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.