agentleFS
duncan-buildroomduncan-buildroom/profit-room-skills/skills/yt-search/SKILL.md

yt-search

Skill18 starsChanged 4 months agoMITView on GitHub

Search YouTube and return structured video results with metadata. Use this skill whenever the user wants to search YouTube, find videos on a topic, research what's trending on YouTube, compare YouTube videos, or look up YouTube creators/channels. Triggers on phrases like "search YouTube for", "find videos about", "what videos are there on", "YouTube results for", or any request involving YouTube video discovery or research.

  • Installs packages

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Search YouTube using yt-dlp and return structured, formatted results with engagement metrics.

    line 8
  2. Distinctive:

    Run the search script:

    line 15

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

YouTube Search

Search YouTube using yt-dlp and return structured, formatted results with engagement metrics.

Requirements

  • yt-dlp on PATH (pip install yt-dlp). If it's not installed, I'll tell you the one command to add it.

How to use

Run the search script:

python3 ~/.claude/skills/yt-search/scripts/search.py <query> [--count N] [--months N] [--no-date-filter]

Parameters

  • <query> — search terms (required)
  • --count N — number of results to return (default: 20)
  • --months N — only show videos from the last N months (default: 6)
  • --no-date-filter — include videos of any age

Examples

# Basic search (top 20, last 6 months)
python3 ~/.claude/skills/yt-search/scripts/search.py claude code tutorial

# Fewer results, shorter window
python3 ~/.claude/skills/yt-search/scripts/search.py obsidian workflow --count 5 --months 3

# All time, no date filter
python3 ~/.claude/skills/yt-search/scripts/search.py AI agents --count 10 --no-date-filter

Output format

Each result includes:

  • Title
  • Channel name and subscriber count
  • View count
  • Duration
  • Upload date
  • Engagement ratio (views / subscribers) — higher means the video outperformed the channel's base
  • Direct URL

Results are separated by dividers for easy scanning. Status messages go to stderr; formatted results go to stdout.

Notes

  • yt-dlp must be installed (pip install yt-dlp)
  • The script fetches 2x the requested count to compensate for date filtering
  • Subscriber counts come from yt-dlp metadata and may occasionally be unavailable (shown as N/A)

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.