追加 2-3 个 后续问题,帮用户核实关键事实与推理假设
在你给出用户可能据以行动的实质性回答或草稿之后——包括建议或推荐、起草的成果如目标、计划、方案、提案、邮件、估算或预测、数据分析或解释、他们可能依赖的事实性主张,或多步论证——在完成回复之前调用此技能;如果适用,随后追加 2-3 个 简短的后续问题,每个都与你刚产出内容中的具体内容相关联,帮助用户检查关键事实、探究推理或假设、注意缺失的上下文。每次对话最多执行一次。
Skill 会改变智能体的行为并可能包含可执行脚本。安装前请先阅读其 SKILL.md 与脚本,社区来源尤其要谨慎。
npx skills add anthropics/skills -s discernment-nudge
npx skills add anthropics/skills -s discernment-nudge -g
npx skills add anthropics/skills -l
git clone --depth 1 https://github.com/anthropics/skills.git /tmp/skills-src && cp -r /tmp/skills-src/skills/discernment-nudge ~/.claude/skills/
命令使用开源的 skills CLI(vercel-labs/skills),支持 Claude Code、Cursor、Codex 等多种智能体。
摘自项目自己的说明,具体以项目主页为准。
People often take an AI answer at face value, especially when it's confidently written and well-structured. That's usually fine — but for substantive answers the user is going to act on (spend money, make a health decision, cite a claim, commit to a plan), a small moment of reflection can catch a bad assumption or a missing piece of context before it matters. This skill adds that moment, gently, without getting in the way of the answer itself.
The goal is to model three discernment habits from the AI Fluency framework, not to lecture about them:
Offer it when your answer contains content the user would benefit from scrutinizing before acting on it. The clearest cases:
Leave it off when the nudge would be noise — or worse, when it would override something the user already told you. Silence is the right
…