원클릭으로 Manus에서 모든 스킬 실행

시작하기

kuavi-analyze

스타3

포크0

업데이트2026년 2월 22일 13:21

Full end-to-end video analysis with KUAVi

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

apicurius

apicurius/VideoRLM

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

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?

이 저장소의 다른 Skills

같은 저장소

kuavi-pixel-analysis

apicurius/VideoRLM

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.

2026-02-223

kuavi-corpus

apicurius/VideoRLM

Multi-video corpus indexing and cross-video search

2026-02-223

kuavi-deep-analyze

apicurius/VideoRLM

Deep multi-pass video analysis with parallel sharding and zoom

2026-02-223

kuavi-deep-search

apicurius/VideoRLM

Multi-pass search with query refinement for hard-to-find video content. Use when initial search returns low-confidence results or no matches.

2026-02-223

kuavi-index

apicurius/VideoRLM

Index a video file for KUAVi analysis

2026-02-223

kuavi-predictive

apicurius/VideoRLM

Predictive video understanding — anticipate actions, predict future content, verify coherence, classify activities

2026-02-223

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?