YouTube Summarizer Skill

Automatically fetch transcripts from YouTube videos, generate structured summaries, and deliver full transcripts to messaging platforms.

Mode

Detect from context or ask: "Quick TL;DR, full summary, or full summary with content angles?"

Default: standard — use quick if they just want the gist. Use deep if they want to extract the video into usable content.

Why This vs ChatGPT?

Problem with ChatGPT: It can't access YouTube transcripts directly. You have to manually copy/paste captions or use a third-party tool first, then feed the text to ChatGPT. Multi-step, clunky, loses video metadata.

This skill provides:

1. One-step transcript extraction - Drop a YouTube URL, get the full transcript automatically
2. Structured summarization - Consistent format (thesis → insights → takeaway) every time, not random bullet points
3. Video metadata included - Title, channel, views, publish date embedded in summary
4. Full transcript delivery - Saves timestamped transcript to file and sends to Telegram/chat platforms
5. Works from VPS/cloud - Uses Android client emulation to bypass YouTube's cloud IP blocking (where yt-dlp fails)
6. Multi-language support - Auto-fetches in requested language with English fallback

You can replicate this by manually enabling captions, copying text, pasting to ChatGPT, reformatting the output, saving to a file, and uploading. Takes 5-10 minutes. This skill does it in 15-20 seconds.

When to Use

Activate this skill when:

• User shares a YouTube URL (youtube.com/watch, youtu.be, youtube.com/shorts)
• User asks to summarize or transcribe a YouTube video
• User requests information about a YouTube video's content
• You need to analyze video content for research or content creation

Dependencies

Required: MCP YouTube Transcript server must be installed at: /root/clawd/mcp-server-youtube-transcript

If not present, install it:

cd /root/clawd
git clone https://github.com/kimtaeyoon83/mcp-server-youtube-transcript.git
cd mcp-server-youtube-transcript
npm install && npm run build

Workflow

1. Detect YouTube URL

Extract video ID from these patterns:

• https://www.youtube.com/watch?v=VIDEO_ID
• https://youtu.be/VIDEO_ID
• https://www.youtube.com/shorts/VIDEO_ID
• Direct video ID: VIDEO_ID (11 characters)

2. Fetch Transcript

Run this command to get the transcript:

cd /root/clawd/mcp-server-youtube-transcript && node --input-type=module -e "
import { getSubtitles } from './dist/youtube-fetcher.js';
const result = await getSubtitles({ videoID: 'VIDEO_ID', lang: 'en' });
console.log(JSON.stringify(result, null, 2));
" > /tmp/yt-transcript.json

Replace VIDEO_ID with the extracted ID. Read the output from /tmp/yt-transcript.json.

3. Process the Data

Parse the JSON to extract:

• result.metadata.title - Video title
• result.metadata.author - Channel name
• result.metadata.viewCount - Formatted view count
• result.metadata.publishDate - Publication date
• result.actualLang - Language used
• result.lines - Array of transcript segments

Full text: result.lines.map(l => l.text).join(' ')

4. Generate Summary

Create a structured summary using this template:

📹 **Video:** [title]
👤 **Channel:** [author] | 👁️ **Views:** [views] | 📅 **Published:** [date]

**🎯 Main Thesis:**
[1-2 sentence core argument/message]

**💡 Key Insights:**
- [insight 1]
- [insight 2]
- [insight 3]
- [insight 4]
- [insight 5]

**📝 Notable Points:**
- [additional point 1]
- [additional point 2]

**🔑 Takeaway:**
[Practical application or conclusion]

Aim for:

• Main thesis: 1-2 sentences maximum
• Key insights: 3-5 bullets, each 1-2 sentences
• Notable points: 2-4 supporting details
• Takeaway: Actionable conclusion

5. Save Full Transcript

Save the complete transcript to a timestamped file:

/root/clawd/transcripts/YYYY-MM-DD_VIDEO_ID.txt

Include in the file:

• Video metadata header (title, channel, URL, date)
• Full transcript text
• URL reference for easy lookup

6. Platform-Specific Delivery

If channel is Telegram:

message --action send --channel telegram --target CHAT_ID \
  --filePath /root/clawd/transcripts/YYYY-MM-DD_VIDEO_ID.txt \
  --caption "📄 YouTube Transcript: [title]"

If channel is other/webchat: Just reply with the summary (no file attachment).

7. Reply with Summary

Send the structured summary as your response to the user.

Real Case Study

User: Content creator researching competitor YouTube strategies

Challenge: Needed to analyze 20+ competitor videos per week to identify trending topics, messaging patterns, and content gaps. Manual process: watch video, take notes, transcribe key quotes. Time: 30-45 min per video.

Solution with youtube-summarizer:

1. Drop YouTube URL in chat
2. Get structured summary in 20 seconds
3. Full transcript saved for reference
4. Copy key insights for content planning doc

Workflow example:

User: Analyze this video: https://youtube.com/watch?v=abc123
[20 seconds later]

📹 Video: "10 AI Tools That Will Replace Your Job in 2026"
👤 Channel: TechFuturist | 👁️ Views: 847K | 📅 Published: Jan 12, 2026

🎯 Main Thesis:
AI tools are automating creative and knowledge work faster than expected, but the real opportunity is in augmentation, not replacement.

💡 Key Insights:
- ChatGPT usage among marketers jumped from 12% to 67% in one year
- Video editing time reduced by 80% using AI tools like Descript
- The biggest wins come from combining tools (Notion + Claude + Zapier)
- Companies hiring "AI workflow designers" to optimize human-AI collaboration
- Workers using AI secretly outperform peers by 40% (BCG study)

📝 Notable Points:
- Shows examples of 3 small businesses that 10× output with AI
- Warns against over-automation: "AI can write, but can't think strategically"

🔑 Takeaway:
Don't ask "Will AI replace me?" Ask "How can I use AI to become 10× more valuable?"

Results after 8 weeks:

• Time saved: 25 hours/week (from 600 min to 60 min for 20 videos)
• Content output: 3 videos/week (up from 1/week)
• Better insights: Full transcripts searchable, found patterns missed when just watching
• Competitive intel: Built database of 160+ competitor video summaries with key quotes
• ROI quote: "This skill turned competitor research from a chore into an assembly line."

Why This Beats Manual Methods

Error Handling

If transcript fetch fails:

• Check if video has captions enabled
• Try with lang: 'en' fallback if requested language unavailable
• Inform user that transcript is not available and suggest alternatives:
  • Manual YouTube transcript feature (Settings → Show transcript)
  • Video may not have captions
  • Try a different video

If MCP server not installed:

• Provide installation instructions
• Offer to install it automatically if in appropriate context

If video ID extraction fails:

• Ask user to provide the full YouTube URL or video ID

**If video is age-rest