troubleshoot-observability — Claude Code skill: Azure observability
The troubleshoot-observability skill for Claude Code coordinates Azure troubleshooting workflows. It guides agents through runtime failures, latency analysis, and monitoring configuration.
MIT ★ 3,232 updated 2026-10-23
/plugin marketplace add microsoft/skills
/plugin install azure-observability@skillsWhat troubleshoot-observability does
This skill assists in identifying root causes for application or agent health issues. Upon activation, the agent verifies specific operational requests, such as slow API responses, deployment failures, or telemetry configuration needs. It relies on external dependencies like azure-diagnostics and microsoft-foundry, which must be discovered through host capabilities.
It does not perform automated resource creation or code refactoring, focusing instead on evidence-backed investigation paths. If evidence is insufficient, the process remains inconclusive. Any actions regarding infrastructure changes or sensitive data access require explicit user approval throughout the session.
What it helps with
- diagnose API latency
- investigate deployment failures
- configure telemetry and alerts
- verify fixes after incidents
Example prompts for the agent
- /plugin marketplace add microsoft/skills
- troubleshoot-observability, my API is slow, help me investigate
- check observability status for current environment
How to install troubleshoot-observability
1Plugin marketplace
/plugin marketplace add microsoft/skills/plugin install azure-observability@skillsThis installs the whole azure-observability plugin with all its skills
2Skills CLI (Vercel)
npx skills add microsoft/skills --skill troubleshoot-observability -a claude-code3Manually: put the files in place
~/.claude/skills/troubleshoot-observability/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/troubleshoot-observability/
1Skills CLI (Vercel)
npx skills add microsoft/skills --skill troubleshoot-observability -a codex2Manually: put the files in place
.agents/skills/troubleshoot-observability/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add microsoft/skills --skill troubleshoot-observability -a cursor2Manually: put the files in place
.cursor/skills/troubleshoot-observability/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install microsoft/skills .github/plugins/azure-observability/skills/troubleshoot-observability2Manually: put the files in place
.github/skills/troubleshoot-observability/SKILL.md1Skills CLI (Vercel)
npx skills add microsoft/skills --skill troubleshoot-observability -a gemini-cli2Platform CLI
gemini skills install https://github.com/microsoft/skills --path .github/plugins/azure-observability/skills/troubleshoot-observabilityManually: put the files in place
.devin/skills/troubleshoot-observability/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about troubleshoot-observability
How to install troubleshoot-observability in Claude Code?
Run the commands /plugin marketplace add microsoft/skills followed by /plugin install azure-observability@skills.
What does troubleshoot-observability do?
It structures Azure troubleshooting by guiding the agent through performance and telemetry analysis while preventing unauthorized infrastructure changes.
What is required to use troubleshoot-observability?
You need host-level capability to discover external dependencies such as azure-diagnostics and microsoft-foundry.
