azure-diagnostics
Debug and troubleshoot production issues on Azure. Covers Container Apps and Function Apps diagnostics, log analysis with KQL, health checks, and common issue resolution for image pulls, cold starts, health probes, and function invocation failures. USE FOR: debug production issues, troubleshoot container apps, troubleshoot function apps, troubleshoot Azure Functions, analyze logs with KQL, fix image pull failures, resolve cold start issues, investigate health probe failures, check resource health, view application logs, find root cause of errors, function app not working, function invocation failures DO NOT USE FOR: deploying applications (use azure-deploy), creating new resources (use azure-prepare), cost optimization (use azure-cost-optimization)
Install with Tessl CLI
npx tessl i github:microsoft/azure-skills --skill azure-diagnostics91
Quality
86%
Does it follow best practices?
Impact
100%
1.58xAverage score across 3 eval scenarios
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 an exemplary skill description that excels across all dimensions. It provides specific concrete actions, comprehensive trigger terms covering both technical and natural language, explicit 'USE FOR' and 'DO NOT USE FOR' clauses, and clear differentiation from related Azure skills. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Container Apps and Function Apps diagnostics, log analysis with KQL, health checks, and common issue resolution for image pulls, cold starts, health probes, and function invocation failures.' These are detailed, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (diagnostics, log analysis, health checks, issue resolution) AND when with explicit 'USE FOR:' triggers. Also includes helpful 'DO NOT USE FOR:' guidance to prevent misuse, which exceeds typical completeness requirements. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'debug production issues', 'troubleshoot container apps', 'analyze logs with KQL', 'fix image pull failures', 'function app not working', 'find root cause of errors'. Includes both technical terms and natural language variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear Azure debugging/troubleshooting niche. Explicitly differentiates from related skills (azure-deploy, azure-prepare, azure-cost-optimization) with 'DO NOT USE FOR' clause, minimizing conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured diagnostic skill with strong actionability and progressive disclosure. The main weaknesses are some verbosity in the header/triggers sections and missing validation/feedback loops in the troubleshooting workflow. The reference architecture and concrete commands make it immediately useful.
Suggestions
Remove or significantly condense the 'AUTHORITATIVE GUIDANCE' header and 'Triggers' section - Claude can infer when to use this skill from context
Add explicit validation steps to the Quick Diagnosis Flow, such as 'Verify fix by re-running health check' or 'If issue persists, escalate to next diagnostic level'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary elements like the verbose 'AUTHORITATIVE GUIDANCE' header and the 'Triggers' section which largely duplicates what Claude would infer from context. The diagnostic flow and commands are appropriately concise. | 2 / 3 |
Actionability | Provides concrete, executable CLI commands and MCP tool invocations with clear parameter structures. Commands are copy-paste ready with placeholder values clearly marked (RESOURCE_ID, RG, APP). | 3 / 3 |
Workflow Clarity | The Quick Diagnosis Flow provides a clear sequence but lacks explicit validation checkpoints or feedback loops. For troubleshooting workflows involving production systems, there's no guidance on verifying fixes or rollback procedures if remediation fails. | 2 / 3 |
Progressive Disclosure | Excellent structure with a clear overview, quick reference section, and well-signaled one-level-deep references to detailed guides (container-apps/, functions/, kql-queries.md). Navigation is intuitive with a service-based table directing to specific troubleshooting guides. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%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.
- Reviewed
Table of Contents
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.