Framework for demonstrating AI capabilities in legal contexts. Provides detailed personas across tenant law, business contracts, startup disputes, employment claims, and consumer protection with progressive complexity scenarios. Use when: (1) Demonstrating AI-powered legal triage or intake systems, (2) Showcasing responsible AI-assisted client interactions, (3) Training staff on appropriate AI use in legal contexts, (4) Creating realistic scenarios for legal tech presentations, (5) Developing educational materials about AI in legal services, or (6) Testing AI-powered legal information systems in controlled environments.
npx skills add https://github.com/lawve-ai/awesome-legal-skills --skill legal-simulation-patrick-munro
Realistic simulation framework for demonstrating how AI can assist with legal information needs while respecting professional boundaries and data protection principles. Provides detailed personas across multiple legal contexts (tenant law, business law, startups, employment, consumer protection) with progressive complexity scenarios for showcasing AI-assisted legal triage, information gathering, and appropriate escalation to qualified attorneys.
THIS SKILL IS FOR DEMONSTRATION AND EDUCATIONAL PURPOSES ONLY. IT DOES NOT PROVIDE LEGAL ADVICE.
IMPORTANT - READ CAREFULLY:
Users must:
Neither the skill creator nor Claude/Anthropic:
Data Protection Notice: While this skill demonstrates GDPR-compliant interaction patterns, users collecting actual personal data must implement proper data protection measures under applicable law and consult with qualified privacy/data protection counsel.
Use this skill when you need to:
NOT for: Actual legal consultations, providing legal advice, or replacing qualified legal professionals
Background
Legal Context
Complexity Level: Low
Demonstration Scenarios
AI Value Demonstration: Rapid information access, document template generation, procedure explanation, appropriate attorney referral
Background
Legal Context
Complexity Level: Medium
Demonstration Scenarios
AI Value Demonstration: Contract analysis, damages estimation, negotiation guidance, escalation path mapping
Background
Legal Context
Complexity Level: High
Demonstration Scenarios
AI Value Demonstration: Multi-jurisdictional analysis, stakeholder impact assessment, resolution option comparison, specialist attorney matching
Background
Legal Context
Complexity Level: Medium-High
Demonstration Scenarios
AI Value Demonstration: Compliance gap analysis, risk scoring, documentation review, settlement range estimation, employment law specialist referral
Background
Legal Context
Complexity Level: Entry-Medium
Demonstration Scenarios
AI Value Demonstration: Consumer rights explanation, multi-party liability analysis, regulatory pathway guidance, evidence collection
Enhanced Feature: Persona variation generator - creates modified versions of each persona with different complicating factors (cross-border elements, time limitations, concurrent legal issues, varying jurisdictional frameworks).
Demonstrates responsible data handling in legal contexts:
Initial Intake (Minimal Data Collection)
Data Minimization Demonstration
Transparency and Consent
Security and Confidentiality
Enhanced Feature: GDPR compliance checklist generator - creates data protection impact assessment frameworks for legal service AI implementations, identifying risks and mitigation measures.
Each persona includes 3-5 scenarios that increase in complexity:
Level 1: Information Provision
Level 2: Document Analysis
Level 3: Options Exploration
Level 4: Strategy Frameworks
Level 5: Attorney Matching and Referral
Enhanced Feature: Complexity escalation triggers - automatic detection of when AI simulation should escalate to attorney referral based on factors like monetary value, legal complexity, time sensitivity, or jurisdictional uncertainty.
Presentation/Demo Format
"Let me show you how AI can assist someone facing [legal issue]. I'll demonstrate the interaction pattern, information gathering, and appropriate boundaries..."
Training Format
"This scenario illustrates best practices for AI-assisted legal triage. Notice how the AI [specific behavior]. This demonstrates [key principle]..."
Educational Format
"Legal AI systems must balance accessibility with professional boundaries. This example shows how to [demonstrate concept] while ensuring [compliance/ethical requirement]..."
