Video Generation
Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.
npx skills add jjyaoao/HelloAgents --skill video-generation --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides building video generation capabilities using the z-ai-web-dev-sdk, allowing applications to create videos from text prompts or images and manage tasks asynchronously with polling and result retrieval.
How it works
- Emphasizes backend usage of the z-ai-web-dev-sdk (not in client-side code).
- Describes two primary workflows: simple CLI-based task creation and SDK-based programmatic task creation.
- Demonstrates creating a video generation task with parameters (prompt, quality, with_audio, size, fps, duration) and then polling for results via an async result query, eventually extracting a video URL from several possible result fields.
- Provides examples for image-to-video and keyframe-based video generation, with guidance to encode images as base64 data URIs and match MIME types, or use URLs (less reliable).
- Covers handling of task status (PROCESSING, SUCCESS, FAIL) and includes polling configurations (poll interval, max polls).
- Includes code samples for checking status and for polling with exponential backoff, using ZAI.create() and zai.video.generations.create(...) calls.
- Describes an asynchronous two-step pattern: create Task, then poll for results.
When to use it
- Use for applications that generate video content from text prompts or images, including image-to-video and start/end-frame workflows, with optional audio.
- Use for batch or production environments requiring custom logic, task queues, or integration with web applications.
What it can touch
- The backend SDK pathways, specifically:
- Assorted calls to ZAI.create(),
- zai.video.generations.create(...),
- zai.async.result.query(...),
- CLI tool paths via z-ai video (as an alternative for simple tasks).
- It references handling of task results from fields like result.video_result[0].url, result.video_url, result.url, or result.video.
Caveats
- Requires using the z-ai-web-dev-sdk in backend code only, not in client-side code.
- Encourages base64-encoded image data for image_url parameters to improve reliability and match MIME types to image formats.
- Mentions multiple acceptable result fields for extracting the final video URL, implying variability in API responses.
- Describes optional features like with_audio, custom size, fps, duration; outcomes depend on the underlying API and task polling success.
# Video Generation Skill This skill guides the implementation of video generation functionality using the z-ai-web-dev-sdk package, enabling AI models to create videos from text descriptions or images through asynchronous task processing. ## Skills Path **Skill Location**: `{project_path}/skills/video-generation` This skill is located at the above path in your project. **Reference Scripts**: Example test scripts are available in the `{Skill Location}/scripts/` directory for quick testing and reference. See `{Skill Location}/scripts/video.ts` for a working example. ## Overview Video Generation allows you to build applications that can create video content from text prompts or images, with customizable parameters like resolution, frame rate, duration, and quality settings. The API uses an asynchronous task model where you create a task and poll for results. **IMPORTANT**: z-ai-web-dev-sdk MUST be used in backend code only. Never use it in client-side code. ## Prerequisites The z-ai-web-dev-sdk package is already installed. Import it as shown in the examples below. ## CLI Usage (For Simple Tasks) For simple video generation tasks, you can use the z-ai CLI instead of writing code. The
- Skills Path
- Overview
- Prerequisites
- CLI Usage (For Simple Tasks)
- Basic Text-to-Video
- Custom Quality and Settings
- Image-to-Video
- First-Last Frame Mode
- With Audio Generation
- Save Output
- Custom Polling Parameters
- CLI Parameters
- Supported Resolutions
- Checking Task Status Later
Generate video with automatic polling z-ai video --prompt "A cat playing with a ball" --poll Using short options z-ai video -p "Beautiful landscape with mountains" --poll Quality mode (speed or quality) z-ai video -p "Ocean waves at sunset" --quality quality --poll Custom resolution and FPS z-ai video \ Custom duration (5 or 10 seconds) z-ai video -p "Fireworks display" --duration 10 --poll
What does the Video Generation skill do?
Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.
How do I install it?
Run `npx skills add jjyaoao/HelloAgents --skill video-generation --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From jjyaoao/HelloAgents, a repository with 2,615 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.