What it does
This skill builds a repeatable record of whether a brand is retrieved, mentioned and cited across defined prompt families.
When to use it
Use it when a team needs a baseline or wants to evaluate whether source improvements change answer behavior over time.
Instructions
Freeze the prompt set before testing. Record system, date, answer, cited URL and confidence notes. Repeat observations before reporting a pattern.
Do not collapse mentions and citations into one score. They represent different outcomes.