Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Extracts transcripts, summaries, and metadata from YouTube videos. Combines a summarize tool for fast transcript retrieval with AI analysis for audience sentiment and key takeaways. Optionally downloads audio or frames from specific video segments.
Combining transcript extraction, AI analysis, and media download in one workflow avoids switching between yt-dlp, a transcription service, and a separate summarizer.
When to use it
- Summarizing a long lecture or conference talk
- Pulling transcript text from a tutorial video
- Extracting key timestamps from a product review
- Analyzing viewer sentiment from comment sections
- Downloading specific video segments for offline review
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Analyze this YouTube video and give me the key takeaways with timestamps
- 1Fetch transcript using summarize tool with --extract-only flag
- 2Compress transcript into a 5-point summary
- 3Run Gemini analysis on core message and practical takeaways
- 4Check comments for audience sentiment if available
- 5Return summary with source link and key moment timestamps
Structured summary with core message, 5 key points, sentiment note, and timestamped source links
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.