azure-observability-investigator
Use this skill for Azure Monitor, Log Analytics, Application Insights, alerting, KQL triage, telemetry-gap analysis, workbooks, or operator-grade incident and posture investigations.
Install
npx skills add https://github.com/VincentChuWaiChow/vanguard-frontier-agentic/tree/master/skills/azure/azure-observability-investigator
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install vincentchuwaichow-vanguard-frontier-agentic@llmmart
git clone https://github.com/VincentChuWaiChow/vanguard-frontier-agentic.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole vincentchuwaichow/vanguard-frontier-agentic collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Azure Observability Investigator
Purpose
Investigate Azure operational health using evidence from metrics, logs, traces, alerts, and observability configuration before jumping to root-cause claims.
This skill is for operator-grade Azure monitoring work across:
- Azure Monitor metrics and logs,
- Log Analytics workspace design and query posture,
- Application Insights telemetry and dependency signals,
- alert rules, action groups, and alert processing rules,
- workbook or Grafana-backed operational visibility,
- KQL-based triage,
- telemetry blind spots, noisy alerts, and missing-signal investigations.
When to use
Use this skill when the user asks for:
- Azure Monitor or Application Insights incident investigation,
- noisy, duplicate, stale, or low-value alert review,
- Log Analytics or KQL triage help,
- missing telemetry or observability-gap analysis,
- workspace or signal-placement review,
- dashboard, workbook, or operational reporting critique,
- recommended next diagnostic steps for a recent failure.
Do not use this skill as a substitute for:
- full application debugging with code changes,
- SIEM engineering or Microsoft Sentinel content design,
- resource-health-first outage triage when the main question is whether Azure itself is degraded,
- instrumentation implementation details unless the user asks for that next.
Lean operating rules
- Prefer Microsoft Learn documentation through the user's configured documentation MCP, then sampled read-only Azure evidence when available, then sanitized user evidence.
- Separate confirmed facts from inference. If state was not queried or shown, say so.
- Challenge broad access, broad scope, destructive changes, and hand-wavy production claims.
- Keep the answer scoped, reversible, least-privilege, and explicit about blockers or unknowns.
References
Load these only when needed:
- Azure Observability Investigation Operations — use for current service behavior, common failure modes, hard design rules, verification targets, and push-back conditions.
- Safety checklist — use for evidence labels, risk gates, mutation boundaries, approval rules, credential boundaries, and current-state caveats.
- MCP and evidence path — use when choosing live Azure evidence, confirming Microsoft MCP capability, or switching to documentation mode.
- Workflow and output contract — use when executing the full review, applying stress checks, or formatting the final answer.
- Official sources — use when you need the detailed Microsoft documentation list or source notes.
Response minimum
Return, at minimum:
- the scoped target and evidence level,
- the main risks or control gaps,
- the safest next actions,
- the assumptions or blockers that prevent stronger conclusions.
Files (vanguard-frontier-agentic)
-
references
-
mcp-and-evidence.md 1.2 KB
Loading… -
observability-investigation-operations.md 4.6 KB
Loading… -
official-sources.md 2.4 KB
Loading… -
safety-checklist.md 1.6 KB
Loading… -
workflow-and-output.md 1.6 KB
Loading…
-
-
metadata.json 1.7 KB
Loading… -
SKILL.md 3.3 KB
--- name: azure-observability-investigator description: Use this skill for Azure Monitor, Log Analytics, Application Insights, alerting, KQL triage, telemetry-gap analysis, workbooks, or operator-grade incident and posture investigations. allowed-tools: Read Grep Glob WebFetch metadata: author: github: VincentChuWaiChow version: 0.1.2 updated: "2026-06-05" category: observability --- # Azure Observability Investigator ## Purpose Investigate Azure operational health using evidence from metrics, logs, traces, alerts, and observability configuration before jumping to root-cause claims. This skill is for operator-grade Azure monitoring work across: - Azure Monitor metrics and logs, - Log Analytics workspace design and query posture, - Application Insights telemetry and dependency signals, - alert rules, action groups, and alert processing rules, - workbook or Grafana-backed operational visibility, - KQL-based triage, - telemetry blind spots, noisy alerts, and missing-signal investigations. ## When to use Use this skill when the user asks for: - Azure Monitor or Application Insights incident investigation, - noisy, duplicate, stale, or low-value alert review, - Log Analytics or KQL triage help, - missing telemetry or observability-gap analysis, - workspace or signal-placement review, - dashboard, workbook, or operational reporting critique, - recommended next diagnostic steps for a recent failure. Do not use this skill as a substitute for: - full application debugging with code changes, - SIEM engineering or Microsoft Sentinel content design, - resource-health-first outage triage when the main question is whether Azure itself is degraded, - instrumentation implementation details unless the user asks for that next. ## Lean operating rules - Prefer Microsoft Learn documentation through the user's configured documentation MCP, then sampled read-only Azure evidence when available, then sanitized user evidence. - Separate confirmed facts from inference. If state was not queried or shown, say so. - Challenge broad access, broad scope, destructive changes, and hand-wavy production claims. - Keep the answer scoped, reversible, least-privilege, and explicit about blockers or unknowns. ## References Load these only when needed: - [Azure Observability Investigation Operations](references/observability-investigation-operations.md) — use for current service behavior, common failure modes, hard design rules, verification targets, and push-back conditions. - [Safety checklist](references/safety-checklist.md) — use for evidence labels, risk gates, mutation boundaries, approval rules, credential boundaries, and current-state caveats. - [MCP and evidence path](references/mcp-and-evidence.md) — use when choosing live Azure evidence, confirming Microsoft MCP capability, or switching to documentation mode. - [Workflow and output contract](references/workflow-and-output.md) — use when executing the full review, applying stress checks, or formatting the final answer. - [Official sources](references/official-sources.md) — use when you need the detailed Microsoft documentation list or source notes. ## Response minimum Return, at minimum: - the scoped target and evidence level, - the main risks or control gaps, - the safest next actions, - the assumptions or blockers that prevent stronger conclusions.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.