Well Architected Review logo

Well Architected Review

Community
ricmmartins
well-architected-review

Run a Well-Architected Framework (WAF) review against Azure resources in scope. Use when asked about best practices, architecture review, WAF assessment, or pillar compliance (Reliability, Security, Cost, Operational Excellence, Performance Efficiency).

Overview

Publisherricmmartins
Repositoryazure-sre-agent-skills
Skill namewell-architected-review
Stars
70
Forks
14
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by ricmmartins on GitHub. Read the source before you install it.

Installation

Install the Well Architected Review AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ricmmartins/azure-sre-agent-skills/tree/main/skills/01-well-architected-review
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ricmmartins/azure-sre-agent-skills.git /tmp/azure-sre-agent-skills
mkdir -p .claude/skills
cp -r /tmp/azure-sre-agent-skills/skills/01-well-architected-review .claude/skills/well-architected-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Well Architected Review in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Well Architected Review on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Well Architected Review is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Well-Architected Review

Purpose

Perform a structured assessment of Azure resources against the five pillars of the Microsoft Azure Well-Architected Framework. Produce a scored report with prioritized recommendations.

When to use this skill

  • User asks "are we following best practices?"
  • User asks for a WAF or Well-Architected review
  • User wants to assess architecture quality before a launch or audit
  • Periodic (quarterly) architecture health check

Pillars and checks

1. Reliability

Run the following checks and report findings:

  1. Availability design: Check if critical workloads use availability zones or availability sets
    bash
    az vm list --query "[].{name:name, zones:zones, availabilitySet:availabilitySet.id}" -o table
    az appservice plan list --query "[].{name:name, zoneRedundant:zoneRedundant, sku:sku.name}" -o table
  2. Backup coverage: Verify Recovery Services vaults and backup policies exist for VMs, databases, and file shares
    bash
    az backup vault list -o table
    Then for each vault:
    bash
    az backup item list --vault-name <vault> --resource-group <rg> --backup-management-type AzureIaasVM -o table
  3. Disaster recovery: Check for paired regions, ASR replication, or geo-redundant storage
  4. Health probes: Verify App Service health checks, load balancer probes, and Container Apps health endpoints
  5. Auto-healing: Check if App Service auto-heal rules or AKS pod disruption budgets are configured

2. Security

  1. Identity: Check for managed identities vs. stored credentials
    bash
    az webapp identity show --name <app> --resource-group <rg>
    az ad app list --query "[].{name:displayName, passwordCredentials:passwordCredentials}" -o table
  2. Network isolation: Check for private endpoints, NSGs, and service endpoints
    bash
    az network private-endpoint list -o table
    az network nsg list -o table
  3. Encryption: Verify encryption at rest (storage, databases) and in transit (TLS)
  4. Key management: Check Key Vault usage and key/secret expiration dates
    bash
    az keyvault list -o table
    az keyvault secret list --vault-name <vault> --query "[].{name:name, expires:attributes.expires}" -o table
  5. Defender for Cloud: Check Secure Score and outstanding recommendations

3. Cost Optimization

  1. Rightsizing: Identify underutilized VMs (CPU < 5% average over 14 days)
  2. Orphaned resources: Find unattached disks, unused public IPs, empty resource groups
    bash
    az disk list --query "[?managedBy==null].{name:name, size:diskSizeGb, rg:resourceGroup}" -o table
    az network public-ip list --query "[?ipConfiguration==null].{name:name, rg:resourceGroup}" -o table
  3. Reservations: Check if high-usage resources could benefit from reserved instances
  4. Dev/Test pricing: Verify non-production workloads use Dev/Test subscriptions or B-series VMs
  5. Storage tiers: Check if cool/archive tiers are used for infrequently accessed data

4. Operational Excellence

  1. IaC coverage: Check for ARM/Bicep/Terraform templates in connected repos
  2. Tagging: Verify mandatory tags (environment, owner, cost-center) exist
    bash
    az resource list --query "[?tags.environment==null].{name:name, type:type, rg:resourceGroup}" -o table
  3. Monitoring: Check for alert rules, action groups, and diagnostic settings
    bash
    az monitor metrics alert list -o table
    az monitor diagnostic-settings list --resource <id> -o table
  4. Deployment practices: Check for deployment slots, blue-green, or canary configurations
  5. Automation: Check for runbooks, Logic Apps, or scheduled tasks for routine operations

5. Performance Efficiency

  1. Autoscaling: Verify autoscale rules exist for App Service plans, VMSS, and Container Apps
    bash
    az monitor autoscale list --resource-group <rg> -o table
    Note: az monitor autoscale list requires --resource-group. Iterate over relevant resource groups, or use Azure Resource Graph:
    bash
    az graph query -q "resources | where type == 'microsoft.insights/autoscalesettings'" -o table
  2. Caching: Check for Redis Cache or CDN usage on high-traffic workloads
  3. Database performance: Check DTU/vCore utilization, index recommendations
  4. Content delivery: Verify static assets use CDN or Front Door
  5. Connection pooling: Check for connection string patterns suggesting missing pooling

Scoring model

For each check, assign one of:

  • ✅ Pass — follows best practice
  • ⚠️ Needs attention — partially implemented or at risk
  • ❌ Fail — not implemented, risk exposure

Accepted exceptions (optional)

If the user provides a list of accepted exceptions, do not flag those items. Instead, note them in the report as Accepted Exception with the reason provided.

