agentleFS
Sign inStart free
larchankalarchanka/skills/yt-random-comment-picker/SKILL.md

yt-random-comment-picker

Skill31 starsChanged 7 days agoMITView on GitHub

Downloads YouTube video comments, filters to unique authors, and randomly selects one comment to return.

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Only top-level comments are considered (replies/thread comments are filtered out)

    line 64
  2. Distinctive:

    If multiple comments from the same author exist, only the first one encountered is kept

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Random Comment Picker

This skill downloads comments from a YouTube video, filters them to keep only comments with unique authors (first occurrence wins), and randomly selects one comment to return with author and text.

Skill Details

  • Name: yt-random-comment-picker
  • Version: 1.0.0
  • Description: Downloads YouTube video comments, filters to unique authors, and randomly selects one comment to return.

Usage

yt-random-comment-picker <youtube_video_url>

Example

yt-random-comment-picker https://youtu.be/VIDEO_ID

How It Works

  1. Download comments: Uses yt-dlp to fetch the comment section from the specified YouTube video URL
  2. Extract top-level comments: Filters to keep only top-level comments (not replies/thread comments)
  3. Filter unique authors: Keeps only the first comment from each unique author (subsequent duplicates are removed)
  4. Random selection: Uses Python's random.choice() to select one comment from the filtered list
  5. Output: Displays the selected comment with author and text, plus JSON output for programmatic use

Requirements

  • yt-dlp must be installed and available in PATH
  • Python 3.6+
  • Internet access to fetch YouTube comments

Output Format

Human-readable:

Author: @username
Comment: <comment text>

JSON (printed at end):

{
  "author": "@username",
  "text": "<comment text>",
  "likes": 5
}

Notes

  • The skill may take 30-60 seconds to download and process comments depending on the video's comment count
  • Only top-level comments are considered (replies/thread comments are filtered out)
  • If multiple comments from the same author exist, only the first one encountered is kept
  • The selection is truly random - each unique-author comment has equal probability of being selected
  • Works with any YouTube video URL that has comments available

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free