How do I install the Video Understanding skill?

Run npx skillmds@latest add modbender/video-understanding-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Video Understanding safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: executes scripts, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Video Understanding?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Video Understanding free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Video Understanding?

modbender (@modbender) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Video Understanding by modbender — Agent Skill

Name: Video Understanding
Rating: 4.2 (5 reviews)
Author: modbender

Video Understanding

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.

modbender Updated Sep 22, 2026 12 repo stars

File contents

Video Understanding (Gemini)

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

Requirements

yt-dlp — brew install yt-dlp / pip install yt-dlp
ffmpeg — brew 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

Flag	Description	Default
`-q` / `--question`	Question to answer (added to default fields)	none
`-p` / `--prompt`	Override entire prompt (ignores -q)	structured JSON
`-m` / `--model`	Gemini model	gemini-2.5-flash
`-o` / `--output`	Save output to file	stdout
`--keep`	Keep downloaded video file	false
`--download-only`	Download only, skip analysis	false
`--max-size`	Max file size in MB	500
`--raw`	Raw text output instead of JSON	false

How It Works

YouTube URLs → Passed directly to Gemini (no download needed)
All other URLs → Downloaded via yt-dlp → uploaded to Gemini File API → poll until processed
Gemini analyzes video with structured prompt → returns JSON
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

---name: video-understanding-2description: 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.---# Video Understanding (Gemini)Analyze videos using Google Gemini's multimodal video understanding. Supports 1000+ video sources via yt-dlp.## Requirements- `yt-dlp` — `brew install yt-dlp` / `pip install yt-dlp`- `ffmpeg` — `brew install ffmpeg` (for merging video+audio streams)- `GEMINI_API_KEY` environment variable## Default OutputReturns 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)```bashuv run {baseDir}/scripts/analyze_video.py "<video-url>"```### Ask a question (adds "answer" field)```bashuv run {baseDir}/scripts/analyze_video.py "<video-url>" -q "What product is shown?"```### Override prompt entirely```bashuv run {baseDir}/scripts/analyze_video.py "<video-url>" -p "Custom prompt" --raw```### Download only (no analysis)```bashuv run {baseDir}/scripts/analyze_video.py "<video-url>" --download-only -o video.mp4```## Options| Flag | Description | Default ||------|-------------|---------|| `-q` / `--question` | Question to answer (added to default fields) | none || `-p` / `--prompt` | Override entire prompt (ignores -q) | structured JSON || `-m` / `--model` | Gemini model | gemini-2.5-flash || `-o` / `--output` | Save output to file | stdout || `--keep` | Keep downloaded video file | false || `--download-only` | Download only, skip analysis | false || `--max-size` | Max file size in MB | 500 || `--raw` | Raw text output instead of JSON | false |## How It Works1. **YouTube URLs** → Passed directly to Gemini (no download needed)2. **All other URLs** → Downloaded via yt-dlp → uploaded to Gemini File API → poll until processed3. Gemini analyzes video with structured prompt → returns JSON4. Temp files and Gemini uploads cleaned up automatically## Supported SourcesAny URL supported by [yt-dlp](https://github.com/yt-dlp/yt-dlp/blob/master/supportedsites.md): 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`

Frequently asked questions