Menu
Index a video file for KUAVi analysis
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Compositional pixel analysis patterns using kuavi_eval for counting, motion detection, change tracking, and visual comparison. Use when questions require precise measurements, object counting, or frame-by-frame comparison.
Full end-to-end video analysis with KUAVi
Multi-video corpus indexing and cross-video search
Deep multi-pass video analysis with parallel sharding and zoom
Multi-pass search with query refinement for hard-to-find video content. Use when initial search returns low-confidence results or no matches.
Predictive video understanding — anticipate actions, predict future content, verify coherence, classify activities
| name | kuavi-index |
| description | Index a video file for KUAVi analysis |
| argument-hint | <video-path> |
| disable-model-invocation | true |
Index a video file to enable semantic search, scene detection, and analysis.
$ARGUMENTS or in the conversation.kuavi_index_video MCP tool with the video path./kuavi-search for finding specific content, or /kuavi-analyze for full analysis.User: /kuavi-index /path/to/video.mp4
Call kuavi_index_video with video_path="/path/to/video.mp4", then report:
scene_stride for per-frame averaged embeddings (smoother scene detection)store_feature_maps=True for spatial analysisauto_fps=True to automatically compute FPS from video duration (targets 120 frames)For multi-video workflows, use kuavi_index_corpus instead:
kuavi_index_corpus(video_paths=["/path/to/video1.mp4", "/path/to/video2.mp4"])
This builds a cross-video index enabling kuavi_search_corpus for cross-video semantic search.