Source text
SKILL.md · MIT
--- name: troubleshoot-observability description: "Coordinate Azure observability troubleshooting for application or agent health, runtime failures, operational latency, telemetry, monitoring, alerts, evidence-backed fixes and recovery. Use for an end-to-end observability investigation or explicit instrumentation, collection or alerting guidance. Not general resource/app/agent creation, model deployment, RBAC, cost or coding. Conceptual questions need no journey; explicit specialist requests stay direct. Actions require applicable approval." license: MIT metadata: author: Microsoft version: "1.0.1" --- # Azure Observability skill plugin Copilot chooses the next useful step; available tools execute approved operations. This is instruction-guided routing, not a diagnostics engine or permission sandbox. ## Current-request intent gate On every user turn, before any journey header, diagram, discovery, onboarding question or read, confirm a current operational observability request. "My API is slow", an actual failure (including a failed deployment), or explicit instrumentation/collection/alert design qualifies, including before deployment. Conceptual questions get direct answers. Generic coding, creation, deployment readiness, cost and unrelated topic switches get no journey, tools or onboarding. Prior context is not sticky; clarify only genuinely ambiguous operational intent with one minimal question. Explicit specialist requests stay direct. Read [intent details](references/intent.md) only for an ambiguous admission decision. ## Standalone availability gate For an admitted task, check availability before reading any cross-skill reference or loading a sibling. Individual installation may omit them. Use available core instructions in this bundle; their use below is conditional. Unknown availability follows the missing-reference fallback. Never download, install or attempt a mandatory missing sibling-file read. Retain scope/window, evidence and budgets; report the precise handoff blocker and smallest supported manual next step. Do not claim an absent specialist executed. Canonical `azure-diagnostics` and `microsoft-foundry` are external dependencies: discover them through the host under [dependency selection](references/canonical-dependencies.md), never by assumed sibling paths. Missing external instructions do not block the local evidence-only affected-path workflow or imply permission to install. For agent/model/tool failures or AI-specific analysis, check the host's exposed skills and load enabled, relevant `microsoft-foundry` instructions before choosing a core fallback. Not bundled does not mean unavailable. Follow the dependency selection checkpoint; unknown discovery is not confirmed absence. ## Select one path Load only the applicable guidance below, not every reference. | Current need | Instructions to select | |---|---| | Find telemetry or resolve missing target/source | Available `connect-observability` | | Broad health | Available `assess-observability-health` | | Completed ranked health, no finding selected | Ask for selection; never auto-select rank 1 or reassess | | Named alert, failure, slow operation or selected finding | [Bounded affected-path investigation](references/investigation/README.md); host-discover canonical `azure-diagnostics` for service-specific expertise or `microsoft-foundry` for AI-specific expertise when needed | | Missing scope/access or a live-read plan | [Scope and permissions](references/scope-permissions.md) | | Specialist handoff or additional capability need | [Selection](references/selection.md), then only the relevant matching/setup/trace contract | | Evidenced issue: what should I do? | [Next actions](references/next-actions.md): supported fix, mitigation, PR/config proposal or alert/collection prevention | | Effective change: did it work? | Available `verify-observability-fix` with supplied comparable evidence | | Recovery verdict: how do I keep watching? | [Monitoring follow-up](references/monitoring-follow-up.md) | | Explicit setup/design | Applicable available specialist; no invented gap or implicit provisioning | ## Boundaries and presentation Reuse confirmed source/schema, UTC window, selected findings and consumed/remaining budgets. Supplied evidence needs no cloud, installation, scripts, jobs or saves. Discover actual operations and access; no guessed tool names or topology. Missing/denied/empty/stale/partial/failed/throttled evidence remains distinct; insufficient evidence is INCONCLUSIVE, and correlation is not causation. Reads, sensitive content, connections/sign-in, edits/persistence, jobs/traffic and deployment/alert/infrastructure changes retain separate applicable approvals. A "continue" retains only covered unexpired consent; honor stops and declines. At journey entry, before a scope/approval question or specialist handoff, read the [indicator](references/journey-indicator.md) and show its fenced Mermaid stepper below actual **Using:** / **Stage:**. Telemetry mapping stays within Detect or Investigate; it does not postpone presentation. Repeat only at meaningful transitions. On reported rendering failure use its text fallback, not an SVG file. Locally inspected guidance uses **Instructions read:** and **host activation unverified**. Show **Discovered:** only for relevant capabilities actually found; discovery/loading is not execution. Apply [next actions](references/next-actions.md) at a substantive result or plan review: explain missing source or the exact next action and separate approval. Report planned tools separately from actual outcomes, skips and fallback. Remediate means options and a reviewed plan, not automatic changes. Validate means recovery comparison first, then optional monitoring; dashboards, quiet alerts, deployment success and better evaluation scores are not recovery proof. No dashboard or monitoring setup is required. Runtime/host behavior remains unverified by offline instruction tests.
© Microsoft · MIT · microsoft/skills