Skip to content
SkillMixed897 tokens in use

YouTube Competitive Analysis

Find outlier videos and recurring title patterns across the YouTube channels you choose, then check packaging against your own analytics.

3,862 stars on the repository MIT Licenseericosiu/ai-marketing-skills · yt-competitive-analysis
npx skills add ericosiu/ai-marketing-skills -s yt-competitive-analysis
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing YouTube Competitive Analysis costs

24tokens idle
897tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: analyze.py.

Touches

shelldetectednetworkdetectedcredentialsdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure23/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources5/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Reads credentials−15

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 25
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 25
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    analyze.py, line 15

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity88
  • Maintenance44
  • Community56
  • Maturity28
  • Momentum40

YouTube Competitive Analysis runs a Python script against the YouTube Data API for the channels you name or for two built-in sets of AI and business creators. It reports each video’s multiplier against its channel average, marks outliers at two times the average, lists common words in outlier titles and shows upload cadence.

The SKILL.md adds a feedback loop: compare a candidate title and thumbnail with your own history, log what you publish and read analytics back after 24 to 48 hours, 7 days and 28 days.

What You Get

  • A list of outlier videos with their multiplier against the channel average
  • Common title words and patterns drawn from the outliers
  • Upload cadence per channel in videos per week
  • JSON or console output for any channel set
  • A readback routine for judging your own packaging after publishing

Common Use Cases

  • Researching what is working for competitors before planning titles
  • Tracking a short list of creators over the last 30 days
  • Drafting title and thumbnail ideas from proven formats
  • Judging after publish whether a new package beat your baseline

What Makes It Unique

Many title tools stop at ideas. This skill measures each video against its own channel average, so a small channel’s breakout shows up next to a large one. It also states that packaging counts as validated only after your own analytics are checked, with set readback windows.

Under The Hood

The agent runs one Python script with your YouTube Data API key. The script calls the YouTube API over the network to list channels and videos, computes multipliers and title patterns locally and prints the result or writes JSON. The key is passed on the command line. The rest of the SKILL.md is guidance for the agent, such as which analytics to compare before and after publishing, and it does not run further commands.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers