ReddRadar
Agent skill
Generative Framework
Conversation-driven specification and execution of healthcare data generation at scale
Install this agent skill to your Project
npx add-skill https://github.com/mark64oswald/healthsim-workspace/tree/main/skills/generation
SKILL.md
Generative Framework Skills
Use these skills when building specifications for data generation or executing batch generation.
Quick Reference
| Skill | Use When | Location |
|---|---|---|
| Profile Builder | Defining population characteristics for batch generation | builders/profile-builder.md |
| Journey Builder | Defining temporal event sequences | builders/journey-builder.md |
| Quick Generate | Simple single-entity generation | builders/quick-generate.md |
| Profile Executor | Executing a profile specification | executors/profile-executor.md |
| Journey Executor | Executing a journey specification | executors/journey-executor.md |
| Cross-Domain Sync | Coordinating cross-product generation | executors/cross-domain-sync.md |
Trigger Phrases
Building Specifications
- "Build a profile for 100 Medicare members"
- "Create a journey for diabetic patients"
- "Specify a commercial cohort with CHF"
- "Define a surgical episode journey"
Executing Specifications
- "Generate patients from this profile"
- "Execute the diabetic journey for 50 patients"
- "Run batch generation for this cohort"
Using Templates
- "Use the Medicare diabetic template"
- "Start with the surgical episode journey"
- "Generate using the commercial healthy profile"
Workflow Overview
1. Build a Profile (Optional)
Build a profile for 200 Medicare Advantage members:
- Age 65-85, normal distribution centered at 74
- 40% with Type 2 diabetes
- 30% with heart failure
- San Diego County geography
2. Build a Journey (Optional)
Create a first-year diabetic journey:
- Initial diagnosis visit with labs
- Metformin prescription
- Quarterly follow-ups with A1c
- Possible titration to second agent
3. Execute Generation
Generate the cohort using this profile and journey
Save as cohort "ma-diabetic-cohort-2025"
Distribution Types
| Type | Use Case | Example |
|---|---|---|
categorical |
Discrete choices | Gender: M/F/Other |
normal |
Bell curve | Age centered at 72 |
log_normal |
Skewed positive | Healthcare costs |
uniform |
Equal probability | Random day in range |
explicit |
Specific values | Exactly these NDCs |
See distributions/distribution-types.md for details.
Journey Patterns
| Pattern | Use Case | Example |
|---|---|---|
linear |
Simple sequence | Office visit → Lab → Follow-up |
branching |
Decision points | ER → Admit OR Discharge |
protocol |
Trial schedules | Cycle 1 Day 1, Day 8, Day 15 |
lifecycle |
Long-term patterns | New member first year |
See the journeys/ folder for pattern details.
Integration with Products
The Generative Framework orchestrates all HealthSim products:
| When Generating | Products Involved | Cross-Domain Triggers |
|---|---|---|
| Patient cohort | PatientSim, NetworkSim | Provider assignment |
| Member claims | MemberSim, PatientSim, NetworkSim | Encounter → Claim |
| Pharmacy fills | RxMemberSim, PatientSim, NetworkSim | Rx → Fill, DUR check |
| Trial subjects | TrialSim, PatientSim, NetworkSim | Subject ↔ Patient linking |
Templates
Pre-built profiles and journeys for common use cases:
Profile Templates
- medicare-diabetic.md - Medicare T2DM cohort
- commercial-healthy.md - Commercial healthy adults
- medicaid-pediatric.md - Medicaid children
Journey Templates
- diabetic-first-year.md - New T2DM diagnosis year 1
- surgical-episode.md - Elective surgery episode
- new-member-onboarding.md - New member first 90 days
Related Skills
- State Management - Save/load generated cohorts
- Identity Correlation - Cross-product entity linking
- PopulationSim - Real-world demographic data
- NetworkSim - Real provider assignments
Implementation Status: Foundation phase. See GENERATIVE-FRAMEWORK-PROGRESS.md for details.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
mark64oswald/healthsim-workspace
healthsim-rxmembersim
RxMemberSim generates realistic synthetic pharmacy data for testing PBM systems, claims adjudication, and drug utilization review. Use when user requests: (1) pharmacy claims or prescription data, (2) DUR alerts or drug interactions, (3) formulary or tier cohorts, (4) pharmacy prior authorization, (5) NCPDP formatted output.
mark64oswald/healthsim-workspace
healthsim-patientsim
Generate realistic clinical patient data including demographics, encounters, diagnoses, medications, labs, and vitals. Use when user requests: (1) patient records or clinical data, (2) EMR test data, (3) specific clinical cohorts like diabetes or heart failure, (4) HL7v2 or FHIR patient resources.
mark64oswald/healthsim-workspace
healthsim-trialsim
Generate realistic clinical trial synthetic data including study definitions, sites, subjects, visits, adverse events, efficacy assessments, and disposition. Use when user requests: clinical trial data, CDISC/SDTM/ADaM datasets, trial cohorts (Phase I/II/III/IV), FDA submission test data, or specific therapeutic areas like oncology or biologics/CGT.
mark64oswald/healthsim-workspace
healthsim-membersim
MemberSim generates realistic synthetic claims and payer data for testing claims processing systems, payment integrity, and benefits administration.
mark64oswald/healthsim-workspace
healthsim-networksim
NetworkSim provides provider network intelligence using real NPPES data (8.9M providers). Use this skill for ANY request involving: (1) provider search by specialty or location, (2) facility search (hospitals, nursing homes, clinics), (3) NPI validation, (4) network adequacy assessment against CMS/NCQA standards, (5) healthcare desert identification, (6) provider density analysis, (7) network roster generation, (8) hospital or physician quality metrics, (9) cross-product provider assignment, (10) pharmacy network analysis.
mark64oswald/healthsim-workspace
healthsim-populationsim
PopulationSim provides population-level intelligence using public data sources. Use this skill for ANY request involving: (1) population demographics or profiles, (2) geographic health patterns or disparities, (3) social determinants of health (SDOH), (4) SVI or ADI analysis, (5) cohort definition or specification, (6) clinical trial feasibility, site selection, or enrollment projection, (7) service area analysis, (8) health equity assessment, (9) census data or ACS variables, (10) CDC PLACES health indicators.
Didn't find tool you were looking for?