Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Discernment Nudge

ASecurity

Build discernment habits: nudges and checklists for evaluating claims, spotting manipulation, and thinking clearly under pressure. Use when you want better judgment about what to believe and share.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgoreact

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill discernment-nudge --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Discernment Nudge?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Discernment Nudge
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-discernment-nudge/badge)](https://www.skillsdirectory.com/skills/aicodedecode-discernment-nudge)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: discernment-nudge
description: Build discernment habits: nudges and checklists for evaluating claims, spotting manipulation, and thinking clearly under pressure. Use when you want better judgment about what to believe and share.
category: productivity
---

# Discernment Nudge

## Overview

Discernment is the habit of pausing before believing: evaluating evidence, spotting manipulation, and updating beliefs gracefully.

In an age of viral claims and persuasive AI-generated content, discernment is a core life skill — not paranoia, but disciplined judgment.

This skill provides portable nudges: tiny checklists that trigger critical thinking exactly when it matters — before sharing, deciding, or arguing.

## When to use

- Evaluating surprising or emotional claims before sharing
- Spotting manipulation in media, marketing, or arguments
- Making decisions under hype or pressure
- Teaching critical thinking to teams or students
- Building personal resistance to misinformation

## Core concepts

- **The pause.**
  Emotional reaction (outrage, amazement, vindication) is the signal to pause, not to share. Strong emotion is manipulation's favorite vehicle.
- **Source check.**
  Who claims this? What's their track record? Do they show their work (data, methods, citations)? Anonymous viral claims start at zero credibility.
- **Evidence quality.**
  Anecdote < correlation < controlled study < meta-analysis. Ask: what would change my mind? If nothing, it's identity, not belief.
- **Incentive check.**
  Who benefits if I believe this? Follow the money, status, and tribal incentives — including your own (wanting it to be true).
- **The steelman test.**
  Can I state the opposing view fairly? If not, I don't understand the issue well enough to have a strong opinion.
- **Base rates.**
  How often are claims like this true? Extraordinary claims need extraordinary evidence — and most viral claims aren't extraordinary, just unverified.
- **Update gracefully.**
  Changing your mind with new evidence is the goal, not a failure. Track predictions; calibrate over time.
- **Nudge design.**
  Tiny friction before believing/sharing: a 3-question checklist, a 10-minute wait on outrage-bait, a 'verify before forwarding' rule.

## Practical workflow

1. **Install the pause.**
   Rule: never share anything that triggered strong emotion without a 10-minute cool-down. Set it as a phone reminder if needed.
2. **Build the 3-question checklist.**
   1) Who's the source and what's their evidence? 2) Who benefits if I believe this? 3) What would change my mind? Run it on 5 claims this week.
3. **Audit your feeds.**
   Which sources have earned trust via track record? Which trade in outrage? Prune the manipulators; the information diet shapes the mind.
4. **Practice steelmanning.**
   Weekly: take an opposing view you dislike and state its best case fairly. Discernment requires understanding, not just doubting.
5. **Track predictions.**
   Write down beliefs with confidence levels; revisit quarterly. Calibration — knowing how often you're right — is a trainable skill.
6. **Pre-commit verification.**
   Rule: verify before forwarding to groups. One quick search. The forwarder is responsible for what they spread.
7. **Teach the nudges.**
   Share the checklist with family/team. Discernment scales when it's a shared norm, not a private virtue.
8. **Review mistakes.**
   When you believed wrong: what was the tell you missed? Log it. Each error is training data for better judgment.

## Common pitfalls

- **Cynicism as discernment.**
  Doubting everything equally isn't wisdom — it's laziness. Discernment weighs evidence; cynicism dismisses it.
- **Motivated reasoning.**
  Applying scrutiny only to claims you dislike. The checklist must run on congenial claims too — especially those.
- **Sharing without verifying.**
  Forwarding because 'it might be true and important.' The forwarder owns the spread; verify first.
- **Credential worship.**
  'Expert says' without checking the expert's domain, evidence, or incentives. Credentials inform; they don't settle.
- **Anecdote overweighting.**
  One vivid story beating solid statistics. Vividness is persuasive, not probative — notice when it sways you.
- **Tribe-first truth.**
  Believing because 'our side' says it. The incentive check applies to your own tribe most of all.
- **Never updating.**
  Treating changed minds as weakness. Updating on evidence is the entire point of thinking.
- **Paralysis by analysis.**
  Demanding perfect certainty before acting. Discernment informs decisions; it doesn't replace them. Decide with calibrated confidence.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →