Ai First Engineering

If you're running a team where Claude or other AI agents are generating significant chunks of your implementation, this codifies the operating model shift you need to make. It's opinionated about what matters now: planning quality over typing speed, eval coverage over vibes, architecture with explicit boundaries instead of implicit conventions. The review and hiring sections are especially practical, focusing on behavior regressions and decomposition skills rather than style nitpicking. Honestly feels like someone wrote down what they learned the hard way after six months of high-velocity AI-assisted shipping. Worth reading even if you cherry-pick which parts to adopt.

Install to Claude Code

npx -y skills add affaan-m/everything-claude-code --skill ai-first-engineering --agent claude-code