What problem does it solve?
Manually configuring repositories to meet strict team engineering standards is tedious, inconsistent, and prone to human error, especially for data and AI projects with specific tooling and structure requirements. This Skill automates the entire process, ensuring every repo is compliant without manual guesswork.
Core Features & Use Cases
- Automated Compliance Auditing: Scans existing repositories to identify gaps against AI Services / BNE Data Engineering standards, including missing dependencies, incorrect folder structures, and violated data governance policies.
- Adaptive Scaffolding: Generates a fully compliant repository structure with mandatory core components (uv, ruff/mypy, standard folder hierarchy, required boilerplate files) and optional user-selected components (dev containers, Docker, infrastructure-as-code, CI/CD pipelines, Jupyter notebooks, ML model storage, GitHub PR templates).
- Use Case: A data engineer launching a new AWS analytics project can use this Skill to instantly create a repo pre-configured with all required tooling, folder structure, and optional dev container support, passing team audits on the first check.
Quick Start
Use the set-up-env skill to scaffold the current working directory to match the AI Services / BNE Data Engineering team standards, asking me which optional components to include before making any changes.