Guidance for teams whose implementation output is largely AI-generated: process, architecture, review and testing standards.
- What it does
- This skill provides an operating model for engineering teams where AI agents produce most implementation output. It covers process shifts such as planning quality and evaluation coverage, architecture requirements favoring explicit boundaries and typed interfaces, code review focus areas, hiring and evaluation signals, and testing standards for generated code. It produces guidance and checklists rather than files or code.
- When to use it
- Use it when designing processes, reviews or architecture for a team that relies heavily on AI-assisted code generation. It also fits setting review priorities and test standards for generated code, or assessing engineering signals in hiring.
- Requirements
- No tools, packages or credentials are required; it is instructions only and ships no scripts.