Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost optimization, disaster recovery, landing zones, security architecture, serverless design.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly articulates specific capabilities across multiple cloud platforms, provides explicit trigger guidance with both 'Use when' and 'Invoke for' clauses, and includes a rich set of natural keywords users would employ. It uses proper third-person voice throughout and covers a well-defined niche with minimal conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'designs cloud architectures', 'creates migration plans', 'generates cost optimization recommendations', 'produces disaster recovery strategies', and names specific platforms (AWS, Azure, GCP). | 3 / 3 |
Completeness | Clearly answers both 'what' (designs architectures, creates migration plans, generates cost recommendations, produces DR strategies) and 'when' with explicit 'Use when...' and 'Invoke for...' clauses listing specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'cloud architectures', 'migration plans', 'cost optimization', 'disaster recovery', 'AWS', 'Azure', 'GCP', 'Well-Architected Framework', 'landing zones', 'security architecture', 'serverless design', 'multi-cloud'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in multi-cloud architecture across AWS/Azure/GCP. The specific mentions of Well-Architected Framework, landing zones, and serverless design create a distinct identity unlikely to conflict with general coding or DevOps skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable cloud architecture skill with strong workflow validation checkpoints and executable multi-cloud examples. Its main weakness is that the body is heavier than it needs to be—several complete Terraform blocks and CLI examples could be moved to the referenced files (aws.md, cost.md) to keep the top-level skill leaner. The reference table structure is good but the inline content undermines the progressive disclosure pattern.
Suggestions
Move the full Terraform examples (VPC, ASG, IAM) into the respective reference files (references/aws.md) and keep only a brief snippet or summary in the main skill body.
Consolidate the MUST DO / MUST NOT DO lists to remove conceptual overlap (e.g., merge 'implement security by design' and 'skip encryption' into a single constraint).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy—the MUST DO/MUST NOT DO lists overlap conceptually (e.g., 'implement security by design' vs 'skip encryption'), and providing both AWS CLI and Terraform for IAM adds bulk. Some patterns like the full ASG Terraform block are lengthy for a top-level skill file that should delegate to references. | 2 / 3 |
Actionability | The skill provides fully executable CLI commands and complete Terraform configurations across multiple cloud providers. The IAM, VPC, auto-scaling, and cost analysis examples are all copy-paste ready with real service calls and proper syntax. | 3 / 3 |
Workflow Clarity | The 6-step core workflow is clearly sequenced with explicit validation checkpoints after Design, before Migration cutover, after Migration, and after DR testing. Each checkpoint includes concrete verification commands and clear pass/fail criteria (e.g., confirm peering is Active before proceeding). | 3 / 3 |
Progressive Disclosure | The reference table with 'Load When' guidance is well-structured and points to provider-specific files one level deep. However, no bundle files were provided to confirm these references exist, and the inline content is quite heavy—the full Terraform examples for VPC, ASG, and IAM could reasonably live in the referenced files rather than the main skill body. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
5e8b6b8
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.