Does it help with asset modeling?

Absolutely. It covers modeling twin ontologies using industry standards like DTDL and RealEstateCore, as well as custom schema design.

How does it handle state synchronization?

It provides implementation patterns for device-to-twin and twin-to-device pipelines, including consistency models and staleness threshold management.

Which IoT platforms does this skill support?

This skill provides specialized guidance for Azure Digital Twins, AWS IoT TwinMaker, and open-source alternatives like Eclipse Ditto and FIWARE.

Can I use this for predictive maintenance projects?

Yes, it includes patterns for Remaining Useful Life (RUL) prediction approach and ML model selection including Isolation Forest, LSTM, and Weibull.

Digital Twin Engineering

Name: Digital Twin Engineering
Author: rnavarych

byrnavarych

•

Infraestructura en la Nube

Architects and implements sophisticated digital twin systems with real-time synchronization, predictive maintenance, and simulation-based modeling.

This skill provides comprehensive guidance for designing and deploying digital twin architectures across various maturity levels, from basic digital shadows to complex bidirectional simulation twins. It leverages industry-standard ontologies like DTDL and RealEstateCore while offering platform-specific implementation strategies for Azure Digital Twins and AWS IoT TwinMaker. Users can effectively model physical assets, manage state synchronization, perform what-if scenario analysis in sandboxed environments, and integrate machine learning for predictive maintenance and anomaly detection.

Características Principales

01Multi-level digital twin architecture design (Shadow vs. Twin vs. Simulation)

02Ontology modeling with DTDL, RealEstateCore, and custom schemas

0311 GitHub stars

04Sandboxed what-if scenario analysis for risk-free simulation

05Real-time device-to-twin and twin-to-device synchronization pipelines

06Predictive maintenance integration using RUL models and anomaly detection

Casos de Uso

01Implementing predictive maintenance for industrial machinery using ML-driven state analysis

02Designing a large-scale building management system using graph-based twin topologies

03Creating a virtual sandbox to test operational changes before deploying to physical assets

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add rnavarych/alpha-engineer digital-twin

For use in Claude.ai and ChatGPT

Características Principales

01Multi-level digital twin architecture design (Shadow vs. Twin vs. Simulation)

02Ontology modeling with DTDL, RealEstateCore, and custom schemas

0311 GitHub stars

04Sandboxed what-if scenario analysis for risk-free simulation

05Real-time device-to-twin and twin-to-device synchronization pipelines

06Predictive maintenance integration using RUL models and anomaly detection

Casos de Uso

01Implementing predictive maintenance for industrial machinery using ML-driven state analysis

02Designing a large-scale building management system using graph-based twin topologies

03Creating a virtual sandbox to test operational changes before deploying to physical assets