agentic-engineering

原文涵盖的主题

• Agentic Engineering
• Operating Principles
• Eval-First Loop
• Task Decomposition
• Model Routing
• Session Strategy
• Review Focus for AI-Generated Code
• Interpret Tool Results Before Comparing Data

Use this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls. 1. Define completion criteria before execution. 2. Decompose work into agent-sized units. 3. Route model tiers by task complexity. 4. Measure with evals and regression checks. 1. Define capability eval and regression eval. 2. Run baseline and capture failure signatures. 3. Execute implementation. 4. Re-run evals and compare deltas. Apply the 15-minute unit rule: each unit should be independently verifiable each unit should have a single dominant risk each unit should expose a clear done condition Haiku: classification, boilerplate transforms, narrow edits Sonnet: implementation and refactors Opus: architecture, root-cause analysis, multi-file invariants Continue session for closely-coupled units. Start fresh session after major phase transitions. Compact after milestone completion, not during active debugging. Prioritize: invariants and edge cases error boundaries security and auth assumptions hidden coupling and rollout risk Do not waste review cycles on style-only disagreements when automated format/lint already enforce style. For document reads

这里只展示节选，请以完整原文和当前要求为准。