Install
openclaw skills install video-summarizeClawHub Security found sensitive or high-impact capabilities. Review the scan results before using.
Video summarization. Trigger: 1.User provides a video link (Bilibili/YouTube/Douyin/Twitter/TikTok etc.), 2.Summarize this video
openclaw skills install video-summarizeIntelligently fetch video transcripts → Let LLM summarize the content
Video Link → Check Cache → Try downloading subtitles → Has subtitles? → Extract text directly → Summarize
↓ No subtitles
Download audio → Whisper transcribe → Summarize
Powered by yt-dlp, supports 1000+ platforms:
| Platform | Example URL |
|---|---|
| Bilibili | https://www.bilibili.com/video/BVxxx |
| YouTube | https://www.youtube.com/watch?v=xxx |
| Douyin | https://www.douyin.com/video/xxx |
| Twitter/X | https://twitter.com/user/status/xxx |
| TikTok | https://www.tiktok.com/@user/video/xxx |
https://www.instagram.com/p/xxx | |
| AcFun | https://www.acfun.cn/v/acxxx |
| iQiyi/Youku/Tencent | Various Chinese video platforms |
| Others | Any platform supported by yt-dlp |
The script will automatically check and install missing dependencies:
brew install ffmpegbrew install whisper-cppbrew install python3Run:
scripts/install_dependency.sh
Note: First-time installation may take a while depending on your network speed.
# Process a video (first run transcribes, subsequent runs return cached result)
scripts/process.sh "video_url"
Pipeline:
summarize_result/{title}_transcript_raw.txtThen ask me to summarize and save the result as a markdown file!
https://www.bilibili.com/video/BV1s8UZBZEa8https://www.youtube.com/watch?v=dQw4w9WgXcQhttps://www.douyin.com/video/7123456789https://twitter.com/user/status/123456789https://www.tiktok.com/@user/video/123456789Filenames use the video title for clarity, special characters handled automatically:
cache/{title}/
└── transcript_raw.txt # Raw transcript
summarize_result/
└── {title}.md # Summary
Filename sanitization:
《》【】:? → _/\:*?"<>| → __video-summarize/
├── cache/ # Cache directory
│ └── {title}/ # Per-video directory
│ ├── transcript_raw.txt # Raw transcript (preserved)
│ ├── status.json # Processing status (cleaned up)
│ ├── subs/ # Subtitle temp dir (cleaned up)
│ ├── audio.m4a # Audio file (cleaned up)
│ └── audio.wav # WAV format (cleaned up)
├── summarize_result/ # Summary output directory
│ └── {title}.md # Summary file
├── whisper-models/
│ └── ggml-base.bin
├── scripts/
│ ├── install_dependency.sh
│ ├── process.sh
│ └── safe_filename.py
└── SKILL.md
| Platform | Manual Subtitles | Auto Subtitles |
|---|---|---|
| YouTube | ✅ Supported | ✅ Supported |
| Bilibili | ✅ Supported | ⚠️ Partial |
| Others | Varies | Varies |
Subtitle priority: Chinese manual > English manual > Auto-generated