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, VM RDP, Linux SSH, VM black screen, can't connect to VM, reset VM password, NSG or firewall blocking, 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

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.github/plugins/azure-skills/skills/azure-diagnostics/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

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

The body is well-organized and actionable with concrete CLI/MCP examples, but it loses points for implicit workflow checkpoints and, more seriously, for repeatedly routing users to missing troubleshooting/* files that do not exist in the bundle.

Suggestions

Create the missing troubleshooting/aks/aks-troubleshooting.md, troubleshooting/compute/vm-troubleshooting.md, and troubleshooting/messaging/README.md files referenced in the routing table, or remove/repoint those links to existing references.

Add explicit validation checkpoints to the diagnosis flow (e.g., 'if resource health is degraded, stop and surface that before reading logs') to convert the implicit sequence into a feedback-loop workflow.

Trim the 'MANDATORY COMPLIANCE' banner and the duplicated resource-health CLI block to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with concise code blocks and a routing table, but the 'AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE' banner and a duplicated resource-health CLI block are trimmable padding.	4 / 5
Actionability	It provides executable az CLI commands, a KQL example, and MCP tool invocation templates with parameters, but the MCP blocks are structured templates with placeholders rather than fully copy-paste-ready calls.	4 / 5
Workflow Clarity	A numbered Quick Diagnosis Flow and routing Rules give a clear sequence, but checkpoints are implicit and there are no validate/fix/retry feedback loops for the investigation workflow.	3 / 5
Progressive Disclosure	Structure and one-level-deep reference signaling are good, but three routed paths (troubleshooting/aks, troubleshooting/compute, troubleshooting/messaging) point to a non-existent troubleshooting/ tree, breaking navigation.	3 / 5
	Total	14 / 20 Passed

Description

95%Weight 40%Scale 1-5

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

A strong, well-scoped description that pairs a concrete capability statement with an exhaustive set of natural trigger phrases. Minor weakness is that specificity rides on triggers rather than a crisp enumerated action list.

Dimension	Reasoning	Score
Specificity	The description names the domain and concrete tooling ('using AppLens, Azure Monitor, resource health, and safe triage') but the capability list leans on trigger phrasing rather than enumerated actions, leaving minor gaps short of comprehensive.	4 / 5
Completeness	It explicitly answers 'what' ('Debug Azure production issues... using AppLens, Azure Monitor, resource health, and safe triage') and 'when' via a concrete 'WHEN:' clause with many trigger phrases.	5 / 5
Trigger Term Quality	Extensive natural trigger phrases users would actually say ('app service high CPU', 'can't connect to VM', 'reset VM password', 'crashloop', 'pod pending', 'message lock lost', 'service bus dead letter') with strong synonym and error-code coverage.	5 / 5
Distinctiveness Conflict Risk	A narrow Azure-production-diagnostics niche with highly specific triggers (kube-system/CoreDNS failures, AMQP connection failure, service bus dead letter) gives it a clear niche with minimal overlap risk.	5 / 5
	Total	19 / 20 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: 8 missing, 13 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
Path: .github/plugins/azure-skills/skills/azure-diagnostics/SKILL.md
Commit: 16dc8c5

Reviewed: about 12 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.