跳至主要内容
小龙虾小龙虾AI
🤖

Video Understanding

Use whenever the user provides any video URL, YouTube link, or video file, even if they only ask to watch, look at, react to, understand, analyze, summarize,...

下载1.9k
星标5
版本1.3.0
图像视频
安全通过
⚙️脚本

技能说明


name: video-understanding description: > Analyze videos with Google Gemini multimodal AI. Download from any URL (Loom, YouTube, TikTok, Vimeo, Twitter/X, Instagram, 1000+ sites) and get transcripts, descriptions, and answers to questions. Use when asked to watch, analyze, summarize, or transcribe a video, or answer questions about video content. Triggers on video URLs or requests involving video understanding. compatibility: "Requires yt-dlp, ffmpeg, and GEMINI_API_KEY environment variable. Python 3.10+ with uv." metadata: openclaw: emoji: "🎬" requires: bins: ["yt-dlp", "ffmpeg"] env: ["GEMINI_API_KEY"] primaryEnv: "GEMINI_API_KEY" install: - id: "yt-dlp-brew" kind: "brew" formula: "yt-dlp" bins: ["yt-dlp"] label: "Install yt-dlp (brew)" - id: "ffmpeg-brew" kind: "brew" formula: "ffmpeg" bins: ["ffmpeg"] label: "Install ffmpeg (brew)"

Video Understanding (Gemini)

Analyze videos using Google Gemini's multimodal video understanding. Supports 1000+ video sources via yt-dlp.

Requirements

  • yt-dlpbrew install yt-dlp / pip install yt-dlp
  • ffmpegbrew install ffmpeg (for merging video+audio streams)
  • GEMINI_API_KEY environment variable

Default Output

Returns structured JSON:

  • transcript — Verbatim transcript with [MM:SS] timestamps
  • description — Visual description (people, setting, UI, text on screen, flow)
  • summary — 2-3 sentence summary
  • duration_seconds — Estimated duration
  • speakers — Identified speakers

Usage

Analyze a video (structured JSON output)

uv run {baseDir}/scripts/analyze_video.py "<video-url>"

Ask a question (adds "answer" field)

uv run {baseDir}/scripts/analyze_video.py "<video-url>" -q "What product is shown?"

Override prompt entirely

uv run {baseDir}/scripts/analyze_video.py "<video-url>" -p "Custom prompt" --raw

Download only (no analysis)

uv run {baseDir}/scripts/analyze_video.py "<video-url>" --download-only -o video.mp4

Options

FlagDescriptionDefault
-q / --questionQuestion to answer (added to default fields)none
-p / --promptOverride entire prompt (ignores -q)structured JSON
-m / --modelGemini modelgemini-2.5-flash
-o / --outputSave output to filestdout
--keepKeep downloaded video filefalse
--download-onlyDownload only, skip analysisfalse
--max-sizeMax file size in MB500
--rawRaw text output instead of JSONfalse

How It Works

  1. YouTube URLs → Passed directly to Gemini (no download needed)
  2. All other URLs → Downloaded via yt-dlp → uploaded to Gemini File API → poll until processed
  3. Gemini analyzes video with structured prompt → returns JSON
  4. Temp files and Gemini uploads cleaned up automatically

Supported Sources

Any URL supported by yt-dlp: Loom, YouTube, TikTok, Vimeo, Twitter/X, Instagram, Dailymotion, Twitch, and 1000+ more.

Tips

  • Use -q for targeted questions on top of the full analysis
  • YouTube is fastest (no download step)
  • Large videos (10min+) work fine — Gemini File API supports up to 2GB (free) / 20GB (paid)
  • The script auto-installs Python dependencies via uv

如何使用「Video Understanding」?

  1. 打开小龙虾AI(Web 或 iOS App)
  2. 点击上方「立即使用」按钮,或在对话框中输入任务描述
  3. 小龙虾AI 会自动匹配并调用「Video Understanding技能完成任务
  4. 结果即时呈现,支持继续对话优化

相关技能