cfn-behavior-validator

Creates test stacks, analyzes CloudFormation events, compares actual vs documented update behavior, then confirms whether a resource property change triggers replacement rather than an in-place update. Use when: testing if a CFN property change causes resource replacement; investigating stack update behavior, "Update requires" documentation accuracy; validating whether a workaround (e.g. hash-based logical IDs) is actually necessary; questioning UpdateRequiresReplacement behavior for immutable properties; needing empirical evidence before an architectural decision involving CDK/CloudFormation stack updates.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

70%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.

A well-structured, highly actionable body with an exemplary validation-gated workflow, dragged down by redundant explanation and a broken progressive-disclosure story: the body cites a nonexistent EXAMPLES.md while the real reference guide sits unlinked in references/. Fixing the file pointer and de-duplicating the ENI material would lift the two weakest dimensions.

Suggestions

Point the walkthrough reference at the real file (e.g. 'See references/sns-testing-guide.md for a full SNS email subscription walkthrough') instead of the nonexistent EXAMPLES.md, so the 335-line guide is discoverable.

Remove the duplicated Lambda VPC/ENI-churn explanation — keep it in the 'No interruption' anti-pattern and drop the near-verbatim repeat in Mindset.

Replace the placeholder TypeScript stack skeleton with a minimal runnable example (a real resource driven by tryGetContext) so the design step is copy-paste executable like the bash steps.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the Lambda VPC/ENI-churn example appears nearly verbatim in both Mindset and the 'No interruption' anti-pattern, and the 'docs are hand-maintained and drift' idea is repeated across Purpose, Mindset, and the first anti-pattern. Fits 'could be tightened'; not 2 because the anti-pattern WHYs are genuine non-obvious domain gotchas rather than padding.	3 / 5
Actionability	Concrete executable commands throughout — a full describe-stack-events query with --query, continue-update-rollback, and a jq normalization pipeline — but the TypeScript test-stack snippet is a placeholder skeleton ('Add only the resource under test') rather than runnable code. Matches 'mostly executable guidance with minor gaps'; not 5 because of that non-executable skeleton.	4 / 5
Workflow Clarity	The four-step workflow is clearly sequenced and backed by an explicit 'Validation gates' block (initial deploy fails → stop and fix; unexpected events → abort; ambiguous → repeat), giving feedback loops that satisfy the destructive-operation cap. Not 4: checkpoints are explicit, not implicit.	5 / 5
Progressive Disclosure	The scripts table is well-signaled, but the body points to 'EXAMPLES.md in this skill directory' which does not exist, while the actual bundle file references/sns-testing-guide.md (a 335-line SNS walkthrough, i.e. that exact content) is never referenced from SKILL.md. A dangling reference plus an orphaned reference file is more than the 'minor organization gaps' of a 4; the structure is otherwise too good for a 2.	3 / 5
	Total	15 / 20 Passed

Description

96%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.

A strong description: concrete action list, dense natural trigger vocabulary including synonyms, and an explicit multi-clause 'Use when:' block. The only weakness is mild breadth in the stack-update triggers that could pull users of a general CDK skill.

Dimension	Reasoning	Score
Specificity	Lists four concrete, distinct actions ('Creates test stacks, analyzes CloudFormation events, compares actual vs documented update behavior, then confirms whether a resource property change triggers replacement'), comprehensively covering the skill's job. Not 4: there are no meaningful gaps in the capability coverage.	5 / 5
Completeness	Explicitly answers both 'what' (first sentence enumerating the actions) and 'when' with a five-clause 'Use when:' block of concrete trigger phrases. Not 4: the 'when' guidance is already fully explicit and specific, not merely present.	5 / 5
Trigger Term Quality	Covers the natural terms users would say — 'CloudFormation' with its synonym 'CFN', 'CDK', 'resource replacement', 'stack update', 'Update requires', 'workaround' — matching the comprehensive-synonyms anchor. Not 4: no common variation or synonym for this domain is missing.	5 / 5
Distinctiveness Conflict Risk	The validation framing ('testing if', 'validating whether', 'needing empirical evidence') carves a clear niche, but 'investigating stack update behavior' and 'CDK/CloudFormation stack updates' overlap with a general AWS CDK skill. Fits the 'mostly distinct; minor overlap risk with closely related skills' anchor better than the minimal-conflict anchor.	4 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pantheon-org/tekhne
Path: skills/infrastructure/cfn/behavior-validator/SKILL.md
Commit: a1083f4

Reviewed: 3 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.