How do I install the Youtube Summarizer skill?

Run npx skillmds@latest add thedaviddias/youtube-summarizer in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Youtube Summarizer safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Youtube Summarizer?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Youtube Summarizer free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Youtube Summarizer?

thedaviddias (@thedaviddias) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Youtube Summarizer by thedaviddias — Agent Skill

Name: Youtube Summarizer
Rating: 4.666666666666667 (3 reviews)
Author: thedaviddias

Youtube Summarizer

Automatically fetch YouTube transcripts, generate structured summaries, and send full transcripts to messaging platforms. Use when a request includes YouTube URLs and needs metadata, key insights, or downloadable transcripts.

thedaviddias Updated Sep 10, 2026

File contents

YouTube Summarizer Skill

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

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

Quick Method: Use `summarize` CLI

The summarize CLI already handles YouTube videos:

summarize "https://www.youtube.com/watch?v=VIDEO_ID" --youtube auto

This is the preferred method for YouTube summarization.

With model selection

summarize "https://youtu.be/VIDEO_ID" --model google/gemini-3-flash-preview --youtube auto

Length options

summarize "URL" --youtube auto --length short   # Brief summary
summarize "URL" --youtube auto --length long    # Detailed summary
summarize "URL" --youtube auto --length xl      # Very detailed

Alternative: MCP YouTube Transcript Server

For more control, use the MCP server directly:

Setup (if not installed)

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

Fetch 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

URL Patterns

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)

Summary Template

When generating summaries manually, use this format:

📹 **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]

Quality Guidelines

Be concise: Summary should be scannable in 30 seconds
Be accurate: Don't add information not in the transcript
Be structured: Use consistent formatting
Adjust for length:
- Short videos (<5 min): Brief summary
- Long videos (>30 min): More detailed breakdown

Error Handling

If transcript fetch fails:

Check if video has captions enabled
Try with lang: 'en' fallback
Inform user that transcript is not available

If video ID extraction fails:

Ask user to provide the full YouTube URL or video ID

Environment Variables (for MCP server)

If using APIFY fallback:

export APIFY_API_TOKEN="..."  # Optional, for YouTube fallback

Store in 1Password: op://Jarvis/Apify API/credential

---name: youtube-summarizerdescription: Automatically fetch YouTube transcripts, generate structured summaries, and send full transcripts to messaging platforms. Use when a request includes YouTube URLs and needs metadata, key insights, or downloadable transcripts.---# YouTube Summarizer SkillAutomatically fetch transcripts from YouTube videos, generate structured summaries, and deliver full transcripts to messaging platforms.## When to UseActivate 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## Quick Method: Use `summarize` CLIThe `summarize` CLI already handles YouTube videos:```bashsummarize "https://www.youtube.com/watch?v=VIDEO_ID" --youtube auto```This is the **preferred method** for YouTube summarization.### With model selection```bashsummarize "https://youtu.be/VIDEO_ID" --model google/gemini-3-flash-preview --youtube auto```### Length options```bashsummarize "URL" --youtube auto --length short # Brief summarysummarize "URL" --youtube auto --length long # Detailed summarysummarize "URL" --youtube auto --length xl # Very detailed```## Alternative: MCP YouTube Transcript ServerFor more control, use the MCP server directly:### Setup (if not installed)```bashcd /root/clawdgit clone https://github.com/kimtaeyoon83/mcp-server-youtube-transcript.gitcd mcp-server-youtube-transcriptnpm install && npm run build```### Fetch Transcript```bashcd /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```## URL PatternsExtract 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)## Summary TemplateWhen generating summaries manually, use this format:```markdown📹 **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]```## Quality Guidelines- **Be concise:** Summary should be scannable in 30 seconds- **Be accurate:** Don't add information not in the transcript- **Be structured:** Use consistent formatting- **Adjust for length:** - Short videos (<5 min): Brief summary - Long videos (>30 min): More detailed breakdown## Error Handling**If transcript fetch fails:**- Check if video has captions enabled- Try with `lang: 'en'` fallback- Inform user that transcript is not available**If video ID extraction fails:**- Ask user to provide the full YouTube URL or video ID## Environment Variables (for MCP server)If using APIFY fallback:```bashexport APIFY_API_TOKEN="..." # Optional, for YouTube fallback```Store in 1Password: `op://Jarvis/Apify API/credential`

Frequently asked questions