monitoring: Includes built-in SSE event handling to maintain connection stability during long-running render jobs.
SKILL.md
Loading
Related Openclaw Skills
Music Video Clip
A powerful AI skill that transforms audio tracks and video clips into professional, beat-synced 1080p music videos using cloud GPU rendering.
Free Video Subtitle
A powerful AI agent skill for automated video subtitling, captioning, and cloud-based rendering without local software installation.
Journal Pipeline
An autonomous content machine that handles the entire lifecycle of travel editorial from SEO research to Payload CMS publishing.
Ultimate Research
A sophisticated orchestration skill that transforms vague queries into high-confidence, evidence-backed strategic answers using a mandatory core of research tools.
Video Clip Generator
An AI-powered video automation tool that generates optimized, high-quality short clips from raw footage using cloud-based GPU rendering.
Agent Lens
A local observability tool for tracking AI API calls, token consumption, and model spending across major providers.
Featured*
