agentleFS
mark64oswaldmark64oswald/healthsim-workspace/skills/common/SKILL.md

common

Skill9 starsChanged 16 days agoApache-2.0View on GitHub

Cross-product infrastructure for HealthSim — persistence (cohort save/load), identity correlation (SSN-based cross-product linking), and DuckDB database operations. Use when saving/loading cohorts, linking entities across products, or querying the database directly.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. NVIDIA/TensorRT-Model-Optimizer★ 5.6ksame name
    2. NVIDIA/Model-Optimizer★ 5.6ksame name
    3. ianshank/Agents★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository11 other files it gives its agents.

The file

Files
SKILL.md

Common Skills - Master Reference

Cross-product infrastructure skills that enable persistence, identity correlation, and database operations across all HealthSim products.

Quick Start

# Save your current work
Save this cohort as "demo-patients"

# Load previous work
Load the cohort named "demo-patients"

# Find related entities
Find the member record for patient MRN-12345

# Query the database
Show me all cohorts created in the last week

Core Capabilities

State Management

Persist generated data across sessions with cohort save/load operations. Supports auto-persist for token-efficient batch generation.

Triggers: save, load, persist, resume, snapshot, restore Details: state-management.md

Identity Correlation

Link entities across products using SSN as the universal correlator. Track the same person as patient, member, rx member, and trial subject.

Triggers: find member, link patient, correlate, same person, cross-reference Details: identity-correlation.md

DuckDB Operations

Direct database access for advanced queries, schema exploration, and reference data access.

Triggers: query, SQL, schema, database, show tables Details: duckdb-skill.md

Cross-Product Architecture

Common skills enable data flow between products:

┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│  PatientSim │    │  MemberSim  │    │ RxMemberSim │
│   (MRN)     │    │   (MBI)     │    │  (RxID)     │
└──────┬──────┘    └──────┬──────┘    └──────┬──────┘
       │                  │                  │
       └────────┬─────────┴─────────┬────────┘
                │                   │
         ┌──────▼───────┐   ┌───────▼──────┐
         │  Identity    │   │    State     │
         │ Correlation  │   │  Management  │
         │   (SSN)      │   │  (Cohorts)   │
         └──────────────┘   └──────────────┘
                │                   │
                └─────────┬─────────┘
                          │
                   ┌──────▼──────┐
                   │   DuckDB    │
                   │  Database   │
                   └─────────────┘

Database Schema

Common skills work with these core tables:

TablePurposeKey Columns
cohortsSaved cohort metadatacohort_id, name, created_at
personsCore person identityperson_id, ssn, demographics
patientsPatientSim entitiespatient_id, mrn, person_id
membersMemberSim entitiesmember_id, mbi, person_id
rx_membersRxMemberSim entitiesrx_member_id, rx_id, person_id

Related Skills

  • Generation Skills - Profile and journey building
  • PopulationSim - Reference data and population targeting
  • NetworkSim - Provider network modeling

Part of HealthSim Workspace Infrastructure

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.