YouTube Clipper Skill

YouTube Clipper is an AI-powered YouTube video clipper for Claude Code. It downloads videos, generates semantic chapters, clips segments, translates subtitles to bilingual format, and burns subtitles into videos.

Use Cases

• Extract highlights from YouTube videos (e.g., tech interviews, courses, talks)
• Generate bilingual subtitles (Chinese/English) for multi-language distribution
• Create short clips ready for social media platforms (Xiaohongshu, Douyin, WeChat)
• Automatically segment long videos by semantic content for quick navigation

Core Capabilities

• AI Semantic Analysis — Generate fine-grained chapters (2–5 minutes each) by understanding video content, not just mechanical time splitting
• Precise Clipping — Use FFmpeg to extract video segments with frame-accurate timing
• Bilingual Subtitles — Batch translate subtitles to Chinese/English with 95% API call reduction and 10x faster translation
• Subtitle Burning — Hardcode bilingual subtitles into videos with customizable styling
• Content Summarization — Auto-generate social media content (Xiaohongshu, Douyin, WeChat)

How It Works

1. Environment Check — Verifies yt-dlp, FFmpeg, and Python dependencies
2. Video Download — Downloads video (up to 1080p) and English subtitles
3. AI Chapter Analysis — Claude analyzes subtitles to generate semantic chapters (2–5 min each)
4. User Selection — Choose which chapters to clip and processing options (translate subtitles, burn subtitles, generate summary)
5. Processing — Clips video, translates subtitles, burns subtitles (if requested)
6. Output — Organized files in ./youtube-clips/<timestamp>/

What You Need to Provide

• A YouTube video URL
• A command in Claude Code, e.g.: Clip this YouTube video: https://youtube.com/watch?v=VIDEO_ID
• Optionally, select which chapters to clip and whether to generate bilingual subtitles, burn subtitles, or create a summary

What You Will Get

For each clipped chapter, the output directory contains:

./youtube-clips/20260122_143022/
└── Chapter_Title/
    ├── Chapter_Title_clip.mp4              # Original clip (no subtitles)
    ├── Chapter_Title_with_subtitles.mp4    # With burned-in subtitles
    ├── Chapter_Title_bilingual.srt         # Bilingual subtitle file
    └── Chapter_Title_summary.md            # Social media content

Configuration

Edit ~/.claude/skills/youtube-clipper/.env to customize:

# FFmpeg path (auto-detected if empty)
FFMPEG_PATH=

# Output directory (default: current working directory)
OUTPUT_DIR=./youtube-clips

# Video quality limit (720, 1080, 1440, 2160)
MAX_VIDEO_HEIGHT=1080

# Translation batch size (20-25 recommended)
TRANSLATION_BATCH_SIZE=20

# Target language for translation
TARGET_LANGUAGE=中文

# Target chapter duration in seconds (180-300 recommended)
TARGET_CHAPTER_DURATION=180

Selection Guide

Unlike mechanical time-based splitting, this skill uses AI semantic analysis to:

• Understand content semantics and identify natural topic transitions
• Generate meaningful chapter titles and summaries
• Ensure complete coverage with no gaps

Usage Examples

Example: Extract highlights from a tech interview

Input:

Clip this video: https://youtube.com/watch?v=Ckt1cj0xjRM

AI-generated chapters:

1. [00:00 - 03:15] AGI as an exponential curve, not a point in time
2. [03:15 - 06:30] China's gap in AI development
3. [06:30 - 09:45] The impact of chip bans

Select chapters → get clipped videos with bilingual subtitles and social media content.

Requirements & Notes

System Dependencies

FFmpeg libass Support

• macOS users: The standard ffmpeg package from Homebrew does NOT include libass support (required for subtitle burning). Install ffmpeg-full:

  brew uninstall ffmpeg
  brew install ffmpeg-full
  

• Verify libass support: ffmpeg -filters 2>&1 | grep subtitles — should output subtitles V->V (...)

Troubleshooting

• Slow video download: Set a proxy in .env: YT_DLP_PROXY=http://proxy-server:port or socks5://proxy-server:port
• Subtitle translation fails: The skill auto-retries up to 3 times. If persistent, check network connectivity, Claude API status, or reduce TRANSLATION_BATCH_SIZE
• Special characters in filenames: Automatically sanitized by removing \ / : * ? " < > |, replacing spaces with underscores, and limiting length to 100 characters