CtrlK
BlogDocsLog inGet started
Tessl Logo

multi-cloud-architecture

Decision framework and patterns for architecting applications across AWS, Azure, and GCP.

50

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/multi-cloud-architecture/SKILL.md

The canonical home for this skill is multi-cloud-architecture in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

50%Weight 40%Scale 1-5

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

The content is a well-sectioned reference with useful cross-cloud comparison tables and a clear migration phase sequence, but it relies on generic best-practice lists and vague instructions, includes no executable code or commands, lacks explicit validation checkpoints in its migration workflow, and points to reference files that do not exist. Tightening the generic sections, adding validation loops, and creating the referenced files would raise the score.

Suggestions

Create the referenced files (references/service-comparison.md, references/multi-cloud-patterns.md, resources/implementation-playbook.md) or remove the dangling references, moving the inlined comparison tables into them.

Add explicit validation checkpoints to the Migration Strategy, e.g. a 'Validate pilot before proceeding' gate with a fix-and-retry loop, to satisfy the destructive/batch workflow cap.

Trim the generic Best Practices and Instructions boilerplate, and add at least one concrete executable artifact (e.g. a Terraform/IaC snippet or a service-selection decision command) to improve actionability.

DimensionReasoningScore

Conciseness

The body avoids 'what is a cloud' padding and the comparison tables are dense reference data, but the generic Best Practices list ('Use infrastructure as code', 'Implement CI/CD pipelines') and the vague Instructions boilerplate ('Clarify goals...', 'Apply relevant best practices') restate knowledge Claude already has; not a 4 because those padded/generic sections are more than minor, not a 2 because there is no severe verbosity.

3 / 5

Actionability

The service-comparison tables and named abstraction tools (Terraform/OpenTofu, Kafka, Istio) give some concrete reference, but there is no executable code, Terraform, or commands and the patterns/migration steps are high-level hints; not a 4 because nothing is copy-paste executable, not a 2 because the tables are genuinely concrete guidance for service selection.

3 / 5

Workflow Clarity

The Migration Strategy lays out four sequenced phases (Assessment, Pilot, Migration, Optimization) with sub-steps, but validation is only implicit ('Test thoroughly', 'Validate functionality') with no validate→fix→retry checkpoints; per the destructive/batch cap it cannot exceed 3, and not a 2 because a clear sequence does exist.

3 / 5

Progressive Disclosure

Section headers and explicit 'See references/...' signals plus a Reference Files section give structure, but the referenced files (resources/implementation-playbook.md, references/service-comparison.md, references/multi-cloud-patterns.md) do not exist on disk, and the comparison/pattern detail that should live in them is inlined; not a 4 because the references are dangling and content is not actually split, not a 2 because organization and signaling are present.

3 / 5

Total

12

/

20

Passed

Description

61%Weight 40%Scale 1-5

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 cleanly names the multi-cloud domain and the three target providers, giving it solid trigger-term quality and distinctiveness, but it lacks any explicit 'Use when...' trigger clause and its actions are framed abstractly rather than concretely. Adding a trigger clause and concrete verbs would lift completeness and specificity.

Suggestions

Append an explicit trigger clause, e.g. 'Use when designing multi-cloud architectures, migrating workloads between AWS/Azure/GCP, or selecting cloud services for a workload.'

Replace abstract framing ('Decision framework and patterns') with concrete verbs such as 'Compare, select, and architect cloud services across AWS, Azure, and GCP'.

Add natural synonyms users say ('multi-cloud', 'cloud migration', 'hybrid cloud') to broaden trigger coverage.

DimensionReasoningScore

Specificity

Quotes "architecting applications across AWS, Azure, and GCP" and "Decision framework and patterns" name the domain plus 1-2 actions, but the 'framework and patterns' framing is abstract rather than concrete verbs like 'select services' or 'design failover'; not a 4 because coverage is not comprehensive, not a 2 because a real action (architecting across the three clouds) is named.

3 / 5

Completeness

It gives a clear 'what' ("Decision framework and patterns for architecting applications across AWS, Azure, and GCP") but no 'Use when...' clause or equivalent trigger guidance, so per the missing-trigger cap it cannot exceed 3; not a 4 because the 'when' is entirely absent rather than merely weak.

3 / 5

Trigger Term Quality

"AWS, Azure, and GCP" and "architecting applications" are natural phrases users say when they need this skill, giving good keyword coverage; not a 5 because common synonyms like 'multi-cloud', 'cloud migration', and 'hybrid cloud' are absent, not a 3 because the named providers alone exceed 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

The multi-cloud scope with all three named providers carves a clear niche distinct from single-cloud skills; not a 5 because related skills (cost-optimization, hybrid-cloud-networking) create minor overlap risk, not a 3 because the three-provider framing is more specific than 'somewhat specific'.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.