Generate CogVideo for Openclaw

A professional AI video generation skill that leverages the Zhipu AI CogVideoX model to transform text prompts into cinematic video content.

ilaus
v1.0.2
Mar 29, 2026
0
1.2k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install cogvideox-generator

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install cogvideox-generator 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 Generate CogVideo?

The generate_cogvideo skill is a powerful integration for AI agents within the Openclaw Skills framework, enabling the programmatic creation of video content. By utilizing Zhipu AI's state-of-the-art CogVideoX model, developers can generate high-fidelity videos that include options for audio synchronization and specific resolution controls.

This skill bridges the gap between text-based reasoning and visual content creation, allowing agents to produce media assets on demand. Whether you need rapid prototyping (speed mode) or high-definition visual storytelling (quality mode), this skill provides a streamlined interface for sophisticated video synthesis.

Generate CogVideo Use Cases

  • Automating social media video content creation from text descriptions.
  • Generating visual assets for presentations or marketing materials via AI agents.
  • Rapid prototyping of cinematic scenes for storyboarding and creative direction.
  • Enhancing multi-modal agent responses with dynamically generated video and audio.

How Generate CogVideo Works

  1. The AI agent receives a text-based request for video creation from the user.
  2. The agent processes the natural language and maps it to the generate_cogvideo skill parameters, including resolution and frame rate.
  3. A secure request is sent to the Zhipu AI CogVideoX API using the provided ZHIPUAI_API_KEY.
  4. The model synthesizes the video frames and optional audio track based on the prompt complexity.
  5. The generated video asset is returned to the agent for storage or display to the end-user.

Generate CogVideo Setup

To use this skill within the Openclaw Skills environment, you must configure your API credentials:

  1. Obtain an API Key from the Zhipu AI (BigModel) platform.
  2. Set the environment variable in your Openclaw configuration:
export ZHIPUAI_API_KEY='your_api_key_here'
  1. Ensure your agent has permission to access external network requests for API communication.

Generate CogVideo Data Schema & Taxonomy

The skill utilizes a structured input schema to define the video output characteristics:

Parameter Type Description Default
prompt string Detailed text description of the video content Required
quality string Output mode: 'quality' (prioritize fidelity) or 'speed' (prioritize time) 'quality'
size string Video resolution (e.g., '1920x1080') '1920x1080'
fps integer Frames per second: 30 or 60 30
with_audio boolean Whether to generate an accompanying audio track True

Generate CogVideo Advanced Features

  • Multi-mode optimization allowing users to toggle between Quality Priority and Speed Priority.
  • Integrated audio generation for a complete multimedia experience out-of-the-box.
  • Support for high-resolution 1080p output at 60 FPS for professional-grade smoothness.
  • Seamless integration with other Openclaw Skills to chain video generation with data analysis or creative writing.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*