ai-first-engineering

SKILL.md

Engineering operating model for teams shipping code with AI-assisted generation.

Emphasizes planning quality, evaluation coverage, and behavior-focused code review over traditional syntax checking and typing speed

Requires agent-friendly architectures with explicit boundaries, stable contracts, typed interfaces, and deterministic tests to minimize implicit behavior

Shifts review priorities to behavior regressions, security assumptions, data integrity, failure handling, and rollout safety

Raises testing standards for generated code with required regression coverage, explicit edge-case assertions, and integration checks across interface boundaries

Identifies key hiring signals: clean decomposition of ambiguous work, measurable acceptance criteria, high-signal prompts and evals, and risk control enforcement under delivery pressure

AI-First Engineering

Use this skill when designing process, reviews, and architecture for teams shipping with AI-assisted code generation.

Process Shifts

Planning quality matters more than typing speed.

Eval coverage matters more than anecdotal confidence.

Review focus shifts from syntax to system behavior.

Architecture Requirements

Prefer architectures that are agent-friendly:

explicit boundaries

stable contracts

typed interfaces

deterministic tests

Avoid implicit behavior spread across hidden conventions.