Robertjam954/multimodal_rag_application / .claude/skills/azure-diagnostics
azure-diagnostics
VerifiedDebug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, troubleshoot functions, troubleshoot AKS, kubectl cannot connect, kube-system/CoreDNS failures, pod pending, crashloop, node not ready, upgrade failures, analyze logs, KQL, insights, image pull failures, cold start issues, health probe failures, resource health, root cause of errors, troubleshoot event hubs, troubleshoot service bus, messaging SDK error, AMQP connection failure, message lock lost, service bus dead letter.
troubleshooting/aks/references/aks-mcp.md
View on GitHub# AKS MCP Reference
Use this reference when AKS-aware MCP tools are available in the client.
## Preference Order
1. `mcp_azure_mcp_aks`
2. The AKS-MCP tools that surface after discovery in the client
3. Supporting Azure tools such as `mcp_azure_mcp_applens`, `mcp_azure_mcp_monitor`, and `mcp_azure_mcp_resourcehealth`
4. Raw `az aks` and `kubectl` only when required functionality is missing from MCP
## Happy Path
After selecting `mcp_azure_mcp_aks`, let the client enumerate the exact AKS-MCP tools it exposes and choose the smallest tool that fits the task.
Favor the obvious read paths first:
- cluster and Azure-side inspection
- detector or diagnostic workflows
- monitoring, metrics, or control-plane-log checks
- kubectl-style read operations
## Authentication And Access
AKS-MCP is Azure CLI-backed. Expect service principal, workload identity, managed identity, or existing `az login` auth, usually keyed by `AZURE_CLIENT_ID`. If `AZURE_SUBSCRIPTION_ID` is set, expect the server to select that subscription after login.
Default to `readonly`. Only suggest `readwrite` or `admin` when the current diagnostic step truly requires it.
## Detector Notes
For detector-style workflows, use the cluster resource ID, keep the time window within the last 30 days, cap each run to 24 hours, and stay within the supported AKS detector categories.
## Fallback Rule
If the client does not expose the AKS-MCP surface needed for a check, then fall back to:
- `az aks` for Azure-side AKS operations
- raw `kubectl` for Kubernetes-side inspection
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |