Transform raw video footage into polished, export-ready clips using AI-driven cloud GPU rendering and automated editing workflows.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install video-workflow
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-workflow 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 Workflow?
The video-workflow skill is a robust solution within the Openclaw Skills library designed to bridge the gap between raw video assets and finished professional content. By utilizing a cloud-based rendering pipeline, this skill allows users to process MP4, MOV, and AVI files up to 500MB without requiring local hardware resources. It automates common editing tasks such as trimming pauses, managing multi-track timelines, and applying transitions, resulting in high-quality 1080p output in under two minutes.
Built for content creators and developers, this skill integrates seamlessly with the Nemo Video API to provide an end-to-end production environment. Whether you are generating marketing clips or processing screen recordings, the skill handles everything from anonymous token management to complex session-based timeline state tracking, ensuring a smooth and scalable video production experience.
Video Workflow Use Cases
- Automating the creation of social media content by trimming raw clips and adding stylized transitions.
- Batch processing screen recordings to remove silences and export clean, high-definition MP4 tutorials.
- Integrating AI-driven video editing capabilities into custom agents using the Openclaw Skills framework.
- Rapidly generating previews and rough cuts for video production teams using simple text-based instructions.
How Video Workflow Works
- Authentication: The skill checks for a NEMO_TOKEN or automatically requests an anonymous token using a unique client identifier.
- Session Creation: A dedicated session is initialized to track the project state and maintain a persistent timeline.
- Media Ingestion: Users upload raw files via multipart requests or provide external URLs for the backend to ingest.
- Intent Processing: Commands sent via Server-Sent Events (SSE) are analyzed to perform specific edits like adding BGM, text overlays, or trimming segments.
- Timeline Management: The internal state maps tracks (video, audio, text) and segments to a draft schema for real-time updates.
- Rendering: A POST request triggers a cloud GPU node to composite the final video based on the draft instructions.
- Export: The system polls the rendering status and provides a final download URL once the high-quality MP4 is ready.
Video Workflow Setup
To get started with this skill, ensure you have the necessary environment variables configured. If no token is provided, the skill will attempt to provision an anonymous token automatically.
# Set your API token for the video workflow
export NEMO_TOKEN="your_nemo_api_token"
# The skill will look for configuration at:
# ~/.config/nemovideo/
The integration handles the anonymous-token exchange and session creation internally on first use, allowing for an immediate 'Ready!' status for new users exploring Openclaw Skills.
Video Workflow Data Schema & Taxonomy
The skill manages complex video metadata and timeline states through a structured taxonomy:
| Key | Description | Type |
|---|---|---|
session_id |
Unique identifier for the current editing project | String |
draft |
The core data structure containing tracks (t) and segments (sg) |
Object |
tt |
Track Type (0: Video, 1: Audio, 7: Text) | Integer |
d |
Duration of segments in milliseconds | Integer |
video_infos |
Metadata for all uploaded source files | Array |
output.url |
Final destination for the rendered 1080p MP4 | String |
Video Workflow Advanced Features
- Server-Sent Events (SSE) integration for real-time processing feedback and heartbeat monitoring.
- Automated mapping of GUI-centric instructions (click, drag, open) into programmatic API calls.
- Support for multi-agent workflows where editing intents are classified and routed to specialized actions.
- Intelligent credit management with support for anonymous usage and registration-bound account top-ups.
- Flexible export options leveraging H.264 codecs for maximum platform compatibility across all Openclaw Skills applications.
SKILL.md
Loading
Related Openclaw Skills
Ramp Video
Ramp Video is an AI-driven video editing skill that automates complex speed ramping and slow-motion effects through simple natural language commands.
AI Anonymous Token — Anonymize Faces in Videos
An AI-powered video processing skill that automatically blurs faces and removes identifiable information from footage using cloud-based GPU rendering.
Format Converter — Convert Videos to MP4
A high-performance cloud video rendering skill that converts multiple video formats into web-ready 1080p MP4 files without local software.
Unified Video — AI Video Merger
An AI-driven video processing skill that automates merging multiple clips into a single, polished MP4 video with smooth transitions.
YouTube AI Subtitle Generator
A cloud-powered AI tool for generating accurate, multilingual subtitles and captioned 1080p MP4 exports for YouTube creators.
AI DJ Agency
A professional talent management pipeline for onboarding DJs and matching event organizers with qualified performers using a local Python-driven roster.
Featured*
