Mk youtube get info
Skill kouko/monkey-knowledge-youtube-skills/skills/mk-youtube-get-info
Get YouTube video metadata (title, channel, duration, views, subtitle availability). Use when user wants video details or needs to check subtitle availability before summarization.From its SKILL.md
npx -y skills add kouko/monkey-knowledge-youtube-skills --skill mk-youtube-get-infoAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.5 KB, as published. Nobody here has run it
YouTube Video Info
Get video details and generate content summary.
Quick Start
/mk-youtube-get-info <URL> [browser]
Examples
# Basic usage (auto-detects cookies if needed)
/mk-youtube-get-info https://www.youtube.com/watch?v=dQw4w9WgXcQ
# Specify browser for cookie authentication
/mk-youtube-get-info https://www.youtube.com/watch?v=dQw4w9WgXcQ chrome
How it Works
- Execute:
{baseDir}/scripts/info.sh "<URL>" - Parse JSON to get video metadata
- Try to get subtitles for summarization
- Generate summary based on subtitle content
- If no subtitles, display video info only
Output Format
{
"video_id": "dQw4w9WgXcQ",
"title": "Video Title",
"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
"channel": "Channel Name",
"channel_url": "https://www.youtube.com/channel/UCuAXFkgsw1L7xaCfnd5JJOw",
"duration_string": "10:30",
"view_count": 1234567,
"upload_date": "20240101",
"language": "en",
"availability": "public",
"description": "Video description (first 500 chars)",
"has_subtitles": true,
"subtitle_languages": ["en", "ja", "zh-Hant"],
"has_auto_captions": true,
"auto_caption_count": 157
}
Fields
| Field | Description |
|---|---|
video_id | YouTube video ID |
title | Video title |
url | Full video URL |
channel | Channel name |
channel_url | Channel URL |
duration_string | Duration (e.g., "10:30") |
view_count | Number of views |
upload_date | Upload date (YYYYMMDD) |
language | Primary language (ISO 639-1 code) |
availability | Access level: public, unlisted, members_only, subscriber_only, needs_auth, premium_only, private |
description | Video description (truncated to 500 chars) |
has_subtitles | Whether manual subtitles exist |
subtitle_languages | Array of available subtitle language codes |
has_auto_captions | Whether auto-generated captions exist |
auto_caption_count | Number of auto-generated caption languages |
Centralized Metadata Store
This skill automatically saves video metadata to /tmp/monkey_knowledge/youtube/meta/{YYYYMMDD}__{video_id}.meta.json. This metadata can be accessed by downstream skills (caption, audio, transcribe, summary) to include video information in their outputs.
Content Summary
(Generated from subtitle analysis)
- Key point 1
- Key point 2
- ...
Notes
- Uses system yt-dlp/jq if available, otherwise auto-downloads on first run
- Cookie Fallback: If initial request fails, automatically retries with browser cookies (auto-detects Chrome, Firefox, Safari, Edge, Brave)
- Browser Parameter: Optionally specify
chrome,firefox,safari,edge, orbraveto use specific browser cookies
Next Step
After obtaining video info, determine the summarization path based on subtitle availability:
- If
has_subtitles: trueorhas_auto_captions: true: Invoke/mk-youtube-get-captionto download subtitles - If both are
false: Invoke/mk-youtube-get-audioto download audio for transcription
To generate a complete summary, always follow the full pipeline — do NOT skip directly to summarization without first obtaining a transcript through one of the above paths.