multi-cloud-architecture

Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, GCP, and OCI. Use when building multi-cloud systems, avoiding vendor lock-in, or leveraging best-of-breed services from multiple providers.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized but somewhat surface-level overview: it lists patterns, service mappings, and migration phases but lacks a real decision framework, executable guidance, and validation steps. The references exist and are signaled, though their content is redundantly inlined.

Suggestions

Replace the inlined comparison tables and pattern lists with concise summaries and delegate the full detail to the existing references, removing the duplication.

Provide an actual decision procedure (e.g., a criteria matrix or ordered decision rules) that operationalizes the promised 'decision framework' for selecting services across providers.

Add explicit validation/verification checkpoints to the Migration Strategy phases (e.g., test/validate after Pilot, dual-run verification before cutover) to support the high-risk multi-step process.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean tables and bullets, but it duplicates substantial content that also lives in the reference files (service-comparison tables and multi-cloud patterns are restated inline), so it is efficient yet could be tightened rather than fully lean.	2 / 3
Actionability	It names concrete services, patterns, and tools (Terraform/OpenTofu, Kafka, Istio), but offers no executable code or commands and the promised 'decision framework' is never realized as a structured decision procedure, leaving guidance concrete but incomplete.	2 / 3
Workflow Clarity	The Migration Strategy section has a clear four-phase sequence, but the phases are descriptive bullets with no validation checkpoints or feedback loops; for a high-risk multi-step operation, missing verification caps the score at 2.	2 / 3
Progressive Disclosure	Two references are clearly signaled inline and both exist one level deep, but the SKILL.md body duplicates the comparison tables and patterns rather than delegating them, so content that should be separate remains inline.	2 / 3
	Total	8 / 12 Passed

Description

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.

A strong, third-person description that concisely states what the skill does and when to use it with natural trigger phrases. It is specific, distinctive, and complete with an explicit 'Use when' clause.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Design', 'select and integrate services') plus a 'decision framework' and the four specific providers (AWS, Azure, GCP, OCI), matching the 'lists multiple specific concrete actions' anchor; it is not merely a domain-plus-some-actions level.	3 / 3
Completeness	It explicitly answers WHAT (design multi-cloud architectures / select and integrate services) and WHEN via an explicit 'Use when...' clause, satisfying the 'both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	The 'Use when building multi-cloud systems, avoiding vendor lock-in, or leveraging best-of-breed services' clause covers natural terms a user would actually say, matching the good-coverage anchor rather than the partial-coverage level.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow and specific (multi-cloud architecture across these four providers) with distinctive triggers (vendor lock-in, best-of-breed), making conflict with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wshobson/agents
Commit: 5cc2549

Reviewed: about 2 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

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.