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
HEAD:6fbd10303ba9 Safe10/15/2026
Update tracking (upstream polling, re-scan, re-benchmark, accept-or-stay-pinned) ships with Phase 4.