azure-diagnostics

Debug 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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is actionable and well-structured with concrete commands and MCP signatures, but suffers from redundant triggers/health sections and references to troubleshooting files that do not exist in the bundle.

Suggestions

Remove the duplication between the Triggers section and the frontmatter trigger list, and consolidate the two Resource Health CLI blocks into one.

Add explicit validation/verification checkpoints to the Quick Diagnosis Flow (e.g., confirm resource health is healthy before deep-diving into logs) so the workflow supports error recovery.

Fix broken links: create the referenced `troubleshooting/aks/aks-troubleshooting.md` and `troubleshooting/messaging/README.md` files, or repoint those table rows and Routing entries at the references that actually exist.

Dimension	Reasoning	Score
Conciseness	Largely lean with command snippets and a service table, but the Triggers section duplicates the frontmatter trigger list and Resource Health appears twice with overlapping `az resource show` commands, so it could be tightened.	2 / 3
Actionability	Provides concrete, executable commands (`az containerapp logs show`, `az monitor app-insights query` with a real KQL snippet) and explicit MCP tool signatures with parameters, copy-paste ready.	3 / 3
Workflow Clarity	The 5-step Quick Diagnosis Flow sequences the work but lacks explicit validation checkpoints or feedback loops; for production diagnostics this caps clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	Overview with a well-signaled, one-level-deep reference table exists, but the AKS and Messaging rows link to a `troubleshooting/` path that is not present in the bundle, leaving broken routing links.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and complete, clearly stating both capability and when to activate. It carves out a distinctive Azure-diagnostics niche with little conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and tools — "Debug Azure production issues... using AppLens, Azure Monitor, resource health, and safe triage" — alongside specific failure modes rather than vague language.	3 / 3
Completeness	Explicitly answers both what it does (debug Azure production issues via named tools) and when to use it via a clear "WHEN:" clause enumerating triggers.	3 / 3
Trigger Term Quality	Extensive natural phrasings a user would actually say ("app service high CPU", "kubectl cannot connect", "pod pending", "crashloop", "image pull failures", "cold start issues", "message lock lost") give broad, realistic coverage.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear Azure-production-debugging niche with distinctive triggers unlikely to fire for unrelated skills; only minor redundancy ("on Azure") keeps it from being perfect, but distinctiveness is strong.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 5 missing, 10 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 5 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: microsoft/azure-skills
Commit: 2cd48ca

Reviewed: about 8 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.