Skip to content
AI Dev Toolkit.
Esc
  • AI Token CounterCount tokens for GPT, Claude, Gemini, DeepSeek, Qwen and more.Tool
  • LLM API Cost CalculatorEstimate per-request, daily and monthly API costs.Tool
  • AI Model ComparisonCompare prices, context windows and features across models.Tool
  • AI Model Pricing PagesSpecs, real costs and cheaper alternatives for popular models.Tool
  • Context Window CheckerSee whether your text fits each model’s context window.Tool
  • Subscription vs API CalculatorFind out whether a chat plan or the API is cheaper for you.Tool
  • GPU / VRAM CalculatorCheck how much VRAM a local model needs and which GPUs fit.Tool
  • Prompt Caching CalculatorEstimate savings from prompt caching.Tool

Claude skill · Learning and reasoning · Anthropic

Discernment nudge skill for Claude

After advice, analysis or a draft you might act on, adds two or three short questions that help you check the facts and the reasoning.

Command
/discernment-nudge
Licence
Apache-2.0, copying allowed with attribution
Folder
2 files, 21 KB
Runs code
No scripts

Overview

What it does

A skill about using AI output well. After a substantive answer, Claude appends a few follow-up prompts, each tied to something specific it just said, that invite you to verify a key fact, test an assumption or notice missing context.

It is deliberately restrained: at most once per conversation, and skipped for simple lookups, code you’re about to run, creative writing, casual chat, or when you’ve already asked Claude to double-check.

Triggers

When Claude uses it

  • After advice, plans, estimates, data analysis, factual claims or drafts such as proposals and emails that you may rely on.
Its description, which Claude matches against
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.

What it needs

  • Nothing to install; a single SKILL.md.

Install

How to install it

Claude Code

Plugin (type in Claude Code)
/plugin marketplace add anthropics/skills
/plugin install discernment-nudge@anthropic-agent-skills

The discernment-nudge plugin installs this skill only. Its skills are then namespaced, such as /discernment-nudge:discernment-nudge.

Or copy the folder (shell)
git clone --depth 1 https://github.com/anthropics/skills.git
mkdir -p ~/.claude/skills
cp -r skills/skills/discernment-nudge ~/.claude/skills/

That makes it a personal skill, available as /discernment-nudge in all your projects. Copy it into .claude/skills/ in a repository instead to share it with your team.

claude.ai and the Claude API

Zip the skill folder, then in claude.ai open Customize > Skills, choose + and Create skill, then Upload a skill. Code execution must be turned on.

Upload with the Python SDK
from anthropic import Anthropic
from anthropic.lib import files_from_dir

client = Anthropic()
skill = client.skills.create(files=files_from_dir("discernment-nudge"))
print(skill.id)  # use as a custom skill_id with the code execution tool

Checks

SKILL.md validator results

Its SKILL.md (209 lines) run through our SKILL.md validator, with the folder’s file list, for both targets. These check the file’s format, not whether the skill works well.

Claude Code

0 errors, 0 warnings, 0 tips

claude.ai and the API

0 errors, 0 warnings, 1 tip

  • tipThe Claude Help Center’s upload guide gives a 200-character description limit for claude.ai, though the platform docs say 1,024. Keep it under 200 if you’ll upload it there.

Folder

What’s in the folder

  • LICENSE.txt11 KB
  • SKILL.md10 KB

SKILL.md sections

  1. Discernment nudge
  2. Why this exists
  3. When to offer the nudge
  4. When not to
  5. Writing the prompts
  6. Output format

Source

Licence and source

Related

All Claude skillsWrite your own skillSlash command builderGuide: subagents, skills and commands