Download skills/aws-well-architected-review/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
Where does aws-well-architected-review live?
The publisher keeps it at https://github.com/github/awesome-copilot.
Which agents can use aws-well-architected-review?
Claude, Cursor, and Codex can read a SKILL.md you add from the publisher's repository.
Perform an AWS Well-Architected Framework review of the current workload IaC and architecture, generating findings and GitHub issues for improvements.
name: aws-well-architected-review
description: 'Perform an AWS Well-Architected Framework review of the current workload IaC and architecture, generating findings and GitHub issues for improvements.'
AWS Well-Architected Review
This workflow performs a structured AWS Well-Architected Framework (WAF) review against your workload's IaC files and deployed infrastructure. It identifies risks across all 6 WAF pillars and creates GitHub issues to track remediation.
Prerequisites
AWS CLI configured and authenticated
IaC files present in the repository (Terraform, CloudFormation, CDK, or SAM)
VPC Endpoints for S3/DynamoDB to avoid NAT Gateway charges
gp2 EBS volumes migrated to gp3 (same performance, 20% cheaper)
Development/test environments have auto-shutdown schedules
AWS Budgets and Cost Anomaly Detection configured
Unattached EBS volumes and idle EC2 instances identified
Pillar 6: Sustainability
Graviton/ARM instances selected where available
Serverless/managed services preferred over always-on EC2
S3 lifecycle policies reduce unnecessary long-term data storage
Auto Scaling configured to avoid over-provisioning
Region selection considers AWS renewable energy commitments
Step 4: Risk Classification
For each finding, classify:
High Risk: Security vulnerability, single point of failure, no backup/recovery
Medium Risk: Suboptimal reliability, cost inefficiency, performance concern
Low Risk: Best practice deviation, minor optimization opportunity
Step 5: User Confirmation
ποΈ AWS Well-Architected Review Summary
π Review Results:
β’ IaC Files Analyzed: X
β’ AWS Services Identified: Y
β’ Total Findings: Z
β’ High Risk: A (immediate action required)
β’ Medium Risk: B (should address soon)
β’ Low Risk: C (nice to have)
π΄ Top High Risk Findings:
1. [Pillar]: [Finding] β [Why it matters]
2. [Pillar]: [Finding] β [Why it matters]
π‘ This will create Z individual GitHub issues + 1 EPIC issue.
β Proceed with creating GitHub issues? (y/n)
Step 6: Create Individual Finding Issues
Label with "well-architected" and the pillar name (e.g., "security", "reliability").
Title: [EPIC] AWS Well-Architected Review β X findings across 6 pillars
Body: Executive summary with pillar breakdown table (finding counts by pillar and risk level), Mermaid architecture diagram, prioritized checklist linking all individual issues (High β Medium β Low), and success criteria:
All High-risk findings resolved
Medium findings have accepted mitigation plans
No regression in existing CloudWatch alarms or Config rules
Error Handling
No IaC Files Found: Limit review to live resource discovery via AWS CLI and note the gap
Insufficient AWS Permissions: List required read-only permissions for the review
GitHub Creation Failure: Output all findings as formatted markdown to console
Success Criteria
β All 6 WAF pillars reviewed against IaC and live infrastructure
β All findings classified by risk level and pillar
β Actionable remediation steps with IaC examples for each finding
β GitHub issues created for team tracking
β Architecture diagram generated for EPIC context
β AWS documentation references included
How do I install aws-well-architected-review?
Download skills/aws-well-architected-review/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
Where does aws-well-architected-review live?
The publisher keeps it at https://github.com/github/awesome-copilot.
Which agents can use aws-well-architected-review?
Claude, Cursor, and Codex can read a SKILL.md you add from the publisher's repository.