From video-understanding
Analyze and understand video content using Google Gemini. Supports local video files (mp4, mov, webm, avi, mkv) and YouTube links up to an hour long. Use this skill when you need to understand, summarize, or extract information from video content.
How this skill is triggered — by the user, by Claude, or both
Slash command
/video-understanding:video-understandingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill supports video analysis using Google Gemini models. Supported formats:
This skill supports video analysis using Google Gemini models. Supported formats:
| Category | Extensions |
|---|---|
| Video | .mp4, .mov, .webm, .avi, .mkv |
Reference: https://ai.google.dev/gemini-api/docs/video-understanding
bash ${CLAUDE_PLUGIN_ROOT}/scripts/gemini.sh --file=VIDEO_PATH "YOUR QUESTION ABOUT THE VIDEO"
Arguments:
--file - Required: Local video file path or YouTube URL--model - Optional: Model to use (defaults to gemini-3-flash-preview)Examples:
# Analyze a local video
npx -y superconductor-gemini-skills --file=video.mp4 "Summarize this video"
npx -y superconductor-gemini-skills --file=presentation.mov "What are the key points discussed?"
# Analyze a YouTube video
npx -y superconductor-gemini-skills --file="https://www.youtube.com/watch?v=F0I5M4Pb85k" "Summarize the video"
npx -y superconductor-gemini-skills --file="https://youtu.be/F0I5M4Pb85k" "What happens at the 2 minute mark?"
# Find specific moments
npx -y superconductor-gemini-skills --file=video.mp4 "What is the best timestamp to represent this video's content?"
The GEMINI_API_KEY environment variable must be set. Get your key at: https://ai.google.dev/gemini-api/docs/api-key
| Model ID | Context Window | Pricing (Input / Output) |
|---|---|---|
gemini-3-pro-preview | 1M / 64k | $2 / $12 (<200k), $4 / $18 (>200k) |
gemini-3-flash-preview | 1M / 64k | $0.50 / $3 |
gemini-2.5-pro | 1M / 65k | $1.25 / $10 (<200k), $2.50 / $15 (>200k) |
gemini-2.5-flash | 1M / 65k | $0.30 / $2.50 |
npx claudepluginhub superconductor/superconductor-plugin-marketplace --plugin video-understandingAnalyzes video files or YouTube URLs: extracts frames/audio, detects scenes/motion/silence/transitions via ffmpeg tools with structured workflow.
Analyzes a video synchronously using TwelveLabs AI to return a summary or answer questions about its content. Accepts video URLs, file paths, asset IDs, or indexed video IDs.
Imports, searches, and analyzes videos from YouTube, TikTok, Instagram using Memories.ai LVMM for persistent intelligence, summarization, knowledge bases, and social trends research.