Drives AI agent work using evaluation-first execution, task decomposition, and cost-aware model routing. Improves quality and cost discipline on AI-generated code.
How this skill is triggered — by the user, by Claude, or both
Slash command
/everything-claude-code:agentic-engineeringThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
在 AI 智能体执行大多数实施工作且人类强制执行质量和风险控制的工作流中使用此技能。
在 AI 智能体执行大多数实施工作且人类强制执行质量和风险控制的工作流中使用此技能。
应用 15 分钟单元规则:
优先考虑:
当自动格式/lint 已强制执行样式时,不要在仅样式分歧上浪费审查周期。
每项任务跟踪:
仅当较低层以明确的推理差距失败时才升级模型层。
npx claudepluginhub aaione/everything-claude-code-zhGuides eval-first execution, task decomposition, and cost-aware model routing for AI agent engineering workflows.
Guides agentic engineering workflows: eval-first loops, 15-min task decomposition, model routing (Haiku/Sonnet/Opus), AI code reviews, and cost tracking.
Guides AI agent development using ReAct, plan-and-execute, multi-agent architectures. Designs tools, memory systems, guardrails; orchestrates with LangChain, LlamaIndex, CrewAI, AutoGen.