Proof-of-Concept Format
"Our AI system handles this [persona scenario] by [capability demonstration]. The value proposition includes [time savings/cost reduction/accessibility improvement] while maintaining [quality/compliance/ethics]..."
Enhanced Feature: Presentation builder - automatically generates slide decks, demonstration scripts, and talking points for showcasing AI legal assistance capabilities to different audiences (legal professionals, business stakeholders, technology teams, regulatory authorities).
Demonstrates when and how to transition from AI assistance to human professionals:
Automatic Escalation Triggers
Warning Sign Detection
Attorney Referral Best Practices
Enhanced Feature: Attorney matching criteria generator - creates detailed specialist profiles for different legal issues, including practice area, experience level, jurisdictional licensing, language capabilities, and industry knowledge requirements.
Demonstrates handling of jurisdictional complexity:
Jurisdiction Identification
Jurisdictional Limitations
EU-Specific Considerations
Enhanced Feature: Jurisdictional conflict identifier - detects when legal issue involves multiple jurisdictions and explains choice of law and forum selection considerations.
Shows how AI maintains ethical boundaries in legal contexts:
Unauthorized Practice of Law (UPL) Avoidance
Confidentiality Considerations
Conflict of Interest Awareness
Competence and Diligence
Enhanced Feature: Ethical boundary checker - analyzes AI responses to ensure they don't cross into legal advice, maintain appropriate disclaimers, and clearly distinguish information from recommendations.
10. Invite Questions: Encourage audience engagement and address concerns transparently
Enhanced Feature: Demonstration quality assessment rubric - evaluates whether simulated interactions appropriately balance accessibility with professional boundaries, maintain ethical guardrails, and demonstrate clear value proposition.
This skill does NOT:
Users must:
Professional Responsibility: Legal professionals using this skill for demonstrations must comply with their applicable rules of professional conduct regarding advertising, client communications, unauthorized practice of law, and technology competence requirements.
Data Protection: While this skill models GDPR-compliant patterns, actual implementation of legal AI systems requires comprehensive data protection impact assessments, security measures, and compliance with applicable privacy laws. Consult qualified data protection officers and privacy counsel.
Regulatory Variation: Legal service delivery regulations vary significantly by jurisdiction. Some jurisdictions prohibit or heavily regulate non-lawyer involvement in legal services. Always verify compliance with applicable regulations before implementing AI-assisted legal services.
To adapt personas for specific demonstration needs:
Industry Customization
Jurisdictional Customization
Complexity Customization
Audience Customization
FINAL REMINDER: This skill creates fictional scenarios for demonstration purposes only. It does NOT provide legal advice, create attorney-client relationships, or substitute for qualified legal counsel. All legal matters require consultation with licensed attorneys. Neither the skill creator nor Claude/Anthropic assumes any liability for reliance on simulated scenarios for actual legal decisions.
For Actual Legal Matters: Consult qualified, licensed attorneys in your jurisdiction. Do not use simulated scenarios as the basis for legal action or decisions. Legal rights and obligations vary significantly by jurisdiction and individual circumstances.
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks
Automated scRNA-seq cell type annotation via pre-trained logistic regression. 45+ models: immune, gut, lung, brain, fetal, cancer microenvironments. Input normalized AnnData; outputs per-cell labels, majority-vote cluster labels, confidence scores. Use for fast, reference-backed annotation without manual marker inspection.
Classical ML in Python: classification, regression, clustering, dim reduction, evaluation, tuning, preprocessing pipelines. Linear models, tree ensembles, SVMs, K-Means, PCA, t-SNE. Use PyTorch/TF for deep learning; XGBoost/LightGBM for scale.
Python statistical modeling: regression (OLS, WLS, GLM), discrete (Logit, Poisson, NegBin), time series (ARIMA, SARIMAX, VAR), with rigorous inference, diagnostics, and hypothesis tests. Use scikit-learn for ML; statistical-analysis for test choice.
Take lawve-ai/legal-simulation-patrick-munro from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.