On the bundled sample: 10 findings (5 errors, 5 warnings) in 3 files from 9 rules - base image, pip packages, git clone, torch.hub.load and an RF-DETR XL model.

Who it’s for
ML and computer-vision engineers shipping closed-source YOLO detection in SaaS back ends, edge cameras or robots.

What breaks, and when
Ultralytics: “An Enterprise License is required if you want to use Ultralytics YOLO without open-sourcing your entire project” - a torch.hub.load call or base image pulls it in with no requirements line.

What you get
• SKILL.md, an offline Node scanner and the 9-rule table
• file:line, severity and the licence reason per finding

See it first
The real output of the bundled example is on getreadystack.com/skills/yolo-agpl-license-check/ — free, no sign-up, so you see what it finds before you pay.

Install in 30 seconds
Unzip into ~/.claude/skills/, then ask Claude Code: “We ship a closed-source camera service that uses YOLO. Where does this repo depend on Ultralytics, and what would we swap it for? Don’t edit anything yet.”. Needs Node 16+.

What it does not do
Not legal advice; it maps dependencies as text.

FAQ
Q: How is this different from asking Claude without the skill?
A: The skill carries a dated rule table and a scanner that reads every file, so Claude quotes the exact date and line instead of guessing from memory.
Q: How do I get the files?
A: In your Whop library after paying: the lesson “yolo-agpl-license-check.zip”.