What it does
The discernment-nudge skill, published by davila7, is invoked after an assistant gives a substantive answer or draft the user may act on, such as advice, a plan, a proposal or email, an estimate, a data analysis, factual claims, or a multi-step argument. Before the reply is finalised, it appends two or three short follow-up questions, each tied to something specific in the output, to help the user check key facts, probe reasoning or assumptions, and notice missing context. It is used at most once per conversation.
It suits moments when a user is about to rely on what has been produced. It is skipped for trivial how-to requests or simple lookups, purely educational explanations, requests only to format, convert or assemble a file from supplied content, code the user will run, creative writing or casual chat, and requests that already ask for a double-check, citation or review.
The exact boundaries and output format are set out in the skill file, which the publisher's description refers to for detail.
Limitations and requirements
Not applied to trivial how-to or lookup requests, purely educational explanations, formatting or conversion tasks, code the user will run, creative writing or casual chat, or requests that already ask for a check, citation or review. Boundaries and output format are defined in the skill file.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 8
discernment-nudge
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation.
As shown on www.aitmpl.com when we last read it