cloud-architect

Expert cloud architect specializing in AWS/Azure/GCP multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost optimization, and modern architectural patterns.

Install with Tessl CLI

npx tessl i github:sickn33/antigravity-awesome-skills --skill cloud-architect

What are skills?

1.00x

Quality

27%

Does it follow best practices?

Impact

97%

1.00x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/cloud-architect/SKILL.md

SKILL.md

Review

Evals

Discovery

47%

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 contains strong technical keywords that users would naturally use, but fails to provide explicit trigger guidance ('Use when...') and relies on role-based framing rather than concrete actions. The lack of a 'when' clause significantly limits Claude's ability to know when to select this skill over others.

Suggestions

Add an explicit 'Use when...' clause specifying triggers like 'when the user asks about cloud infrastructure, deploying to AWS/Azure/GCP, writing Terraform code, or optimizing cloud costs'

Replace role-based framing ('Expert cloud architect specializing in') with action-based language listing what the skill does (e.g., 'Designs multi-cloud infrastructure, writes Terraform/CDK code, analyzes cloud costs')

Add common user phrasings like 'cloud deployment', 'infrastructure as code', 'cloud billing', 'resource provisioning' to improve trigger coverage

Dimension	Reasoning	Score
Specificity	Names domains (AWS/Azure/GCP, Terraform/OpenTofu/CDK) and general action areas (infrastructure design, cost optimization), but uses role-based framing ('Expert cloud architect') rather than listing concrete actions the skill performs.	2 / 3
Completeness	Describes 'what' at a high level (cloud architecture, IaC, cost optimization) but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Good coverage of natural terms users would say: 'AWS', 'Azure', 'GCP', 'multi-cloud', 'Terraform', 'OpenTofu', 'CDK', 'IaC', 'FinOps', 'cost optimization' are all terms users naturally use when seeking cloud architecture help.	3 / 3
Distinctiveness Conflict Risk	The multi-cloud and specific tool mentions (Terraform/CDK) provide some distinctiveness, but 'infrastructure design' and 'architectural patterns' are broad enough to potentially overlap with other DevOps or architecture skills.	2 / 3
	Total	8 / 12 Passed

Implementation

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

This skill reads as a capability description or persona definition rather than actionable guidance. It extensively lists cloud technologies and concepts Claude already knows without providing concrete implementations, code examples, or clear workflows. The content would benefit from being drastically reduced and replaced with specific, executable guidance for common cloud architecture tasks.

Suggestions

Replace the extensive capability lists with 2-3 concrete, executable examples (e.g., a complete Terraform module for a common pattern, a cost optimization checklist with specific commands)

Add validation checkpoints and feedback loops for multi-step processes like infrastructure deployment or migration workflows

Remove the 'Capabilities' and 'Knowledge Base' sections entirely - Claude already knows these technologies; instead focus on project-specific patterns or constraints

Transform 'Example Interactions' into actual worked examples with code, architecture diagrams (as ASCII), and specific implementation steps

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive lists of technologies Claude already knows. The 'Capabilities' section reads like a resume or marketing document, listing every possible cloud service without providing actionable guidance. Most content explains concepts Claude is already familiar with.	1 / 3
Actionability	No concrete code examples, commands, or executable guidance. The entire skill is abstract descriptions and bullet-point lists of technologies. 'Example Interactions' are just prompts, not actual implementations or step-by-step instructions.	1 / 3
Workflow Clarity	The 'Response Approach' section lists generic steps without validation checkpoints or concrete sequences. No feedback loops, no verification steps, and no clear workflow for any specific cloud architecture task. The instruction to 'open resources/implementation-playbook.md' suggests content exists elsewhere but provides no workflow here.	1 / 3
Progressive Disclosure	References an external file (resources/implementation-playbook.md) for detailed examples, which is appropriate. However, the main content is a monolithic wall of bullet points that could be better organized, and the reference is buried in the instructions rather than clearly signaled in a navigation section.	2 / 3
	Total	5 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Reviewed: about 18 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.