CtrlK
BlogDocsLog inGet started
Tessl Logo

aws-cloudformation

Author, validate, and troubleshoot AWS CloudFormation templates. Covers template authoring with secure defaults, pre-deployment validation (cfn-lint, cfn-guard, change sets), and root-cause diagnosis of failed stacks using CloudFormation events and CloudTrail correlation.

73

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

An excellent instruction-oriented skill body: concise, highly actionable with specific commands and properties, clearly sequenced workflows with validation and error-recovery guidance, and a clean one-level-deep progressive disclosure structure where every referenced file exists.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it skips CloudFormation primers and goes straight to actionable defaults and command flags like 'describe-events --filters FailedEvents=true', with every token earning its place rather than padding with explanations Claude already knows.

3 / 3

Actionability

Guidance is concrete and copy-paste ready — specific commands ('--deployment-config {"mode": "EXPRESS"}', 'describe-events --stack-name <name> --filters FailedEvents=true'), exact property names (PublicAccessBlockConfiguration, DeletionPolicy: Retain), and explicit do/don't API distinctions rather than abstract direction.

3 / 3

Workflow Clarity

Multi-step processes are clearly sequenced with validation checkpoints — the three-layer validation pipeline is ordered, the troubleshoot SOP enumerates failed events and classifies fixes, and the decision table maps intent to action with explicit error-recovery guidance ('Examine EVERY failed event', classify template-level vs environment-level).

3 / 3

Progressive Disclosure

Clear overview with well-signaled one-level-deep references — each SOP is linked once from the relevant section (authoring, validation, troubleshooting, express mode), all referenced files exist in references/, and detailed material is kept out of the overview rather than inlined.

3 / 3

Total

12

/

12

Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description naming concrete capabilities and tools, with excellent distinctiveness and natural trigger terms. Its only gap is the absence of an explicit 'Use when...' clause that pins down invocation timing, which caps completeness.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when authoring, validating, or troubleshooting AWS CloudFormation templates' to satisfy the completeness anchor for both what and when.

Consider adding natural-term variations users might say ('CloudFormation stack is failing', 'cfn template') to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Author, validate, and troubleshoot', 'pre-deployment validation (cfn-lint, cfn-guard, change sets)', and 'root-cause diagnosis of failed stacks using CloudFormation events and CloudTrail correlation' — matching the level-3 anchor of multiple specific concrete actions rather than a single domain mention.

3 / 3

Completeness

It clearly answers 'what' (author/validate/troubleshoot) but lacks an explicit 'Use when...' trigger clause stating when Claude should invoke this skill; per the guideline a missing explicit trigger caps completeness at 2.

2 / 3

Trigger Term Quality

Natural user-facing terms are well covered — 'CloudFormation templates', 'validate', 'cfn-lint', 'cfn-guard', 'change sets', 'failed stacks' — the kinds of terms a user would actually say, with common variations present.

3 / 3

Distinctiveness Conflict Risk

The CloudFormation niche with specific tool names (cfn-lint, cfn-guard) is clearly distinct and unlikely to trigger for the wrong skill; it even scopes out CDK, which sharpens the niche.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
aws/agent-toolkit-for-aws
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.