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.
47
20%
Does it follow best practices?
Impact
97%
1.00xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/cloud-architect/SKILL.mdQuality
Discovery
32%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 reads more like a resume headline than a skill selection guide. While it names relevant technologies and domains, it lacks concrete actions Claude would perform and entirely omits trigger guidance ('Use when...'). The first-person framing as 'Expert cloud architect' uses an identity claim rather than describing capabilities in third person.
Suggestions
Add an explicit 'Use when...' clause listing trigger scenarios, e.g., 'Use when the user asks about cloud infrastructure design, Terraform modules, cloud cost optimization, or multi-cloud deployment strategies.'
Replace the identity claim ('Expert cloud architect specializing in...') with concrete action verbs in third person, e.g., 'Designs multi-cloud infrastructure across AWS/Azure/GCP, generates Terraform/OpenTofu/CDK configurations, analyzes cloud spending for cost optimization.'
Include common natural language variations users might say, such as 'cloud costs', 'infrastructure as code', '.tf files', 'cloud migration', 'deploy to AWS', 'serverless architecture'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names domains (AWS/Azure/GCP, Terraform/OpenTofu/CDK, FinOps) and some general actions (infrastructure design, cost optimization), but doesn't list specific concrete actions like 'generate Terraform modules', 'create cost reports', or 'design VPC architectures'. The terms are more category labels than actionable capabilities. | 2 / 3 |
Completeness | Describes what the skill covers at a high level but completely lacks any 'Use when...' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause should cap completeness at 2, and since the 'what' is also somewhat vague (no concrete actions), this falls to 1. | 1 / 3 |
Trigger Term Quality | Includes relevant technical keywords like AWS, Azure, GCP, Terraform, OpenTofu, CDK, FinOps, and multi-cloud that users might naturally mention. However, it misses common variations and natural phrases users would say like 'cloud costs', 'infrastructure as code', 'deploy to cloud', 'cloud migration', 'serverless', or file extensions like '.tf'. | 2 / 3 |
Distinctiveness Conflict Risk | The multi-cloud and IaC focus provides some distinctiveness, but terms like 'cloud architect' and 'modern architectural patterns' are broad enough to overlap with general DevOps, infrastructure, or architecture skills. The combination of specific tool names (Terraform, CDK) helps somewhat but 'architectural patterns' is very generic. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads like a persona description or job posting rather than actionable instructions. It extensively lists technologies and concepts Claude already knows, provides no executable code or concrete commands, and lacks any meaningful workflow with validation steps. The content would need a fundamental restructuring to be useful—replacing capability lists with specific patterns, code templates, and decision frameworks.
Suggestions
Replace the extensive capability/technology lists with concrete, executable examples: Terraform module templates, CDK snippets, cost estimation commands, and architecture decision records.
Add specific multi-step workflows with validation checkpoints for common tasks like 'deploy multi-region infrastructure' or 'migrate to Kubernetes', including verification commands at each step.
Remove the 'Behavioral Traits', 'Knowledge Base', and 'Capabilities' catalog sections entirely—Claude already knows these technologies. Replace with decision trees (e.g., 'when to use serverless vs containers') and concrete patterns.
Expand the reference to 'resources/implementation-playbook.md' by adding more targeted references for specific domains (e.g., cost-optimization-checklist.md, terraform-patterns.md) with clear descriptions of what each contains.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive lists of technologies, services, and concepts that Claude already knows. The 'Capabilities' section is essentially a catalog of cloud services and tools that adds no actionable value. 'Behavioral Traits' and 'Knowledge Base' sections describe Claude's persona rather than providing instructions. Most of this content is padding. | 1 / 3 |
Actionability | No concrete code examples, commands, or executable guidance anywhere. The entire skill is abstract descriptions, capability lists, and vague instructions like 'Apply relevant best practices and validate outcomes.' The 'Response Approach' is a generic checklist with no specifics. No Terraform snippets, no CLI commands, no architecture diagram templates. | 1 / 3 |
Workflow Clarity | The 'Response Approach' lists 8 high-level steps but they are vague and lack validation checkpoints. There are no concrete workflows for any cloud architecture task—no deployment sequences, no validation steps, no error recovery paths. For a skill involving infrastructure changes (destructive operations), the complete absence of verification steps is a significant gap. | 1 / 3 |
Progressive Disclosure | There is a reference to 'resources/implementation-playbook.md' for detailed examples, which shows some awareness of progressive disclosure. However, the main file itself is a monolithic wall of bullet-pointed lists that could be dramatically condensed, and there's only one external reference with no clear signaling of what it contains. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
90%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 | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
6a07b83
- 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.