Video Download

Video Download

Download videos from YouTube, TikTok, and other platforms to local MP4 files. Handles format selection, platform-prefixed dedup, TikTok cookie fallback, and Douyin/TikTok browser-based fallback automatically.

Quick Start

# Download any video
bash ${CLAUDE_SKILL_DIR}/scripts/download-video.sh '<URL>'

# Download to a custom directory
bash ${CLAUDE_SKILL_DIR}/scripts/download-video.sh '<URL>' 'path/to/output'

Prerequisites

yt-dlp --version   # Required. Install: brew install yt-dlp (macOS) or pip install yt-dlp

Optional (for Douyin/TikTok fallback):

• agent-browser installed globally (npm install -g agent-browser)
• Chrome for Testing installed (agent-browser install)

Usage

Single Video

bash ${CLAUDE_SKILL_DIR}/scripts/download-video.sh '<URL>'

The script handles everything automatically:

• Extracts a platform-prefixed video ID (yt-dQw4w9WgXcQ, tk-7571284267028729101, vid-aHR0cHM6Ly93d3)
• Saves to resources/references/<video_id>.mp4
• Skips download if file already exists (dedup)
• Retries TikTok downloads with --cookies-from-browser chrome on failure
• Removes zero-byte leftovers from interrupted downloads

Batch Download

for URL in '<URL1>' '<URL2>' '<URL3>'; do
  bash ${CLAUDE_SKILL_DIR}/scripts/download-video.sh "$URL"
done

Script Output

Post-Download Actions

After a successful download, the user may want to:

1. Analyze the video — extract script, style, or rhythm:

   renoise analyze <path> --target video --language <user-language> --json
   

2. Add to Material Pool — for use as reference material in video generation:

   node ${CLAUDE_PLUGIN_ROOT}/skills/renoise-cli/scripts/material-ingest.mjs <path>
   

Suggest these options to the user after download completes.

Douyin/TikTok Fallback

When yt-dlp fails for Douyin or TikTok URLs (common with 403 errors or region-restricted content), use the one-step browser-based fallback:

bash ${CLAUDE_SKILL_DIR}/scripts/download-fallback.sh '<douyin-or-tiktok-url>' 'output-dir'

This script wraps the full agent-browser + GreenVideo flow into a single command (open → paste URL → parse → extract video URL → download → close).

Manual Fallback Steps

If the fallback script is unavailable, follow these steps:

1. Open GreenVideo:

   agent-browser open "https://greenvideo.cc/en/"
   

2. Paste URL and parse:

   agent-browser snapshot
   agent-browser fill <input-ref> "<video-url>"
   agent-browser click <start-button-ref>
   

3. Wait 5 seconds, then extract video URL:

   agent-browser eval "
   (function() {
     const nuxtData = window.__NUXT__;
     if (!nuxtData) return 'ERROR: No Nuxt data found';
     const str = JSON.stringify(nuxtData);
     const mp4Match = str.match(/https?:[^\\\"]*(?:mp4|video|play|aweme|douyinvod|bilivideo)[^\\\"]{0,500}/g);
     if (mp4Match && mp4Match.length > 0) return mp4Match[0];
     return 'ERROR: No video URL found in Nuxt state';
   })()
   "
   

4. Download and cleanup:

   curl -L -o ~/Downloads/<filename>.mp4 "<extracted-video-url>"
   agent-browser close
   

Video ID Logic

Troubleshooting