Skip to content
cccskills
Official · MicrosoftFreePublished on GitHubEnglish overview

assess-observability-health

Assess Azure application, resource, or Foundry agent health from supplied evidence or authorized telemetry. The skill ranks observed failures, runtime or tool errors, and latency, while stating evidence gaps in a bounded, read-only report.

OriginalShow the original description

Assess operational Azure application/resource or Foundry-agent health from supplied evidence or authorized telemetry: failed requests, runtime/tool errors and application latency. Return ranked findings and gaps read-only. Not resource creation, general coding fixes or deployment readiness. Direct health requests do not require the coordinator; conceptual health/monitoring questions need no journey.

microsoft/skills3,216 stars(GitHub 3,216 + cccskills 0)
Works withAzure

Run score Not tested

See how to install

Good for

  • Reviewing supplied evidence about an Azure app failure
  • Assessing latency in an operational API
  • Checking Foundry agent errors from authorized telemetry

Overview

What it does

This skill provides one read-only assessment of Azure applications, resources, or Foundry agents using supplied evidence or telemetry within the authorized scope. It checks failed requests, runtime or tool errors, and application latency, then ranks findings with their impact and supporting evidence. The report identifies the assessed target, time window, freshness of information, and observation scope. It also distinguishes missing data from inconsistent data.

When it helps

Use it when an Azure application or agent is experiencing an actual failure or delay and you want to understand the current state from available evidence. An assessment can use supplied safe evidence without connecting to the cloud. For conceptual questions about monitoring, it answers directly without starting an investigation workflow.

Example requests

  • “Assess failed requests and latency for this API.”
  • “Summarize this Foundry agent’s health from the logs I provided.”
  • “Report this Azure app’s health and identify missing evidence.”

Notes

The assessment is read-only. It does not create resources, modify code, deploy, configure alerts, or monitor continuously. Live information requires an authorized tool that is actually available. Generating an optional diagram requires an approved Python 3.9 or later interpreter, but the assessment itself does not.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Document check

AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).

SafetyAre sending data, deleting files, and running commands disclosed?
AGoodIt limits live reads to authorized scope and states that it makes no changes.
Easy setupDoes it need few tools or API keys, and are they documented?
AGoodSupplied evidence needs no Azure access or Python; live-read requirements are stated.

Not counted in the score. Rated by AI (OpenAI Codex) as of Nov 18, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (13)

  • SKILL.md15.5 KB
  • references/application-health.md3.8 KB
  • references/evidence.md3.6 KB
  • references/foundry-agent-health.md12.5 KB
  • references/foundry-agent.md2.6 KB
  • references/health-contract.md4.6 KB
  • references/inline-health-visual.md5.1 KB
  • references/query-guidance.md5.1 KB
  • references/SOURCE-NOTICE.md1.1 KB
  • references/transaction-links.md1.5 KB
  • references/web-api.md1.8 KB
  • scripts/build_appinsights_trace_link.py3.5 KB

1 more file is not shown. View source on GitHub

SKILL.md (original)

Review the instructions the agent will receive before you install.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

agent-framework-azure-ai-py

Official · MicrosoftFreeSummary

Create Python agents on Azure AI Foundry that retain conversation context and use multiple tools. The skill covers code execution, file and web search, external tool connections, streaming responses, and outputs organized into defined fields.

  • Build an agent that retains conversation context
  • Combine code execution with file and web search
  • Connect external tools through MCP
microsoft/skills3.2KUpdated Oct 31, 2026

airunway-aks-setup

Official · MicrosoftFreeSummary

Set up AI Runway on an existing AKS cluster, from checking cluster health and GPU compatibility to installing model serving software, deploying a first AI model, and verifying that it runs.

  • Setting up AI Runway on an existing AKS cluster
  • Checking GPU compatibility before deploying a model
  • Choosing and installing model serving software
microsoft/skills3.2KUpdated Oct 31, 2026

aks-cost-optimization

Official · MicrosoftFreeSummary

Investigate cost efficiency in an existing AKS cluster by examining pod placement, node scaling bottlenecks, and verified storage mappings. It returns evidence for findings such as NAP readiness, bin packing, blocked scale-down, or storage costs.

  • Check whether an AKS cluster is ready for NAP
  • Find bin-packing opportunities in a cluster
  • Investigate why nodes cannot scale down
microsoft/skills3.2KUpdated Oct 31, 2026

aks-gpu-inference

Official · MicrosoftFreeSummary

Investigate GPU and KAITO failures in AKS using read-only evidence. Helps distinguish scheduling problems, memory shortages, workspace readiness issues, and scaling failures, then organizes findings with confidence levels and missing evidence.

  • Investigating GPU pods stuck in Pending
  • Distinguishing container memory shortages from GPU memory failures
  • Investigating a KAITO Workspace that is not ready
microsoft/skills3.2KUpdated Oct 31, 2026

aks-known-issues

Official · MicrosoftFreeSummary

Find documented fixes for known AKS errors by matching the exact error message and required conditions. Get an explanation of the cause, a proposed fix, a Microsoft Learn reference, and read-only verification steps.

  • Look up a documented fix for a specific AKS error
  • Check the cause of a node pool creation failure
  • Review verification steps before changing AKS resources
microsoft/skills3.2KUpdated Oct 31, 2026

aks-network-capture

Official · MicrosoftFreeSummary

Collect bounded packet captures from AKS nodes or pods alongside Azure network settings. Use the captured traffic as evidence when investigating where packets are lost, after initial checks that do not change the environment.

  • Collect packet captures from an AKS node
  • Gather evidence of where packets are lost
  • Retrieve captures alongside Azure network settings
microsoft/skills3.2KUpdated Oct 31, 2026

See all skills by microsoft

Report a problem with this skill