A powerful AI media generation toolkit for face swapping, motion transfer, and digital human creation via RunningHub AI.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install shell-image-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 shell-image-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 Shell Image & Video Skill?
The Shell Image & Video skill integrates advanced RunningHub AI workflows directly into your agent environment. It enables high-fidelity image and video manipulations, including Wan2.2 motion transfer and high-definition dance generation. By leveraging these Openclaw Skills, developers can automate complex media processing tasks through simple command-line scripts. The skill acts as a bridge to RunningHub AI, providing ready-to-use scripts for everything from simple face swaps to sophisticated digital human animations.
Shell Image & Video Skill Use Cases
- Swapping faces in photos for personalized content creation.
- Transferring dance movements from a reference video to a static portrait using Wan2.2.
- Generating talking head digital humans for marketing or educational videos with lip-sync.
- Creating side-by-side comparison GIFs or videos for before and after showcases.
- Producing high-definition 150-frame dance videos from single images and motion references.
How Shell Image & Video Skill Works
- The user provides a target image or video along with specific parameters via CLI commands.
- The skill automatically checks media constraints and uses ImageMagick to compress inputs if they exceed 10MB.
- The request is dispatched to the RunningHub AI engine using the integrated Openclaw Skills API workflow.
- The script monitors the task status in real-time, implementing a retry logic for timeouts or network issues.
- Upon completion, the final media URL is extracted from the JSON response and stored in the local output directory.
Shell Image & Video Skill Setup
To get started with this skill, ensure you have Node.js, ffmpeg, and ImageMagick installed on your system. Navigate to the skill directory and configure your API key:
cd ~/.openclaw/workspace/Shell-openclaw-image-video-skill
# The skill comes pre-configured, but you can set your own key if needed
export RUNNINGHUB_API_KEY="your_api_key_here"
Shell Image & Video Skill Data Schema & Taxonomy
The skill manages data through a structured script and output hierarchy:
| Component | Description |
|---|---|
| Scripts | Located in scripts/, including wan22-animate.js and face-swap.js |
| Output | All generated JSON responses and media URLs are saved in the output/ folder |
| Media Handling | Uses ffmpeg for video processing and ImageMagick for image optimization |
| API Config | Leverages the RunningHub V2 OpenAPI for workflow execution |
Shell Image & Video Skill Advanced Features
- Support for Wan2.2 and Motion Pro for high-fidelity expression and movement transfer.
- Infinite length lip-sync capabilities for extended audio files using the lipsync-extended workflow.
- Multi-agent compatibility allowing for automated video production pipelines within Openclaw Skills.
- Intelligent error handling for task timeouts (task_id not found) and rate limiting (HTTP 429).
- Specialized digital human workflows including HeyGem and TTS integration for synchronized speech.
SKILL.md
Loading
Related Openclaw Skills
Incident Response Playbook Generator API
Automate the creation of tailored incident response playbooks based on organizational data and security compliance requirements.
ClawInboxRAG
A secure, read-only skill for parsing and executing mailbox retrieval commands against a local Gmail RAG backend.
Lottery Predictor V3.6
A sophisticated data-driven lottery prediction engine for Openclaw Skills utilizing an 8-dimensional intelligent scoring system and historical backtesting.
gen-design
An AI-powered system design assistant that generates architecture documents and data models through interactive technology selection and domain knowledge integration.
Central Key Management System
An enterprise-grade platform for the secure generation, verification, and centralized lifecycle management of cryptographic API keys.
Browser Automation
An AI-powered browser automation skill that enables natural language interaction with websites through a high-level CLI.
Featured*
