← Back to Skills Marketplace
video-generate
by
volcengine_skills
· GitHub ↗
· v1.0.0
· MIT-0
885
Downloads
0
Stars
38
Active Installs
1
Versions
Install in OpenClaw
/install video-generate
Description
Generate videos using Seedance models. Invoke when user wants to create videos from text prompts, images, or reference materials.
Usage Guidance
Review before installing. Use a dedicated, low-privilege API key, avoid putting private prompts or media URLs into requests unless you trust the provider, and do not let the agent store real credentials in a workspace env file without explicit approval and a clear plan to remove them later.
Capability Assessment
Purpose & Capability
The code and documentation are coherent with a Seedance/Ark video-generation skill: it sends prompts and optional image, video, or audio reference URLs to an external API and polls for results.
Instruction Scope
The normal generation workflow is scoped, but the error-handling instruction directs the agent to write missing API credentials into a workspace environment file, activate them, and retry without a clear consent or containment step.
Install Mechanism
The artifact includes an executable Python script and no remote installer or hidden setup behavior; however, formal permission/capability declarations are thin compared with the documented network and credential use.
Credentials
Using an API key and outbound network requests is expected for this provider integration, but persisting the key in a workspace env file is broader secret handling than needed and may expose the credential to other tools or future sessions.
Persistence & Privilege
No background service, privilege escalation, destructive action, or local indexing was found, but the credential-persistence instruction creates a lasting workspace configuration change.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video-generate - After installation, invoke the skill by name or use
/video-generate - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Major update: Now generates videos (not just images) using Seedance models and supports multimodal input.
- Replaced image generation script with a comprehensive video generation script (`video_generate.py`)
- Rebranded skill: now named "video-generate" and focused on video creation from text, images, video, or audio inputs
- Supports multiple video models, customizable parameters (aspect ratio, duration, resolution, etc.), multimodal references, and optional audio generation
- Expanded environment variable requirements and detailed API/documentation for video task configuration
- Added robust error handling for missing API keys and user feedback
- SKILL.md completely rewritten for video-focused workflow, usage examples, and options
Metadata
Frequently Asked Questions
What is video-generate?
Generate videos using Seedance models. Invoke when user wants to create videos from text prompts, images, or reference materials. It is an AI Agent Skill for Claude Code / OpenClaw, with 885 downloads so far.
How do I install video-generate?
Run "/install video-generate" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is video-generate free?
Yes, video-generate is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does video-generate support?
video-generate is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created video-generate?
It is built and maintained by volcengine_skills (@warm-wm); the current version is v1.0.0.
More Skills