Example format the user may provide:

CheckReason
1.1 Availability zonesSingle-AZ by design to reduce cost
3.3 Reserved instancesShort-term workload, reservations not applicable
5.5 Connection poolingLegacy app uses persistent connections by design

When exceptions are provided:

  • Skip the flagged checks in scoring
  • List them in a separate "Accepted Exceptions" section at the end of the report
  • Recalculate the overall score excluding excepted checks

Expected output

Report header (mandatory — use this exact format)

Well-Architected Review Report

FieldValue
Subscription(name + ID)
Assessment DateYYYY-MM-DD
Overall ScoreXX%

Summary

A table with pillar scores:

PillarPassNeeds AttentionFailScore
ReliabilityXYZX/(X+Y+Z) %
Security............
Cost Optimization............
Operational Excellence............
Performance Efficiency............
Overallavg %

Detailed findings

For each pillar, list every check with:

  • Status (pass/attention/fail)
  • Evidence (command output or observation)
  • Recommendation (specific action to take)
  • Priority (Critical / High / Medium / Low)
  • Reference link to WAF documentation

Top 5 recommendations

Ordered by impact, with estimated effort (hours/days) for each.

Remediation guidance

For each ❌ or ⚠️ finding, include in the output:

  1. The specific az CLI command to remediate (suggest only — do not execute)
  2. Use GetAzCliHelp to validate the command syntax before suggesting
  3. The official Microsoft Learn documentation link for the remediation

References

Sample output

The following is a redacted example of what the report looks like when run against a subscription.

Well-Architected Review Report

FieldValue
Subscriptioncontoso-prod-001 (a1b2c3d4-e5f6-7890-abcd-ef1234567890)
Assessment Date2026-07-15
Overall Score68%

Summary

PillarPassNeeds AttentionFailScore
Reliability31160%
Security22140%
Cost Optimization41080%
Operational Excellence31160%
Performance Efficiency40180%
Overall165468%

Detailed findings (sample)

Reliability
CheckStatusEvidencePriority
1.1 Availability zones❌ FailVMs vm-web-01, vm-web-02 in rg-app-prod have no zones configuredCritical
1.2 Backup coverage✅ PassRecovery Services vault rsv-prod-eastus protects 4/4 VMs—
1.3 Disaster recovery⚠️ Needs attentionNo ASR replication configured for rg-app-prodHigh
Security
CheckStatusEvidencePriority
2.1 Managed identity✅ PassApp Service app-api-prod uses System-Assigned MI—
2.2 Network isolation❌ FailSQL Server sql-contoso-prod has public endpoint enabledCritical
2.3 Key management⚠️ Needs attention2 secrets in kv-contoso-prod expire within 30 daysHigh

Top 5 recommendations

#RecommendationImpactEffort
1Enable availability zones on production VMsCritical2 hours
2Disable public endpoint on SQL ServerCritical30 min
3Configure ASR replication for rg-app-prodHigh4 hours
4Rotate expiring Key Vault secretsHigh1 hour
5Add autoscale rules to App Service plan asp-prodMedium30 min

Remediation guidance (sample)

bash
# Enable availability zones on VM (redeploy required)
az vm create --name vm-web-01 --resource-group rg-app-prod --zone 1 ...

# Disable public access on SQL Server
az sql server update --name sql-contoso-prod --resource-group rg-data-prod --set publicNetworkAccess="Disabled"

# Add autoscale rule to App Service plan
az monitor autoscale create --resource-group rg-app-prod --resource asp-prod --resource-type Microsoft.Web/serverfarms --min-count 2 --max-count 10 --count 2

Frequently asked questions

What does the Well Architected Review AI skill do?

Run a Well-Architected Framework (WAF) review against Azure resources in scope. Use when asked about best practices, architecture review, WAF assessment, or pillar compliance (Reliability, Security, Cost, Operational Excellence, Performance Efficiency).

Why use Well Architected Review on TypingMind?

Because you install it once and use it with any model. Well Architected Review is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Well Architected Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ricmmartins/azure-sre-agent-skills/tree/main/skills/01-well-architected-review. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Well Architected Review?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Well Architected Review?

As many as you like. As long as a model supports skills, you can use Well Architected Review with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Well Architected Review AI skill free?

Yes. It is published on GitHub by ricmmartins under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