Anthropic ships 'discernment-nudge', a skill whose only job is deciding when Claude should tell you to double-check it

GitHub (anthropics/skills)·medium signalXBlueskyLinkedInCopy link

Daniel San flagged the skill on August 20, calling it the "best trigger logic writing I've read this year" and noting the section on when NOT to fire is about three times longer than when to fire. The SKILL.md confirms it: the skill appends 2-3 follow-up questions after substantive answers users will act on (estimates, consequential advice, factual claims), at most once per conversation, and carves out trivial lookups, educational explanations, format conversions, code the user will run, creative writing and any request where the user already asked for a review. Install is `/plugin marketplace add anthropics/skills` then `/plugin install discernment-nudge@anthropic-agent-skills`; the repo sits at 170,610 stars.