multi-cloud-architecture

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

1.07x

Quality

—

Does it follow best practices?

Impact

99%

1.07x

Average score across 3 eval scenarios

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.

The body is a well-organized but verbose reference dump that explains cloud concepts Claude already knows and provides descriptive rather than executable guidance. It signals reference files that are missing while duplicating their content inline, and its migration workflow lacks validation checkpoints.

Suggestions

Move the compute/storage/database comparison tables and cost-factor lists into the referenced files (references/service-comparison.md, references/multi-cloud-patterns.md) and actually create them, keeping SKILL.md as a lean overview.

Add validation/verification checkpoints to the Migration Strategy phases (e.g., verify pilot results before migration, validate functionality after each incremental migration) to create feedback loops for this risky operation.

Replace or supplement the ASCII diagram and descriptive pattern bullets with concrete, executable guidance (e.g., example Terraform snippets, IaC commands, or specific decision-criteria checks) so the skill instructs rather than only describes.

Dimension	Reasoning	Score
Conciseness	The ~180-line body is padded with comparison tables and enumerated lists of general cloud reference knowledge Claude largely already knows, and content that should live in reference files is duplicated inline rather than tightened.	2 / 3
Actionability	Gives concrete named services and pattern descriptions but no executable code or commands — the only code block is an ASCII diagram, and guidance like 'Use Kubernetes for compute' is descriptive rather than instructive.	2 / 3
Workflow Clarity	The Migration Strategy offers a clear 4-phase sequence but lacks any validation checkpoints, verification steps, or feedback loops for a risky multi-step operation, which caps it at the middle level.	2 / 3
Progressive Disclosure	References are signaled one level deep in-text and in a Reference Files section, but the referenced files (references/service-comparison.md, references/multi-cloud-patterns.md) do not exist and the large reference content is kept inline rather than split out.	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.

The description is strong: it concisely states concrete capabilities across the three providers and gives an explicit 'Use when' trigger clause with natural keywords. It is distinctive and unlikely to conflict with adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Design multi-cloud architectures', 'select and integrate services across AWS, Azure, and GCP', 'leveraging best-of-breed services') rather than vague language, matching the anchor for several specific actions.	3 / 3
Completeness	Explicitly answers what ('Design multi-cloud architectures... select and integrate services') and when ('Use when building multi-cloud systems, avoiding vendor lock-in, or leveraging best-of-breed services'), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Includes natural terms users would say when needing this skill ('multi-cloud', 'vendor lock-in', 'best-of-breed', 'AWS, Azure, and GCP'), with good coverage of relevant variations.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (cross-provider multi-cloud architecture) with distinct triggers unlikely to fire for single-cloud skills, so it is unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Commit: abece4a

Reviewed: 4 days 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.