MentoLoop Clinical Platform Development

Development skill for the MentoLoop clinical education platform, providing architectural context and development guidelines for healthcare education workflows.

What This Skill Does

This skill provides comprehensive context and development guidelines for working on the MentoLoop platform, a HIPAA-compliant clinical education system that matches students with preceptors using AI-powered algorithms. It helps you understand the codebase structure, maintain compliance requirements, and follow platform-specific development patterns.

Instructions

When working on MentoLoop platform tasks:

1. **Read Context Files First**

- Always check `.cursor/rules` directory for relevant markdown documentation

- Reference the exact file you consulted in your response

- Use the provided file paths to locate specific components

2. **Follow Development Principles**

- Only modify code directly relevant to the specific request

- Never use placeholders like `# ... rest of the processing ...` - always include complete code

- Break problems into smaller steps and think through each separately

- Always provide a complete PLAN with REASONING based on evidence from code and logs before making changes

- Explain OBSERVATIONS clearly, then provide REASONING to identify issues

- Add console logs when needed to gather more information

3. **Understand Core Components** (by importance)

**MentorFit Matching Engine** (Importance: 95)

- Location: `mentoloop-gpt5-template/gpt5-convex-actions.ts`

- AI-powered matching for student-preceptor pairing

- 10-factor weighted compatibility scoring (learning style, feedback preferences, autonomy)

- Tiered match classifications (Gold/Silver/Bronze)

- Clinical specialty alignment validation

**HIPAA Compliance Layer** (Importance: 90)

- Location: `lib/middleware/security-middleware.ts`

- PHI access tracking and audit logging

- Clinical data redaction system

- Healthcare-specific data validation

- Compliance reporting framework

**Clinical Hours Management** (Importance: 90)

- Location: `lib/supabase/services/clinicalHours.ts`

- FIFO-based hour credit tracking

- Specialty-specific hour requirement validation

- Automated progression checkpoints

- Rotation period management

**Healthcare Payment Processing** (Importance: 85)

- Location: `lib/supabase/services/payments.ts`

- Clinical rotation payment workflows

- Tiered pricing model (Core/Pro/Premium)

- Revenue sharing calculations for preceptors

- Institution billing integration

**Student Intake Workflow** (Importance: 85)

- Location: `app/student-intake/page.tsx`

- Clinical rotation requirements collection

- Program verification with institutions

- Learning style assessment

- Rotation scheduling preferences

**Preceptor Management** (Importance: 80)

- Location: `app/preceptor-intake/page.tsx`

- Medical credential verification

- Clinical specialty validation

- Teaching style assessment

- Availability management

4. **Domain-Specific Features to Consider**

- HIPAA-compliant messaging system

- Clinical documentation templates

- Rotation hour banking system

- Automated clinical milestone tracking

- Institution compliance reporting

- Medical credential verification workflows

5. **Security and Compliance Requirements**

- All PHI (Protected Health Information) must go through compliance layer

- Audit logging required for all clinical data access

- Data redaction must be applied where appropriate

- Healthcare-specific validation rules must be followed

6. **When Making Changes**

- Verify HIPAA compliance implications

- Check impact on clinical hours tracking if modifying student/preceptor workflows

- Ensure payment calculations remain accurate if touching financial code

- Test matching algorithm changes against known good/silver/bronze scenarios

- Validate credential verification workflows still function

Usage Example

When asked to "add a new field to track preceptor availability":

1. Read relevant context from `.cursor/rules`

2. Identify affected components: `app/preceptor-intake/page.tsx`, potentially matching engine

3. Plan changes with reasoning about impact on matching algorithm

4. Implement complete code (no placeholders)

5. Verify HIPAA compliance for new data field

6. Test matching engine still produces valid results

7. Respond with context attribution

Important Notes

*Context improved by Giga AI - using Main Overview, Core Business Components (MentorFit Matching Engine, Clinical Hours Management, Healthcare Payment Processing, HIPAA Compliance Layer), Integration Points (Student Intake Workflow, Preceptor Management), and Development Guidelines*