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

73%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/azure-diagnostics/SKILL.md

Quality

Content

57%

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

This skill serves well as a routing hub and quick-reference for Azure diagnostics, with strong progressive disclosure and clear service-to-reference mapping. Its main weaknesses are the abstract diagnostic workflow lacking decision criteria and validation checkpoints, some content duplication, and MCP tool examples that aren't in a clearly executable format. The verbose trigger list and authoritative banner consume tokens without adding value.

Suggestions

Replace the abstract Quick Diagnosis Flow with concrete decision trees: e.g., 'If HTTP 5xx → check resource health first → if healthy, query application logs with [specific KQL] → if unhealthy, check Azure status page'

Remove the duplicated CLI commands (resource health check appears twice) and trim the Triggers section to 3-4 representative examples since Claude can generalize

Add validation/verification steps after remediation actions, such as 'After applying fix, re-run health check and confirm status returns Available'

Standardize MCP tool examples into a consistent, copy-paste-ready format rather than the current pseudo-YAML notation

Dimension	Reasoning	Score
Conciseness	The skill has some unnecessary verbosity — the 'AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE' banner is performative, the 'Triggers' section extensively lists things Claude can infer, and some commands are repeated (e.g., `az resource show` and `az monitor activity-log list` appear in both Quick Reference and Check Azure Resource Health sections). However, the overall structure is reasonably efficient with tables and concise sections.	2 / 3
Actionability	Provides concrete CLI commands and MCP tool invocations with parameter structures, which is good. However, the MCP tool examples use pseudo-syntax rather than executable/copy-paste-ready format, and the Quick Diagnosis Flow is abstract ('What's failing?', 'What do logs show?') without concrete decision criteria or specific actions to take at each step.	2 / 3
Workflow Clarity	The Quick Diagnosis Flow provides a high-level sequence but lacks validation checkpoints, decision branches, and feedback loops. For production troubleshooting (a high-stakes, multi-step process), there's no explicit 'if X then do Y' logic, no verification steps after remediation, and no error recovery guidance. The routing table is clear but the actual diagnostic workflow is underspecified.	2 / 3
Progressive Disclosure	Excellent use of progressive disclosure with a clear overview/routing table pointing to one-level-deep references organized by service type. The table format makes navigation easy, references are well-signaled with relative paths, and the skill appropriately keeps high-level guidance inline while deferring service-specific details to dedicated files.	3 / 3
	Total	9 / 12 Passed

Description

89%

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 with excellent trigger term coverage and clear completeness via the explicit WHEN clause. Its main weakness is that the 'what it does' portion is somewhat thin on concrete actions—it says 'debug' and 'triage' but doesn't enumerate specific capabilities like 'query logs with KQL, analyze resource health status, identify root causes from AppLens detectors.' The trigger term list is extensive and well-chosen for real user queries.

Suggestions

Expand the capability portion before the WHEN clause to list more concrete actions, e.g., 'Queries logs with KQL, analyzes AppLens detectors, checks resource health status, identifies root causes, and recommends remediation steps.'

Dimension	Reasoning	Score
Specificity	The description names the domain (Azure production issues) and mentions specific tools (AppLens, Azure Monitor, resource health), but the 'what it does' portion is limited to 'debug...issues...using...safe triage' without listing multiple concrete actions like 'analyze logs, restart services, query metrics.' The bulk of the description is trigger terms rather than capability descriptions.	2 / 3
Completeness	The description explicitly 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). The 'WHEN' clause is comprehensive and clearly delineated.	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would actually say: 'high CPU', 'deployment failure', 'crashloop', 'pod pending', 'node not ready', 'cold start issues', 'dead letter', 'AMQP connection failure', 'KQL', 'kubectl cannot connect'. These are highly specific, natural phrases that map directly to real user queries across multiple Azure services.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with Azure-specific terminology (AppLens, AKS, App Service, Event Hubs, Service Bus, AMQP, KQL) that clearly carves out a niche. Unlikely to conflict with generic debugging or non-Azure cloud skills due to the specificity of the platform and service references.	3 / 3
	Total	11 / 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/github-copilot-for-azure
Commit: d4563f6

Reviewed: 3 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.