aws-skills
AWS development with infrastructure automation and cloud architecture patterns
34
18%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-aws-skills/SKILL.mdQuality
Discovery
22%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is too vague and abstract to effectively guide skill selection. It names the domain (AWS) but fails to list concrete actions, specific AWS services, or any trigger guidance. Without a 'Use when...' clause and specific capabilities, Claude would struggle to reliably select this skill over other cloud or infrastructure-related skills.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about AWS services, CloudFormation templates, CDK stacks, Lambda functions, or cloud deployment.'
List specific concrete actions such as 'Creates CloudFormation/CDK templates, configures IAM policies, sets up VPCs, deploys Lambda functions, manages S3 buckets.'
Include natural trigger terms users would say, such as specific AWS service names (EC2, S3, Lambda, RDS, DynamoDB), file types (.yaml, .json for templates), and common phrases like 'deploy to AWS', 'serverless', 'cloud infrastructure'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'infrastructure automation' and 'cloud architecture patterns' without listing any concrete actions. It doesn't specify what the skill actually does (e.g., deploy CloudFormation stacks, configure Lambda functions, set up VPCs). | 1 / 3 |
Completeness | The description partially addresses 'what' (AWS development, infrastructure automation) but in very vague terms, and completely lacks any 'when' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it down to 1. | 1 / 3 |
Trigger Term Quality | 'AWS' is a strong natural keyword users would say, and 'infrastructure automation' and 'cloud architecture' are somewhat relevant. However, it's missing common variations like 'CloudFormation', 'CDK', 'Terraform', 'Lambda', 'S3', 'EC2', 'deploy', or 'serverless' that users would naturally mention. | 2 / 3 |
Distinctiveness Conflict Risk | 'AWS' provides some specificity that distinguishes it from generic coding or DevOps skills, but 'infrastructure automation' and 'cloud architecture patterns' are broad enough to overlap with Terraform, Kubernetes, or general DevOps skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially an empty shell — it restates its own description three times and provides no actual guidance, code, patterns, or actionable content for AWS development or infrastructure automation. The limitations section is generic boilerplate. It fails on every dimension because there is no substantive content to evaluate.
Suggestions
Add concrete, executable examples for core AWS tasks (e.g., CDK stack definitions, CloudFormation templates, CLI commands for common operations).
Define specific workflows with validation steps for infrastructure operations (e.g., deploy → validate → rollback pattern with explicit commands).
Replace the repeated description with actual architecture patterns, best practices, and tool-specific guidance (e.g., CDK vs SAM vs Terraform recommendations with code).
If detailed content exists in the linked repository, summarize key patterns inline and create well-signposted references to specific sub-documents rather than a single opaque repository link.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is short but entirely vacuous — it repeats the description multiple times without adding any substance. While not verbose in absolute terms, every token is wasted because none provide actionable information. | 2 / 3 |
Actionability | There are no concrete commands, code examples, architecture patterns, or specific AWS guidance whatsoever. The entire body is vague meta-description with zero executable or instructive content. | 1 / 3 |
Workflow Clarity | No workflow, steps, or processes are described. There is no sequence, no validation checkpoints, and no guidance on how to actually perform any AWS task. | 1 / 3 |
Progressive Disclosure | The only reference is a link to a source repository with no description of what it contains. There is no structured navigation, no signposted sub-documents, and no content hierarchy beyond boilerplate headings. | 1 / 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
- boisenoise/skills-collections
- Commit
431bfad
- 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.