What does this skill do, and when should you use it?
Azure Diagnostics is one skill in the azure-skills plugin within Microsoft's Agent Skills repository. It focuses on troubleshooting Azure production incidents across App Service, Container Apps, Function Apps, AKS, Event Hubs, and Service Bus. Its workflow covers symptoms, resource health, logs, metrics, and recent changes, with optional AppLens, Azure Monitor, and Resource Health MCP support. AKS and Azure Messaging incidents are routed to dedicated troubleshooting documents.
It identifies symptoms, checks Azure resource health, reviews activity and application logs, analyzes metrics and KQL results, investigates recent changes, and documents findings and attempted remediation. The skill supplies Azure CLI examples for resource inspection, activity logs, Container Apps logs, and Application Insights trace queries. It also specifies invocation patterns for AppLens, Azure Monitor, and Resource Health MCP tools.
- An App Service engineer investigating high CPU, deployment failures, crashes, slow responses, TLS, or custom-domain issues.
- A Function App developer diagnosing invocation failures, timeouts, binding errors, cold starts, or missing app settings.
- An AKS operations team investigating pending pods, CrashLoop failures, unavailable nodes, CoreDNS, networking, ingress, or upgrade problems.
- A Container Apps engineer diagnosing image-pull failures, cold starts, health probes, or port mismatches.
- An Event Hubs or Service Bus SDK developer investigating AMQP connection failures, lost message locks, dead letters, or connectivity errors.
How do you install this skill?
- Do not treat scaling, configuration, certificate, identity, or auto-heal commands as default executable actions; confirm targets, permissions, blast radius, backups, and rollback first.
- Azure CLI, MCP, kubectl, log tables, and regional capabilities vary by environment; validate all placeholders, query results, and remediation suggestions manually.
- Logs, configuration, connection strings, and diagnostic output may contain sensitive data; the documentation lacks redaction, data-minimization, and data-transfer guidance.
- Mainland-China network, Azure-region, and MCP reachability are unspecified, and there are no Chinese trigger or interaction examples.
- Shell / CLI
- Network access
- MCP Server
Azure CLIAppLens MCPAzure Monitor MCPAzure Resource Health MCP
The repository README documents this collection command: npx skills add microsoft/skills. Select the required skills in the wizard; skills are installed in the chosen agent directory, such as .github/skills/ for GitHub Copilot. It also documents Copilot CLI plugin installation: /plugin marketplace add microsoft/skills, followed by /plugin install azure-skills@skills. The supplied material does not document a standalone installation command for azure-diagnostics.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/.github/plugins/azure-skills/skills/azure-diagnostics" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- troubleshoot app service
- AKS pod is pending, investigate the root cause.
With the skill loaded, submit a concrete diagnostic request such as “troubleshoot app service” or “AKS pod is pending, investigate the root cause.” The prescribed sequence is to identify symptoms, check resource health, review logs, analyze metrics, and investigate recent changes. Route AKS incidents to AKS Troubleshooting and Event Hubs or Service Bus SDK issues to Messaging Troubleshooting. For MCP calls, provide the resource ID, workspace ID, and KQL query as applicable; for CLI commands, replace RESOURCE_ID, RG, APP, and APP-INSIGHTS with real values.
What are this skill's strengths and limitations?
- Covers common production failure modes across several major Azure services.
- Provides a concrete diagnostic sequence plus Azure CLI, KQL, and MCP usage patterns.
- Separates AKS and Azure Messaging incidents through explicit routing guidance.
- The SKILL.md identifies Microsoft as author, version 1.1.6, and MIT as the license.
- Its scope is Azure production troubleshooting rather than general cloud or local-application debugging.
- AppLens and the other MCP tools are conditional on availability and require suitable environment access.
- Several detailed guides are referenced under files not included in the supplied material, so their depth cannot be assessed here.
- The source does not provide independent test coverage or a complete Azure permissions checklist for this individual skill.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Azure Production Diagnostics this page ✓ Microsoft · Official | 52 · Use with care | ★ 2.7k | 3mo ago | MIT |
| Azure Reliability Advisor ✓ Microsoft · Official | 57 · Use with care | ★ 2.7k | 3mo ago | MIT |
| Azure Cloud Migration Assistant ✓ Microsoft · Official | 54 · Use with care | ★ 2.7k | 3mo ago | MIT |
| AI Runway AKS Deployment Guide ✓ Microsoft · Official | 51 · Use with care | ★ 2.7k | 3mo ago | MIT |
| AKS Automatic Readiness ✓ Microsoft · Official | 55 · Use with care | ★ 2.7k | 3mo ago | MIT |
How did FollowSkills review this skill?
The skill explicitly defaults to read-only diagnostics, and its AKS guidance forbids restarting, deleting, scaling, upgrading, or reconfiguring unless the user explicitly requests remediation. However, other service guides directly provide commands for scaling, changing registry identity, enabling auto-heal, binding certificates, and changing configuration, without uniform step-by-step confirmation, least-privilege guidance, sensitive-log redaction, data-flow disclosure, or rollback plans, so points are deducted.
It provides a systematic flow covering symptoms, resource health, logs, metrics, and recent changes, and tells the agent to stop and ask when AKS identity is missing. However, it depends on Azure CLI, multiple MCP tools, kubectl, Docker, Kudu, and specific log tables; installation, authentication, permission, version-compatibility, and complete tool-failure feedback are underdocumented. Some commands and queries lack sufficient applicability notes. The score stays within the static-review ceiling because execution was not performed and edge coverage is limited.
Triggers cover common Azure production-diagnostics scenarios across App Service, Container Apps, Functions, AKS, Event Hubs, and Service Bus, while AKS inputs and stop conditions are relatively clear. However, the scope is very broad, non-fit cases, input/output formats, service-version differences, Chinese-language interaction, and mainland-China network or regional reachability are not addressed. Some core paths depend on Azure online services and MCP, so points are deducted.
The skill has triggers, a quick flow, service routing, reference directories, and command examples. Metadata includes MIT licensing, Microsoft authorship, and version 1.1.6; the repository also supplies a license, security policy, CI, and work-in-progress maintenance signals. However, there is no changelog, explicit maintenance owner or update path, dependency/install guidance, FAQ, compatibility matrix, or complete limitations disclosure. Progressive disclosure and troubleshooting remain incomplete if referenced documents or MCP tools are unavailable, so points are deducted.
For common Azure diagnostic tasks it supplies reusable CLI, KQL, and MCP templates, evidence ordering, and an output checklist, offering clear value over manual discovery. However, commands use many placeholders, correctness depends on environment, permissions, diagnostic configuration, and tool versions, and remediation suggestions require human review without representative result samples or static verification evidence. The score follows the static ceiling and is reduced for limited completeness and direct usability.
The material contains concrete commands, KQL, input requirements, evidence ordering, and several safety constraints; the repository also includes generic CI, evaluation workflows, and test code. However, the supplied tests do not demonstrate this azure-diagnostics skill's key paths. The workflows mainly cover generic evaluation and infrastructure, with no skill-specific tests, real outputs, independent corroboration, or versioned change evidence, so only limited static auditability is awarded.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →