| name | kuavi-analyze |
| description | Full end-to-end video analysis with KUAVi |
| agent | video-analyst |
| context | fork |
| argument-hint | <video-path> <question> |
| disable-model-invocation | true |
KUAVi Analyze Video
Perform comprehensive video analysis: index, search, reason, and answer.
Instructions
- Parse
$ARGUMENTS for: video path and question/task.
- Index: If the video is not yet indexed, call
kuavi_index_video.
- Orient: Call
kuavi_get_scene_list to understand the video structure.
- Search: Use the SEARCH-FIRST strategy to find relevant content:
- Decompose the question into search sub-queries
- Search across multiple fields (summary, action, visual, temporal)
- Search transcript for spoken content
- Inspect: Extract frames for the most relevant segments.
- Reason: Synthesize findings from visual evidence and transcript.
- Verify: Cross-reference visual and audio evidence.
- Answer: Provide a clear, evidence-based answer.
Arguments
The first argument is the video path. Remaining text is the question.
Example: /kuavi-analyze /path/to/video.mp4 What is the main topic of this presentation?