Agent Skills Index

Directory / Anthropic Agent Skills / discernment-nudge

discernment-nudge

skill Software development

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. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.
Description from the SKILL.md front matter.

Install

Add the marketplace (once, in Claude Code)
/plugin marketplace add anthropics/skills
Install the discernment-nudge bundle that contains it
/plugin install discernment-nudge@anthropic-agent-skills
Or with GitHub CLI v2.90+ (any supported agent)
gh skill install anthropics/skills discernment-nudge

Commands follow each host's documentation (Claude Code, Claude.ai, Claude API docs). gh skill needs GitHub CLI 2.90 or later and is in public preview.

Catalog
Anthropic Agent Skills (anthropic-agent-skills)
Author
Anthropic
Source code
anthropics/skills
License
Complete terms in LICENSE.txt
Repository stars
182,130 for anthropics/skills (the whole catalog repo)
Added to catalog
2026-08-17
Last change
2026-08-17
Installed via bundle
discernment-nudge

What it contains

Similar in Software development