azure-diagnostics

Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, 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.

Quality

78%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.github/plugins/azure-skills/skills/azure-diagnostics/SKILL.md

Quality

Discovery

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.

This is a strong skill description that clearly defines its scope (Azure production debugging), names specific tools and services, and provides an extensive explicit trigger list via the 'WHEN:' clause. The trigger terms are highly natural and cover a wide range of specific failure scenarios a user would encounter. The description is concise yet comprehensive, making it easy for Claude to select this skill appropriately.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and tools: AppLens, Azure Monitor, resource health, safe triage, and references specific scenarios like crashloop, pod pending, node not ready, upgrade failures, cold start issues, health probe failures, and KQL analysis.	3 / 3
Completeness	Clearly answers both 'what' (debug Azure production issues using AppLens, Azure Monitor, resource health, and safe triage) and 'when' with an explicit 'WHEN:' clause listing extensive trigger scenarios covering container apps, functions, AKS, specific error conditions, and log analysis.	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'debug production issues', 'troubleshoot container apps', 'kubectl cannot connect', 'CoreDNS failures', 'pod pending', 'crashloop', 'node not ready', 'image pull failures', 'cold start issues', 'health probe failures', 'KQL', 'analyze logs'. These are highly natural phrases a user would type when encountering these problems.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche: Azure-specific production debugging using named Azure tools (AppLens, Azure Monitor) and Azure-specific services (AKS, container apps, functions). The combination of Azure platform + specific debugging scenarios + named tools makes it very unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

57%

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

This skill provides a reasonable hub/overview for Azure diagnostics with good progressive disclosure and routing to sub-documents. However, it suffers from some unnecessary verbosity (authoritative guidance banner, triggers list, generic diagnosis flow) and the actionable content—while present—could be more concrete with executable examples and explicit decision trees. The workflow lacks validation checkpoints and feedback loops expected for production incident triage.

Suggestions

Remove the 'AUTHORITATIVE GUIDANCE' banner and 'Triggers' section—these waste tokens on things Claude can infer from context and skill metadata.

Replace the generic Quick Diagnosis Flow with a concrete decision tree: e.g., 'If resource health shows Degraded → check activity log for platform events → if platform event found, document and wait; if not, proceed to logs.'

Make MCP tool examples more concrete with a consistent, clearly executable format and add expected output interpretation (e.g., 'If AppLens returns severity=Critical, prioritize the top recommendation').

Add a validation/feedback loop: after attempting remediation, re-check resource health and logs to confirm resolution before closing the incident.

Dimension	Reasoning	Score
Conciseness	The 'AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE' banner is unnecessary filler. The 'Triggers' section lists things Claude can infer from context. The 'Quick Diagnosis Flow' is generic knowledge Claude already has. However, the tool invocation examples and CLI commands are appropriately concise.	2 / 3
Actionability	CLI commands and MCP tool invocations provide concrete guidance, but the MCP tool examples use a pseudo-YAML format that isn't clearly executable. The Quick Diagnosis Flow is vague ('What's failing?', 'What do logs show?') rather than providing specific actionable steps. Placeholder values like RESOURCE_ID and RG are appropriate but some commands lack context on interpreting output.	2 / 3
Workflow Clarity	The Quick Diagnosis Flow provides a sequence but lacks validation checkpoints and feedback loops. There's no guidance on what to do if resource health check reveals issues vs. passes, no error recovery steps, and no explicit decision points between the diagnostic steps. The routing table is helpful but the actual diagnostic workflow is underspecified.	2 / 3
Progressive Disclosure	Excellent use of progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to container-apps, functions, AKS troubleshooting, KQL queries, and Azure Resource Graph. The routing section explicitly clarifies what stays in this file vs. what's delegated. The reference table with service-to-file mapping is well-structured.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/azure-skills
Commit: 742d20b

Reviewed: 5 days 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.