discernment-nudge
This skill helps users scrutinize AI-generated content before acting on it by appending follow-up questions to verify facts, probe reasoning, and notice missing context
Lift—not yet benchmarked
82
Trustsecurity · quality · license · upkeep
Scan Saferisk 0/100
License—metadata + link-out
Not yet benchmarked
Lift = pass-rate with the skill minus without, with a 95% confidence interval. This skill hasn’t been through a run yet — request one via the contact form. How benchmarking works →