geo-infer-risk

Geospatial risk modeling including catastrophe models, exposure analysis, and underwriting. Use when assessing spatial risk, building catastrophe models, analyzing exposure/hazard/vulnerability, or computing portfolio risk metrics.

Best use case

geo-infer-risk is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Geospatial risk modeling including catastrophe models, exposure analysis, and underwriting. Use when assessing spatial risk, building catastrophe models, analyzing exposure/hazard/vulnerability, or computing portfolio risk metrics.

Teams using geo-infer-risk should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/GEO-INFER-RISK/SKILL.md --create-dirs "https://raw.githubusercontent.com/ActiveInferenceInstitute/GEO-INFER/main/GEO-INFER-RISK/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/GEO-INFER-RISK/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How geo-infer-risk Compares

Feature / Agentgeo-infer-riskStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Geospatial risk modeling including catastrophe models, exposure analysis, and underwriting. Use when assessing spatial risk, building catastrophe models, analyzing exposure/hazard/vulnerability, or computing portfolio risk metrics.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# GEO-INFER-RISK

## Instructions

### Core Capabilities

- **Catastrophe models**: Cholesky-decomposition spatial correlation
- **Risk engine**: Moran's I, Geary C, Monte Carlo loss calculation
- **Exposure modeling**: Multi-source data loading (DB, file, stream, API)
- **Hazard modeling**: Spatial hazard assessment and mapping
- **Vulnerability**: Bayesian uncertainty quantification
- **Underwriting**: Rule-based fraud detection, env var API keys

### Key Imports

```python
from geo_infer_risk.core.risk_engine import RiskEngine
from geo_infer_risk.core.catastrophe_models import CatastropheModel
from geo_infer_risk.core.exposure_model import ExposureModel
from geo_infer_risk.core.hazard_model import HazardModel
```

## Examples

```python
from geo_infer_risk.core.risk_engine import RiskEngine

engine = RiskEngine()
result = engine.assess(
    hazard_raster=flood_depth,
    exposure_data=building_footprints,
    vulnerability_curve="residential_flood"
)
print(f"Expected loss: ${result.expected_loss:,.0f}")
print(f"Loss exceedance (100yr): ${result.loss_at_return_period(100):,.0f}")
```

```python
from geo_infer_risk.core.catastrophe_models import CatastropheModel

cat_model = CatastropheModel(peril="earthquake", region="pacific_ring")
simulations = cat_model.run_monte_carlo(n_simulations=10_000)
print(f"Mean annual loss: ${simulations.mean_annual_loss:,.0f}")
print(f"99th percentile: ${simulations.percentile(99):,.0f}")
```

## Guidelines

- All 18 former placeholder references verified clean (0 remaining)
- Spatial correlation uses Cholesky decomposition
- Risk aggregation uses real Moran's I and Monte Carlo
- Test: `uv run python -m pytest GEO-INFER-RISK/tests/ -v`

### Integrations

- **BAYES** → Bayesian uncertainty quantification
- **ECON** → Economic loss and insurance modeling
- **CLIMATE** → Climate-driven hazard projections
- **SPACE** → Spatial correlation of hazards
- **AG** → Crop loss risk assessment

Related Skills

We are still matching the closest adjacent skills for this page. In the meantime, continue through the full directory.