用 Strands Evals 与 Amazon Bedrock AgentCore 评估技能型智能体
原标题：Evaluate skill-equipped agents with Strands Evals and Amazon Bedrock AgentCore
AI 摘要
AWS Machine Learning Blog 介绍了如何用 Strands Evals SDK 和 Amazon Bedrock AgentCore Evaluations 评估具备技能（Skill）的智能体。技能是遵循开放 Agent Skills 标准的模块化指令集，可让智能体按需加载领域流程。文章指出技能组合会带来两类通用指标难以发现的失败：选错技能、以及选对技能但未完整遵循其指令，因此新增 Skill Selection Accuracy、Skill Instruction Following 和确定性的 Skill Invoked 三个评估器，并说明如何从轨迹和 OpenTelemetry 追踪中解读逐技能结果以选择修复方向。
正文节选
Evaluate skill-equipped agents with Strands Evals and Amazon Bedrock AgentCore General-purpose agents handle a broad range of tasks, but you still need them to follow the procedures that run your business: compliance checks, document-processing workflows, escalation policies, engineering conventions. Encoding all of that in one system prompt or in application logic gets hard to maintain and update. Skills are a modular alternative. A skill is a reusable set of instructions, usually stored in a S