Systems Lab

Agent skill

yt-competitive-analysis

Analyze YouTube channels for outlier videos and packaging patterns.

activeNeeds a keyActs undeclared433 words

Filed under Positioning and messaging.

From ericosiu/ai-marketing-skills · 21 skills · 3,449 · pushed 2026-08-16

What it does when it runs

Analyze YouTube channels for outlier videos and packaging patterns. Identifies what's working (2x+ average views) across any set of channels. Use when asked for YouTube competitive analysis, viral video patterns, or packaging/title inspiration.

Read from the skill and the 3 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
  • API_KEY
  • YOUTUBE_API_KEY
Hosts it reaches
  • console.cloud.google.com
  • levelingup.beehiiv.com
  • singlebrain.com
  • www.googleapis.com
  • www.singlegrain.com
  • youtube.com
Tool permissions it declares
No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.
Actions present in the files
shellwrites files

Ask about yt-competitive-analysis

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗
git clone --depth 1 --filter=blob:none --sparse https://github.com/ericosiu/ai-marketing-skills.git /tmp/ai-marketing-skills
git -C /tmp/ai-marketing-skills sparse-checkout set "yt-competitive-analysis"
mkdir -p ~/.claude/skills/yt-competitive-analysis
cp -R "/tmp/ai-marketing-skills/yt-competitive-analysis/." ~/.claude/skills/yt-competitive-analysis/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Before you install: this skill will not complete its job on a bare agent. It needs API_KEY, YOUTUBE_API_KEY, which you have to obtain separately.

The skill

Source on GitHub ↗

Reproduced in full from ericosiu/ai-marketing-skills/blob/2eb0f34edb8d6111ca8b2930fed92413c9af7002/yt-competitive-analysis/SKILL.md, which is licensed MIT (repository). 433 words, 11 headings.

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)

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what yt-competitive-analysis does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.