mcpField
Y
yt-competitive-analysis

yt-competitive-analysis

github.com/ericosiuMarketing & growth3.7k206 installsUpdated 5w ago
Repository

About yt-competitive-analysis

A YouTube channel analysis skill for marketers and creators. It uses YouTube Data API v3 to identify videos that outperform a channel’s average and extract title patterns, with a feedback loop for checking packaging against channel analytics.

Key features

  1. 01Analyze selected channels
  2. 02Use predefined channel sets
  3. 03Find videos above channel averages
  4. 04Extract patterns from outlier titles
  5. 05Compare packaging with channel analytics
  6. 06Review post-publish performance

Use cases

  1. 01Find high-performing competitor videos
  2. 02Study title formats for video planning
  3. 03Compare candidate packaging with historical results
  4. 04Review a published video at set intervals

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/ericosiu/ai-marketing-skills --skill yt-competitive-analysis

After installing, type/yt-competitive-analysisin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

analyze.py
README.md
requirements.txt

Details

From the project README

YouTube Competitive Analysis

Outlier detection and packaging pattern extraction for YouTube channels.

When to Use

  • User asks for YouTube competitive analysis
  • User wants to find viral video patterns
  • User wants packaging/title inspiration from specific creators
  • User wants to track competitor YouTube performance

Prerequisites

  • YouTube Data API v3 key set as $YOUTUBE_API_KEY

Usage

# Analyze specific channels
python3 analyze.py "$YOUTUBE_API_KEY" --channels "@handle1,@handle2" --days 30

# Use predefined sets
python3 analyze.py "$YOUTUBE_API_KEY" --set ai
python3 analyze.py "$YOUTUBE_API_KEY" --set business
python3 analyze.py "$YOUTUBE_API_KEY" --set both

# Export formats
python3 analyze.py "$YOUTUBE_API_KEY" --set both --output json
python3 analyze.py "$YOUTUBE_API_KEY" --set both --output console

Predefined Channel Sets

AI Creators: Jeff Su, Alex Finn, Riley Brown, Dan Martell, Matt Wolfe, Nate Herk, Grace Leung, Matt Berman

Business Creators: Alex Hormozi, Gary Vaynerchuk, Patrick Bet-David, Codie Sanchez, Leila Hormozi, Iman Gadzhi, My First Million

Output Interpretation

  • Multiplier: Times above channel average (2.0x = double normal)
  • Outlier threshold: 2x average. Study anything above this.
  • Title patterns: Common words in outlier titles indicate proven formats
  • Cadence: Videos per week. Higher cadence creators may have lower per-video averages.

Channel Analytics Feedback Loop

Competitive analysis is only half the loop. When you have access to the channel's own analytics, compare candidate packaging against actual performance after publish.

Before recommending a package:

  • Pull channel baseline by topic, title pattern, thumbnail pattern, length, publish day/time, and format.
  • Check impressions, CTR, average view duration, retention curve, watch time, subscribers gained, comments, and traffic source.
  • Compare the proposed title/thumbnail/hook against similar historical videos and competitor outliers.

After publishing:

  1. Log video ID, title, thumbnail concept, hook, topic bucket, retention devices, and publish date.
  2. Pull analytics after the chosen readback window.
  3. Compare baseline vs candidate.
  4. Patch title formulas, thumbnail rules, hook patterns, retention beats, chapter structure, Shorts selection, or repurposing guidance only if the candidate wins.

Readback windows:

  • 24-48 hours for CTR and early retention
  • 7 days for average view duration and watch time
  • 28 days for topic durability and subscriber gain

Do not call packaging validated until analytics are checked. Otherwise it is a screenplay wearing a lab coat.

Packaging Skeletons (Proven Formats)

Long-form:

  • "X, Clearly Explained"
  • "X hours of Y in Z minutes"
  • "The Laziest Way to X"
  • "Give me X minutes and I'll Y"
  • "X INSANE Use Cases for Y"

Shorts:

  • "2024 vs 2025 X" (year comparison)
  • "Bad Good Great X" (tier ranking)
  • "Stop doing X, do Y instead" (contrarian)

Comments

Markdown supported