CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

azure-diagnostics

Debug Azure production issues using AppLens, Azure Monitor, resource health, and safe triage, including evidence-only diagnosis without live access. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, container app 503 or target port mismatch, troubleshoot functions, function telemetry missing or stopped after a config/connection-string change, 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, lock renewal during long-running processing, service bus dead letter.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/azure-skills/skills/azure-diagnostics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 has a sound overview-plus-references structure and some genuinely executable CLI/KQL content, but it is undermined by broken navigation (three of six service guides reference nonexistent files), an unlinked scripts/ bundle, pseudocode MCP invocation blocks, and repeated content across sections. All four dimensions land mid-scale as a result.

Suggestions

Fix or remove the broken routing targets: troubleshooting/aks/aks-troubleshooting.md, troubleshooting/compute/vm-troubleshooting.md, and troubleshooting/messaging/README.md do not exist in the bundle — either add these files or repoint the AKS, Compute, and Messaging rows (and the Routing bullets) to real paths (progressive_disclosure, actionability).

Make the bundled scripts actionable: Rule 7 says "Prefer bundled diagnostic scripts" but never names them — list the actual paths in scripts/ (e.g. scripts/aks-baseline.sh, scripts/test-messaging-connectivity.sh) in the routing table or rules, and replace the pseudo-invocation MCP blocks ("mcp_azure_mcp_applens / intent: ... / command: ...") with the real tool-call format (actionability).

De-duplicate the body: drop the "AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE" banner, the Triggers section that restates the frontmatter WHEN list, the repeated CLI block under "Check Azure Resource Health", and the trailing References section that duplicates the routing-table links; use the freed tokens to add verification checkpoints to the Quick Diagnosis Flow (conciseness, workflow_clarity).

DimensionReasoningScore

Conciseness

The core tables and commands are dense, but several sections are redundant or padded: the "AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE" banner, a Triggers section restating the frontmatter WHEN list, the "Check Azure Resource Health / Using CLI" block repeating "az resource show --ids RESOURCE_ID" and "az monitor activity-log list -g RG --max-events 20" verbatim from Quick Reference, and a References section duplicating the routing-table links. Not 2 because there is no concept-explanation fluff; not 4 because the duplication spans multiple sections rather than being minor instances.

3 / 5

Actionability

There is genuinely executable content ("az containerapp logs show --name APP -g RG --follow", the App Insights KQL query), but the MCP blocks are pseudo-invocation format ("mcp_azure_mcp_applens / intent: ... / command: ...") rather than actual tool-call syntax, Rule 7 says "Prefer bundled diagnostic scripts" without naming any of the 12 scripts in scripts/, and three of the six routing targets point to files that do not exist. Not 4 because these gaps exceed "minor"; not 2 because concrete, runnable CLI/KQL guidance is present.

3 / 5

Workflow Clarity

The 5-step Quick Diagnosis Flow ("Identify symptoms - What's failing?" through "Investigate recent changes - What changed?") plus the ordered Rules give a coherent sequence, but steps are generic prompts with no validation checkpoints or error-recovery guidance — e.g. "az resource show --ids RESOURCE_ID" is labeled "Check resource health" even though it returns resource properties rather than health status, so step outcomes cannot be verified. Not 4 because checkpoints are missing entirely; not 2 because a clear, ordered sequence is present.

3 / 5

Progressive Disclosure

The overview-plus-references structure is well signaled (service routing table pointing one level deep to references/app-service/README.md, references/functions/README.md, etc.), but three of the six guide paths referenced in the body ("troubleshooting/aks/aks-troubleshooting.md", "troubleshooting/compute/vm-troubleshooting.md", "troubleshooting/messaging/README.md") do not exist in the bundle, and the 12 files in scripts/ are never linked from the body. Not 4 because broken navigation targets and an unlinked scripts directory are more than minor organization gaps; not 2 because the structure is present and clearly signaled.

3 / 5

Total

12

/

20

Passed

Description

91%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.

The description explicitly states both what the skill does and when to use it, with an exceptionally comprehensive set of natural trigger phrases spanning App Service, Container Apps, Functions, AKS, VMs, and messaging. The only weaknesses are a handful of overly generic trigger terms ("analyze logs", "cold start issues") and action phrasing that leans on tools rather than distinct actions.

DimensionReasoningScore

Specificity

"Debug Azure production issues using AppLens, Azure Monitor, resource health, and safe triage, including evidence-only diagnosis without live access" names the domain and several concrete capabilities. It is not 5 because the action verbs reduce to "debug/troubleshoot" plus a list of tools rather than a comprehensive set of distinct actions, and not 3 because well more than 1-2 concrete capabilities are explicitly stated.

4 / 5

Completeness

Both halves are explicit: the "what" ("Debug Azure production issues using AppLens, Azure Monitor, resource health, and safe triage, including evidence-only diagnosis without live access") and the "when" (an explicit "WHEN:" clause with dozens of concrete trigger phrases), matching the anchor-5 example. Not 4 because neither half could be more explicit.

5 / 5

Trigger Term Quality

The WHEN clause covers natural user phrasing near-exhaustively across all six services: "troubleshoot app service", "app service high CPU", "can't connect to VM", "reset VM password", "crashloop", "AMQP connection failure", "message lock lost", "service bus dead letter". It is not 4 because no common variation or synonym is meaningfully missing.

5 / 5

Distinctiveness Conflict Risk

A clear Azure diagnostics niche with unambiguous triggers ("NSG or firewall blocking", "kube-system/CoreDNS failures", "service bus dead letter"), but generic phrases like "analyze logs", "root cause of errors", "cold start issues", and "health probe failures" could overlap with general logging/observability or other-cloud skills. Not 5 due to that minor overlap risk; not 3 because the vast majority of triggers are distinctly Azure-specific.

4 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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/GitHub-Copilot-for-Azure

Path

plugins/azure-skills/skills/azure-diagnostics/SKILL.md

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.