Skill · em Outros
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…
Procedência
- Origem: anthropics/skills
- Caminho:
skills/discernment-nudge - Versão fixada:
33375500bcea98d610eb30ce10ac4e59b89c390d - Licença: Apache-2.0
- Espelhado em 25/09/2026
- 6,8 mil instalações no skills.sh (lido em 25/09/2026)
Antes de instalar
2 arquivos · 21,4 KB · só texto, nenhum script
Instalar na sua CLI
O comando baixa a versão fixada (commit 3337550) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.
Claude Code
Neste projeto: instala em .claude/skills/discernment-nudge/.
d=".claude/skills/discernment-nudge" u="https://raw.githubusercontent.com/anthropics/skills/33375500bcea98d610eb30ce10ac4e59b89c390d/skills/discernment-nudge" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/LICENSE.txt" "$u/LICENSE.txt"
Global: instala em ~/.claude/skills/discernment-nudge/.
d="$HOME/.claude/skills/discernment-nudge" u="https://raw.githubusercontent.com/anthropics/skills/33375500bcea98d610eb30ce10ac4e59b89c390d/skills/discernment-nudge" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/LICENSE.txt" "$u/LICENSE.txt"
Codex
Neste projeto: instala em .agents/skills/discernment-nudge/.
d=".agents/skills/discernment-nudge" u="https://raw.githubusercontent.com/anthropics/skills/33375500bcea98d610eb30ce10ac4e59b89c390d/skills/discernment-nudge" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/LICENSE.txt" "$u/LICENSE.txt"
Global: instala em ~/.agents/skills/discernment-nudge/.
d="$HOME/.agents/skills/discernment-nudge" u="https://raw.githubusercontent.com/anthropics/skills/33375500bcea98d610eb30ce10ac4e59b89c390d/skills/discernment-nudge" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/LICENSE.txt" "$u/LICENSE.txt"
Antigravity
Neste projeto: instala em .agents/skills/discernment-nudge/.
d=".agents/skills/discernment-nudge" u="https://raw.githubusercontent.com/anthropics/skills/33375500bcea98d610eb30ce10ac4e59b89c390d/skills/discernment-nudge" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/LICENSE.txt" "$u/LICENSE.txt"
Global: instala em ~/.gemini/antigravity-cli/skills/discernment-nudge/.
d="$HOME/.gemini/antigravity-cli/skills/discernment-nudge" u="https://raw.githubusercontent.com/anthropics/skills/33375500bcea98d610eb30ce10ac4e59b89c390d/skills/discernment-nudge" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/LICENSE.txt" "$u/LICENSE.txt"
Peça ao Rook
Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/anthropic.discernment-nudge
Prévia do SKILL.md
---
name: discernment-nudge
description: >
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.
license: Complete terms in LICENSE.txt
---
# Discernment nudge
## Why this exists
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:
- **Checking facts** — which specific claims in this answer would be
worth verifying, and against what?
- **Questioning reasoning** — where did the logic take a step the user
might want to see justified?
…