video-understand
Implement specialized video understanding capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze video content, understand motion and temporal sequences, extract information from video frames, describe video scenes, or perform video-based AI analysis. Optimized for MP4, AVI, MOV, and other common video formats.
npx skills add jjyaoao/HelloAgents --skill video-understand --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
Provides specialized video understanding functionality using the z-ai-web-dev-sdk package to analyze, describe, and extract information from video content, including motion, temporal sequences, and scene changes.
How it works
The skill includes code examples for single video analysis, scene understanding, motion and action detection, event timeline extraction, content classification, and various advanced use cases. It demonstrates use of ZAI.create() and zai.chat.completions.createVision to send prompts and a video_url payload, then returns content from response. It also covers batch processing and multi-turn video conversations.
Key operational patterns emphasized in the skill:
- Import and instantiate the SDK:
import ZAI from 'z-ai-web-dev-sdk';andconst zai = await ZAI.create(); - Send prompts along with a video URL via
video_urlin the message payload - Use
zai.chat.completions.createVisionto obtain a textual or structured response - Options include
thinkingtoggles and--streamin CLI variants, with responses parsed fromresponse.choices[0]?.message?.contentor parsed JSON for structured outputs - CLI and SDK pathways are illustrated for analysis, scene understanding, action detection, timeline extraction, classification, moderation, transcript generation, and educational summarization
Example capabilities showcased:
- Single Video Analysis
- Video Scene Understanding
- Motion and Action Detection
- Event Timeline Extraction
- Video Content Classification
- Video Transcript Generation (Visual Description)
- Sports Video Analysis
- Educational Video Summarization
- Batch Video Processing
When to use it
Use this skill when a user requires analysis of video content, motion, temporal sequences, or extraction of information from video frames. It is optimized for MP4, AVI, MOV, and other common video formats. It is intended for back-end usage only with z-ai-web-dev-sdk.
What it can touch
The skill relies on the z-ai-web-dev-sdk backend tool via ZAI.create() and zai.chat.completions.createVision calls. It references video inputs through video_url payloads in the messages. This includes scripts and examples in the scripts/ directory (e.g., video-understand.ts).
Caveats
- IMPORTANT: z-ai-web-dev-sdk MUST be used in backend code only. Never use it in client-side code.
- License for the skill in the repository is MIT, but the overall metadata indicates NOASSERTION for license in this listing; the skill text itself shows MIT usage guidance.
- The provided examples assume network access to video URLs or local paths as demonstrated; actual behavior depends on SDK response and environment.
# Video Understanding Skill This skill provides specialized video understanding functionality using the z-ai-web-dev-sdk package, enabling AI models to analyze, describe, and extract information from video content including motion, temporal sequences, and scene changes. ## Skills Path **Skill Location**: `{project_path}/skills/video-understand` this skill is located at 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-understand.ts` for a working example. ## Overview Video Understanding focuses specifically on video content analysis, providing capabilities for: - Video scene understanding and description - Action and motion detection - Temporal sequence analysis - Event detection in videos - Video content summarization - Scene change detection - People and object tracking across frames - Audio-visual content analysis (when applicable) **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
- Skills Path
- Overview
- Prerequisites
- CLI Usage (For Simple Tasks)
- Basic Video Analysis
- Analyze Local Videos
- Advanced Video Analysis
- Streaming Output
- CLI Parameters
- Supported Video Formats
- When to Use CLI vs SDK
- Recommended Approach
- Basic Video Understanding Implementation
- Single Video Analysis
Analyze a video from URL z-ai vision --prompt "Summarize what happens in this video" --image "https://example.com/video.mp4" z-ai vision -p "Describe the key events" -i "https://example.com/presentation.mp4" Analyze a local video file z-ai vision -p "What activities are shown in this video?" -i "./recording.mp4" Save response to file z-ai vision -p "Provide a detailed summary" -i "./meeting.mp4" -o summary.json Complex scene understanding with thinking z-ai vision \ Action detection
What does the video-understand skill do?
Implement specialized video understanding capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze video content, understand motion and temporal sequences, extract information from video frames, describe video scenes, or perform video-based AI analysis. Optimized for MP4, AVI, MOV, and other common video formats.
How do I install it?
Run `npx skills add jjyaoao/HelloAgents --skill video-understand --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.