agentic-engineering

AI-driven engineering workflows with eval-first execution, task decomposition, and cost-aware model routing. Use this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls. Apply the 15-minute unit rule: Prioritize: Do not waste review cycles on style-only disagreements when automated format/lint already enforce style. Track per task: Escalate model tier only when lower tier fails with a clear reasoning gap. - Defines an eval-first loop: establish baseline evals before implementation, then re-run post-execution to measure deltas and catch regressions - Decomposes work into 15-minute units with single dominant risks, independent verifiability, and clear done conditions - Routes tasks by complexity: Haiku for classification and boilerplate, Sonnet for implementation, Opus for architecture and multi-file invariants - Emphasizes review focus on invariants, edge cases, error boundaries, and security rather than style enforcement - Tracks cost discipline per task including model tier, token estimates, retries, and wall-clock time to guide escalation decisions - Define completion criteria before execution. - Decompose work into agent-sized units. - Route model tiers by task complexity. - Measure with evals and regression checks.