video-viewing

Video Viewing and Analysis

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "video-viewing" with this command: npx skills add andchir/remotion-animations/andchir-remotion-animations-video-viewing

Video Viewing and Analysis

Download and analyze video files from direct URLs with frame extraction and metadata retrieval.

Quick Start

The simplest way to download a video:

python scripts/download_video.py "https://example.com/video.mp4"

This downloads the video to /mnt/user-data/outputs/ (or current directory if not available).

Options

Custom Output Directory

Use -o or --output to specify a different output directory:

python scripts/download_video.py "URL" -o /path/to/directory

Custom Filename

Use -n or --name to specify a custom filename (without extension):

python scripts/download_video.py "URL" -n my_video

Extract Frames

Use -f or --frames to extract key frames from the video:

python scripts/download_video.py "URL" -f

This extracts frames at regular intervals and saves them as images for visual analysis.

Get Video Info

Use -i or --info to get video metadata without downloading:

python scripts/download_video.py "URL" -i

This displays duration, resolution, codec, frame rate, and file size.

Complete Examples

  • Download video with default settings:

python scripts/download_video.py "https://previews.customer.envatousercontent.com/h264-video-previews/dfb637cb-f04e-46dc-99dc-256fa6090958/61509131.mp4"

  • Download and extract frames for analysis:

python scripts/download_video.py "https://example.com/video.mp4" -f

  • Get video information only:

python scripts/download_video.py "https://example.com/video.mp4" -i

  • Download to custom directory with custom name:

python scripts/download_video.py "https://example.com/video.mp4" -o /custom/path -n my_video

How It Works

The skill uses standard Python libraries to:

  • Download video files using requests with streaming support

  • Extract video metadata using ffprobe (part of ffmpeg)

  • Extract key frames using ffmpeg

  • Support resume for partially downloaded files

Viewing Downloaded Videos

After downloading, Claude can analyze the video content by:

  • Extracting frames at key intervals

  • Analyzing the extracted images to describe video content

  • Providing metadata about duration, resolution, and format

Requirements

The script requires:

  • Python 3.7+

  • requests library (installed automatically)

  • ffmpeg and ffprobe for frame extraction and metadata (optional)

Install ffmpeg on Ubuntu/Debian:

sudo apt-get install ffmpeg

Install ffmpeg on macOS:

brew install ffmpeg

Important Notes

  • Only supports direct video file URLs (not streaming platforms like YouTube)

  • Supported formats: mp4, webm, mkv, avi, mov, m4v, wmv, flv

  • Large files are downloaded with progress indication

  • Frame extraction requires ffmpeg to be installed

  • Downloads are saved to /mnt/user-data/outputs/ by default, or current directory

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

text-animation-copier

No summary provided by upstream source.

Repository SourceNeeds Review
Research

Loan Calculator

贷款计算器。等额本息/等额本金计算、方案对比、提前还款分析、贷款能力评估、还款计划表、再融资分析。Loan calculator with equal installment/principal, comparison, prepayment analysis, affordability, schedule,...

Registry SourceRecently Updated
1690ckchzh
Research

Artist Research

Performs in-depth artist analysis combining Spotify API and external web data to report streaming stats, market position, and monetization potential.

Registry SourceRecently Updated
Research

Amazon-analysis-skill

Find winning Amazon products with 14 battle-tested selection strategies & 6-dimension risk assessment. Backed by 200M+ product database. Use when user asks a...

Registry SourceRecently Updated