engineering-skills

You can integrate pre-built engineering skills by downloading the specific packages you need and using the included SKILL.md files, reference guides, and scripts to apply 30+ Python tools directly to your workflow. Each skill is ready for immediate integration.

Yes, these engineering skills support environments using FastAPI, TensorFlow, and PyTorch. They require Python 3.8+ and include dependencies like numpy, pandas, scikit-learn, spacy, and opencv-python for comprehensive AI/ML and data science work.

The best way to standardize project setup and code reviews is using pre-built, senior-level skills that offer step-by-step workflows and best practices, ensuring consistent quality and efficiency across your entire tech stack.

Yes, you need Python 3.8+ to run the data science and ML scaffolding scripts. The tools rely on standard libraries alongside specific dependencies like scikit-learn, PyTorch, and TensorFlow for analysis and automation.

System design patterns and best practices help scale engineering teams by providing production-ready skills and standardized workflows for common tasks like security audits, ensuring consistent quality and efficiency across projects.

These 30+ stdlib-only Python tools are designed for analysis and scaffolding, but large-scale architecture analysis may require integrating additional external libraries like numpy and pandas to handle complex data processing limits.