← Back to Skills
Society & SafetyTechnologyPlatinum

Helps you recognize why LLMs are structurally incapable of reliable legal advice and how to spot fabricated cases and citations.

AI Legal Self-Help Guard

Understand why AI legal advice fails

intermediatev5.0

Best for

  • Understand why real legal advice is structurally impossible for LLMs
  • Detect fabricated case citations in AI-generated legal content
  • Evaluate AI contract drafts and legal research for reliability
  • Know when to consult a licensed attorney instead of trusting AI

What you'll get

  • Citation verification report flagging 4 of 6 AI-generated case references as likely fabricated
  • Structural analysis showing why an AI employment law response requires interpretive judgment AI cannot provide
  • Contract draft review identifying 3 liability clauses that need attorney review before signing
  • Jurisdiction warning on AI mixing US common law concepts in a German Handelsrecht context
Expects

AI-generated legal content, contract draft, or a legal question the user wants to ask AI

Returns

Risk assessment with citation verification flags, structural impossibility analysis, jurisdiction warnings, and attorney referral recommendation

What's inside

You are a Legal Self-Help Guard. You help people recognize why LLMs cannot reliably provide legal advice and when they must consult a licensed attorney. - You identify structural impossibilities: LLMs perform probabilistic text completion but legal reasoning requires subsumption (applying abstract r...

Covers

What You Do DifferentlyMethodologyWatch For
Not designed for ↓
  • ×Providing legal advice or case assessment
  • ×Replacing licensed attorneys
  • ×Drafting contracts with liability implications
  • ×Interpreting statutes or predicting case outcomes

SupaScore

89
Research Quality (15%)
9.4
Prompt Engineering (25%)
8.8
Practical Utility (15%)
8.8
Completeness (10%)
9
User Satisfaction (20%)
8.6
Decision Usefulness (15%)
9

Evidence Policy

Standard: no explicit evidence policy.

ai legal riskslegal hallucinationcontract aiunauthorized practicecitation fabrication

Research Foundation: 8 sources (5 paper, 3 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

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