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

The canonical home for this skill is azure-diagnostics in microsoft/GitHub-Copilot-for-Azure

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 solid skeleton — a quick diagnosis flow, ordering rules with an evidence-only branch, executable CLI/KQL snippets, and a well-signaled service routing table — but execution breaks down in practice: three routing targets are missing from the bundle, the bundled diagnostic scripts are never named, and roughly a fifth of the body is duplicated trigger/link material. All four dimensions land at the 'structure present, key details missing' level.

Suggestions

Fix the broken routing: either add the missing troubleshooting/aks/aks-troubleshooting.md, troubleshooting/compute/vm-troubleshooting.md, and troubleshooting/messaging/README.md files to the bundle or repoint those links to existing references — currently AKS, VM, and Messaging incidents (3 of 6 service areas) dead-end.

Make rule 7 actionable by naming the bundled scripts with paths, e.g. scripts/aks-baseline.sh, scripts/appservice-diagnostics.sh, scripts/containerapp-diagnostics.sh, scripts/pod-evidence.sh, and scripts/test-messaging-connectivity.sh, so 'run the applicable script first' resolves to a concrete command.

Tighten token use: delete the Triggers section (the description's WHEN clause already carries that list), the trailing References list that duplicates the routing table, and the 'AUTHORITATIVE GUIDANCE' blockquote; optionally replace the generic Quick Diagnosis Flow questions with explicit branch points (e.g. 'if resource health is degraded → stop and report platform issue; if healthy → continue to logs') to add the missing validation checkpoints.

DimensionReasoningScore

Conciseness

The core content is efficient (tight CLI blocks, "Quick Diagnosis Flow", no explanations of concepts Claude already knows), but there is real padding: the "AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE" blockquote adds no diagnostic value, the 15-bullet Triggers section duplicates the description's WHEN list, and the trailing References list repeats links already given in the service table and Routing section. Not 2 because the padding is duplication rather than verbose explanation, and the rest is lean.

3 / 5

Actionability

There is genuinely executable guidance ("az monitor app-insights query --apps APP-INSIGHTS -g RG --analytics-query \"traces | where timestamp > ago(1h)…\"", "az containerapp logs show --name APP -g RG --follow"), but rule 7's "run the applicable script first" never names any of the 12 scripts in scripts/, and the routing targets troubleshooting/aks/aks-troubleshooting.md, troubleshooting/compute/vm-troubleshooting.md, and troubleshooting/messaging/README.md do not exist in the bundle, dead-ending 3 of 6 service areas. These are missing key details, not the minor gaps of anchor 4.

3 / 5

Workflow Clarity

"Quick Diagnosis Flow" lays out a clear 5-step sequence ("Identify symptoms → Check resource health → Review logs → Analyze metrics → Investigate recent changes") and rule 2 gives an explicit evidence-only branch ("do not query or modify Azure… identify assumptions and provide optional verification steps"), but each step is a generic question with implicit checkpoints — there is no validation loop or guidance on how to branch based on what resource health or logs reveal. Not 4 because checkpoints are missing/implicit rather than present-with-minor-gaps.

3 / 5

Progressive Disclosure

The overview shape is good — a service table with issue summaries pointing to one-level-deep references/<service>/README.md files that all exist and are clearly signaled — but scored against the actual bundle, 3 of the 8 referenced paths (all three troubleshooting/… links for AKS, VM, and Messaging) are broken, and the 12 diagnostic scripts in scripts/ are never referenced by path anywhere in the body. Navigation works for only half the service areas, which anchor 4's 'minor organization gaps' does not cover.

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.

A strong description: concrete capability statement, explicit WHEN clause, and exceptionally thorough natural-language trigger coverage across App Service, Container Apps, Functions, AKS, VM, and messaging services. The only weaknesses are generic early triggers and non-Azure-specific Kubernetes terms that slightly raise conflict risk.

DimensionReasoningScore

Specificity

The what-clause names several concrete actions and modes — "Debug Azure production issues using AppLens, Azure Monitor, resource health, and safe triage, including evidence-only diagnosis without live access" — which goes beyond the 1-2 actions of anchor 3, but it is one macro-action with tools rather than the comprehensive list of distinct actions that anchor 5 requires.

4 / 5

Completeness

It explicitly answers both parts: a clear what ("Debug Azure production issues using AppLens, Azure Monitor, resource health, and safe triage, including evidence-only diagnosis") and an explicit "WHEN:" clause with dozens of concrete trigger phrases, matching the anchor-5 example pattern exactly. Not 4, because the 'when' is fully explicit rather than could-be-more-specific.

5 / 5

Trigger Term Quality

The WHEN list gives comprehensive natural phrases a user would actually say — "app service high CPU", "can't connect to VM", "reset VM password", "kubectl cannot connect", "pod pending, crashloop", "message lock lost", "service bus dead letter" — including synonyms and error-specific terms, matching the comprehensive-coverage anchor. Neighboring anchor 4 ('a few natural terms missing') clearly fits worse.

5 / 5

Distinctiveness Conflict Risk

It carves a clear Azure-diagnostics niche with distinct triggers, but generic opening terms ("debug production issues", "analyze logs", "root cause of errors") and Kubernetes phrases that are not Azure-specific ("pod pending", "crashloop", "kubectl cannot connect") create minor overlap risk with generic K8s or log-analysis skills — more than 'minimal', so not 5.

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/azure-skills

Path

.github/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.