Cloud computing environments generate massive volumes of telemetry data. Rapidly identifying and resolving incidents is critical, as outages can cause substantial financial and operational damage. Artificial Intelligence for IT Operations (AIOps) has become essential for analyzing this data and accelerating incident response. While large language models (LLMs) are already being applied in AIOps, as comprehensively surveyed by Zhang et al. (2025), recent research—the framework proposed by Zota et al. (2025), and the multi-agent architecture by Pradhan (2025)—has begun exploring Agentic AIOps. In these systems, autonomous agents analyze telemetry, diagnose root causes, and recommend or autonomously execute remediation actions. While Agentic AIOps represents a significant advancement in autonomous IT operations, current frameworks primarily emphasize agent architectures, workflows, and orchestration layers. It would therefore be interesting to investigate whether introducing a dedicated skills layer—a set of reusable capabilities for tasks such as querying telemetry, correlating events, and checking resource dependencies, etc.—could further improve root-cause analysis in complex cloud environments.