Simulate FSM-based airport weather states and generate METAR/TAF outputs.
npx skills add https://github.com/Jupiter41/arthur-airport --skill weather-service
Please help me install this Agent Skill. Skill: weather-service Source: https://github.com/Jupiter41/arthur-airport/tree/main/services/weather-service Command: npx skills add https://github.com/Jupiter41/arthur-airport --skill weather-service
The weather-service skill provides a complete end-to-end simulation of airport weather and its impact on operations, integrating a four-state FSM, METAR/TAF generation, and runway-capacity calculations to illustrate how weather affects throughput and safety.
Start the weather-service skill and run the simulation to observe FSM-driven weather states, METAR/TAF generation, and runway capacity impacts.
High-intent search queries and answers about installing and using this skill.
Runway capacity is calculated by deriving operational impacts directly from current FSM weather states and generated METAR/TAF data. This maps weather conditions like IMC or LIFR to specific throughput reductions, demonstrating how weather affects airport safety and capacity.
FSM weather transitions move between CAVOK, VMC, IMC, and LIFR states using realistic probabilities to generate METAR and TAF outputs. This mechanism provides a structured way to model evolving weather conditions for airport operations.
Yes, you can use historical METAR CSV replay or live METAR feeds as flexible data sources for the weather simulation. These options allow you to demonstrate airport operations under different conditions using simulated, historical, or live data.
Yes, the airport weather simulation demonstrates integration patterns for Neo4j persistence and Kafka messaging. These modular integrations handle data storage and event streaming, alongside observability components, within a modular architecture.
Model end-to-end airport weather effects by combining FSM state transitions, METAR/TAF generation, and runway capacity calculations within a modular microservices architecture. This approach illustrates weather impacts on throughput and safety across varied scenarios.
TeoSlayerTrack live aircraft positions and aviation weather via Pilot Protocol.
Jupiter41Coordinate flight lifecycle state transitions with Neo4j persistence and Kafka messaging.
danielmiesslerStream PAI multi-agent activity to a WebSocket-enabled dashboard.
rustykuntzFetch METAR, TAF, and PIREP aviation weather data from aviationweather.gov.
