← Back to Skills
Society & SafetyTechnologyPlatinum

Evaluate AI relationship advice for safety and bias.

AI Relationship Safety Guide

AI Safety, Relationship Advice, Bias Detection

intermediatev6.0

Best for

  • Recognize validation loops and confirmation bias in AI relationship advice
  • Identify pseudo-diagnoses and partner labeling in AI output
  • Understand when AI replaces rather than supports human connection
  • Evaluate AI-drafted relationship messages for appropriateness

What you'll get

  • Validation loop detection showing AI elaborating accusatory framing without questioning assumptions
  • Pseudo-diagnosis flag for AI labeling a partner as "narcissistic" from a one-sided 3-paragraph description
  • Safe zone assessment confirming AI-drafted apology message as helpful de-escalation support
  • One-sidedness report recommending couples therapy after AI gave a verdict on a trust breach situation
Expects

AI-generated relationship advice, couples communication question, or concern about AI partnership guidance

Returns

Risk assessment with one-sidedness check, validation loop detection, pseudo-diagnosis flags, and therapist referral guidance

What's inside

You are an AI Relationship Safety Guide. You help people critically evaluate AI-generated relationship advice to distinguish genuinely useful applications from structurally harmful ones. - **You treat one-sidedness as structural, not fixable.** Every relationship question reaches AI filtered through...

Covers

What You Do DifferentlyMethodologyWatch For
Not designed for ↓
  • ×Providing relationship advice or couples counseling
  • ×Replacing licensed therapists or counselors
  • ×Diagnosing partners with personality disorders
  • ×Making separation or divorce decisions

SupaScore

89.4
Research Quality (15%)
9.2
Prompt Engineering (25%)
9
Practical Utility (15%)
8.8
Completeness (10%)
8.8
User Satisfaction (20%)
8.8
Decision Usefulness (15%)
9

Evidence Policy

Standard: no explicit evidence policy.

relationship ai safetycouples advice aipartnership ai risksvalidation loopparasocial relationship

Research Foundation: 8 sources (7 paper, 1 industry frameworks)

This skill was developed through independent research and synthesis. SupaSkills is not affiliated with or endorsed by any cited author or organisation.

Version History

v6.06/12/2026

v6.0 wave-1 repair: re-distilled from masterfile/v2 (truncation incident 2026-06, delta-first rules)

v5.03/25/2026

v5.5 final distill

v1.0.13/15/2026

Works well with

© 2026 Kill The Dragon GmbH. This skill and its system prompt are protected by copyright. Unauthorised redistribution is prohibited. Terms of Service · Legal Notice