agent-harness-skill

Design, diagnose, and improve a universal agent harness around actual usage context and task logic, decide whether an additional control layer is needed, and produce a minimum necessary structure or minimum correction with validation. Use when designing or reviewing agent architecture, analyzing long-running failures, deciding whether an issue belongs to the harness layer, or when user mentions harness, orchestration, state management, checkpoint, recovery, evaluation, human handoff, or observability.

用于围绕项目实际使用场景和任务逻辑设计、诊断和改造通用智能体运行框架，判断是否需要额外控制层，并给出最小必要结构或最小修正与验证方案。 当用户需要设计或评审智能体架构、分析长任务失败、判断问题是否属于运行框架层，或提到“harness”“运行框架”“编排”“状态管理”“检查点”“恢复”“评估”“人工接管”“可观测性”时使用。