This project provides an AI-powered tool for Claude Code, enabling users to efficiently clip and repurpose YouTube videos. It automates the generation of semantically meaningful chapters, extracts precise video segments, translates subtitles into a bilingual format, and hardcodes them into the video. The tool is designed for content creators and researchers looking to streamline video analysis and social media content generation.

How It Works

The core of the tool lies in its AI-driven semantic chapter analysis, which understands video content to create natural topic breaks (2-5 minutes each), unlike mechanical time-based splitting. It utilizes yt-dlp for robust video and subtitle downloading and FFmpeg with libass for frame-accurate clipping and subtitle burning. Subtitle translation is optimized through batch processing, drastically reducing API calls and improving efficiency.

Quick Start & Requirements

• Installation: Recommended: npx skills add https://github.com/op7418/Youtube-clipper-skill. Manual: git clone followed by bash install_as_skill.sh.
• Prerequisites: Python 3.8+, yt-dlp, and FFmpeg with libass support. macOS users must install ffmpeg-full via Homebrew.
• Dependencies: Python packages (yt-dlp, pysrt, python-dotenv) are installed automatically.
• Configuration: Customizable via a .env file in ~/.claude/skills/youtube-clipper/ (e.g., FFmpeg path, output directory, video quality, translation batch size, target language, chapter duration).
• Documentation: SKILL.md, TECHNICAL_NOTES.md, FIXES_AND_IMPROVEMENTS.md, and guides in references/.

Highlighted Details

• AI Semantic Chapter Analysis: Generates chapters based on content understanding, not just time.
• Batch Translation Optimization: Achieves ~95% reduction in API calls for subtitle translation.
• Bilingual Subtitle Format: Outputs SRT files containing both English and target language subtitles.
• Automated Content Summarization: Generates social media content snippets for platforms like Xiaohongshu and Douyin.

Maintenance & Community

Bug reporting and feature requests are managed via GitHub Issues. No explicit links to community channels (e.g., Discord, Slack) or roadmap details are provided in the README.

Licensing & Compatibility

This project is licensed under the MIT License, generally permitting commercial use and integration with closed-source projects.

Limitations & Caveats

FFmpeg requires libass support for subtitle burning, necessitating specific installation steps on macOS (ffmpeg-full). Filenames containing special characters are automatically sanitized. Slow downloads can be mitigated by configuring a proxy in the .env file. Subtitle translation issues may arise from API rate limiting or network instability.