Epigrass Creator

Create Epigrass epidemiological models through step-by-step guided specification. Build metapopulation models (SIR, SEIR, SEIS, SIS, SI) with geographic netw...

Security Scan

The skill's code, docs, and runtime instructions are consistent with an interactive Epigrass model-wizard that imports GeoPackage files and does not request unrelated credentials or network endpoints.

Purpose & Capability

The skill's name/description (Epigrass model creator with GeoPackage support) align with the included Python wizard code that imports geopandas/fiona and reads .gpkg files. No unrelated binaries, credentials, or config paths are requested.

Instruction Scope

SKILL.md and README describe step-by-step interactive prompts and instruct users to install geopandas or fiona for GeoPackage support. The instructions do not ask the agent to read or transmit unrelated system files or secrets. Minor documentation inconsistency: some text implies 'auto-fetch' of city data while the code either uses placeholder coordinates or requires user mapping/entry (the CHANGELOG mentions this was intentionally changed). This is a documentation/code mismatch but not a security issue.

Install Mechanism

No install spec is provided (instruction-only/packaged code), so nothing is automatically downloaded during install. The runtime may require pip-installing geopandas or fiona per the docs; those are standard Python packages (geopandas is heavy but legitimate).

Credentials

The skill declares no required environment variables or credentials. The code does not attempt to access or exfiltrate environment secrets or remote APIs. Dependency on geopandas/fiona is appropriate for GeoPackage parsing.

Persistence & Privilege

always:false and user-invocable are set. The skill does not request permanent platform presence or modify other skills or system-wide settings. Autonomous invocation is allowed by default but not combined with other concerning privileges.

Assessment

This skill appears to do what it says: an interactive wizard to build Epigrass metapopulation models and import GeoPackage files. Before using it: (1) Confirm you want to give the wizard access to any local GeoPackage files — those files may contain sensitive location/population data. (2) Install geopandas or fiona in a controlled environment; geopandas has many binary dependencies and can be heavy. (3) Note the minor docs/code mismatch about 'auto-fetch' city data — the wizard may use placeholder coordinates or require manual mapping rather than fetching remote datasets. (4) It does not request credentials or network endpoints, so no secret exposure is required to use core features. If you plan to import very large GeoPackages, test on a subset first to check performance and memory usage.

Epigrass Creator Skill

Create epidemiological metapopulation models using Epigrass through an interactive, step-by-step wizard.

What is Epigrass?

Epigrass (Epidemiological Geo-referenced Analysis and Simulation System) is a Python library for simulating disease spread across geographic networks.

Supported Models

Model	Compartments	Use Case
SIR	S, I, R	Diseases with lifelong immunity
SEIR	S, E, I, R	Diseases with latent period
SEIS	S, E, I	Diseases with temporary immunity
SIS	S, I	Diseases with no immunity
SI	S, I	Fatal diseases
Custom	User-defined	Specialized scenarios

Workflow (5 Steps)

1. Model Selection - Choose model type
2. Site Definition - Define geographic locations (manual, grid, cities, or GeoPackage import)
3. Parameters - Configure epidemiological parameters
4. Network - Define connections between sites
5. Simulation - Set simulation settings and generate files

GeoPackage Support

Import sites directly from GeoPackage (.gpkg) files:

• Supports any geospatial vector data
• Automatic coordinate extraction
• Column mapping for name, population, geocode
• Works with municipal boundaries, health regions, etc.

Requirements: pip install geopandas (or fiona as fallback)

Usage Examples

User: Create a dengue model for Brazilian cities
→ Wizard guides through SEIR selection, city list, parameters

User: Build SIR model with 10x10 grid
→ Wizard creates synthetic network

User: Custom model with hospitalization
→ Wizard collects compartments and transitions

Output

• model.epg - Epigrass script
• sites.csv - Site/node data
• edges.csv - Edge/connection data
• model_spec.json - Full specification

Requirements

• Python 3.8+
• epigrass (pip install epigrass)