Find installable agent skills for Azure and Microsoft cloud tasks. The skill searches a catalog, checks candidate descriptions, identifies the plugin containing each match, and provides installation guidance for the agent client in use.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Searches the Azure skills catalog and recommends installable agent skills by matching an Azure task to skill metadata and plugin installation guidance. WHEN: before starting any task that involves an Azure or Microsoft-cloud service, product, or data source, when no currently loaded skill or tool already covers it.
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Follow these steps to discover the available azure skill matching the given task description.
List Azure plugin directories from the GitHub Contents API: https://api.github.com/repos/microsoft/azure-skills/contents/.github/plugins?ref=main
In the result, each entry whose type is dir is a plugin directory. Skills are organized by plugins.
For each plugin, list their skills from the GitHub Contents API: https://api.github.com/repos/microsoft/azure-skills/contents/.github/plugins/{plugin-dirname}/skills?ref=main
In the result, each entry whose type is dir is a skill directory. Each skill has a SKILL.md file that explains what this skill should be used for.
Eliminate the skills that obviously aren't relevant by their names. Then for each remaining skill, read their description from the API: https://raw.githubusercontent.com/microsoft/azure-skills/main/.github/plugins/{plugin-dirname}/skills/{skill-name}/SKILL.md
Use the descriptions to further eliminate skills that aren't relevant.
For each relevant skill, discover their plugin name by reading the plugin.json from the GitHub Contents API: https://raw.githubusercontent.com/microsoft/azure-skills/main/.github/plugins/{plugin-dirname}/.plugin/plugin.json
This is important because a plugin's name may be different from its directory name. The installation commands depend on the plugin's name.
Report the matched skills and offer instructions to install them. Skills can be installed by installing their plugin. Read the installation instructions matching the agent client to offer the installation instructions.
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Create Python agents on Azure AI Foundry that retain conversation context and use multiple tools. The skill covers code execution, file and web search, external tool connections, streaming responses, and outputs organized into defined fields.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Set up AI Runway on an existing AKS cluster, from checking cluster health and GPU compatibility to installing model serving software, deploying a first AI model, and verifying that it runs.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load OOM, DCGM/VRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugin).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Lookup documented AKS fixes only when the prompt includes an exact catalog signature and all of its qualifiers: VMCannotFitEphemeralOSDisk; NodePoolMcVersionIncompatible; 'NodeImageVersion is not accepted'; AKS SkuNotAvailable with size, location, and zone; ZonalAllocationFailed with insufficient zone capacity; OverconstrainedAllocationRequest with listed constraints; nested AKS vmssCSE/CSE VMExtensionError_OutboundConnFail, VMExtensionError_K8SAPIServerConnFail, or VMExtensionError_K8SAPIServerDNSLookupFail; or AllocationFailed with the full cataloged internal-error or insufficient-regional-capacity message. Never use for quota errors, code-only or bare wrappers, generic symptoms, incomplete signatures, or failures outside AKS; use aks-troubleshooting or azure-diagnostics.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Collect bounded packet captures from AKS nodes or pods alongside Azure network settings. Use the captured traffic as evidence when investigating where packets are lost, after initial checks that do not change the environment.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Investigate live Azure Kubernetes Service incidents through read-only checks of logs, events, and resource state. Trace workload, node, networking, or upgrade failures and produce an incident report with supporting evidence, confidence, and proposed remediation.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.