I'm practicing around 5/6, I've found that adding "skills" and mcp can sometimes negatively impact the process as much as help, so I've been somewhat constrained on overdoing it. As for 6, mostly just setup guardrails on repeat testing instructions and how to run/test/retest certain things... also to not just update tests when broken, but confirm the designed behavior.

Moving past that, I'm not sure that I really trust it... I feel that manual review of product behavior and code matters a lot. AI agents often make similar mistakes to real people in leaking abstractions or subtle mistakes with security... So I do review almost everything, at least at the level where a feature PR makes sense. Though an AI pass at that can help too.