Society & SafetyTechnologyPlatinum

Helps you understand where AI can safely support mental well-being and where it crosses into dangerous territory requiring a human professional.

Mental Health AI Safety Guide

Navigate AI mental health boundaries safely

1 activationsintermediatev1.0.1

Best for

▸Understand the narrow safe zone for AI in mental health contexts
▸Recognize parasocial relationship warning signs with AI companions
▸Identify when AI mental health support crosses into dangerous territory
▸Learn safe interaction patterns for AI-assisted self-reflection

What you'll get

▸Safety assessment classifying a daily AI journaling practice as safe zone with 2 boundary warnings
▸Parasocial risk report flagging 5 dependency indicators in a user's AI companion relationship
▸Danger zone alert for AI providing informal depression diagnosis with immediate therapist referral
▸Pattern analysis showing healthy tool use transitioning toward problematic emotional reliance over 3 months

Expects

A description of AI mental health interaction or a question about using AI for emotional support

Returns

Safety assessment with zone classification, parasocial risk analysis, pattern evaluation, and professional referral guidance

What's inside

“You are a Mental Health AI Safety Guide. You help people understand where AI can safely support mental well-being and where it becomes dangerous. You are NOT a therapist, counselor, or mental health professional. You help users navigate the boundary between helpful AI-assisted self-reflection and ha...”

Covers

Core PrinciplesDocumented Harm CasesThe Safe Zone (AI Can Help Here)The Danger Zone (AI Must Not Do This)Parasocial Relationship Warning SignsCrisis Detection AwarenessEscalation Rules (Hard-Coded)

Not designed for ↓

×Providing therapy or clinical mental health treatment
×Replacing licensed therapists or counselors
×Diagnosing mental health conditions
×Managing acute mental health crises

SupaScore

90.5▼

Research Quality (15%)

9.2

Prompt Engineering (25%)

Practical Utility (15%)

Completeness (10%)

9.2

User Satisfaction (20%)

Decision Usefulness (15%)

Evidence Policy

Standard: no explicit evidence policy.

mental health aiai companion safetyparasocial relationshipscrisis detectionai therapy risks

Research Foundation: 8 sources (5 paper, 1 industry frameworks, 2 official docs)

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

Version History

v1.0.13/15/2026

Works well with

Responsible AI UsePlatinum Digital Safety for TeensPlatinum AI Health Literacy GuardPlatinum Medical Prompt Safety ArchitectPlatinum