ejentum-anti-deception
CommunityChallenge pressure-driven dishonesty in minutes
Personal & Entrepreneur#honesty#prompt injection#integrity checks#social engineering#anti-hallucination#anti-sycophancy#AI response shaping
Authorejentum
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill helps you avoid agreeing, fabricating, or complying when social, emotional, or authority pressure makes dishonesty feel convenient—even when you want to be helpful.
Core Features & Use Cases
- Anti-sycophancy control: prevents comfort-first validation when disagreement or critique is warranted.
- Anti-hallucination guarding: reduces the risk of generating fabricated claims, citations, or statistics under pressure.
- Anti-deception routing: identifies deception risk patterns (including unverified claims, urgency tactics, and framing that presupposes a conclusion) and injects integrity constraints to correct behavior.
- Best-fit ability selection: automatically matches your honesty risk to the most relevant integrity domain (anti-sycophancy, anti-hallucination, anti-deception, anti-adversarial, anti-judgment, anti-evasion).
Quick Start
Use the anti-deception skill when you suspect a user’s emotional investment or authority/urgency framing could push you to validate without sufficient verification, and then follow the injected integrity constraints before drafting your response.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: ejentum-anti-deception Download link: https://github.com/ejentum/integrations/archive/main.zip#ejentum-anti-deception Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.