pantheon-ai/cfn-template-compare
Compares deployed CloudFormation templates with locally synthesized CDK templates to detect drift, validate changes, and ensure consistency before deployment. Use when the user wants to compare CDK output with a deployed stack, check for infrastructure drift, run a pre-deployment validation, audit IAM or security changes, investigate a failing deployment, or perform a 'cdk diff'-style review. Triggered by phrases like 'compare templates', 'check for drift', 'cfn drift', 'stack comparison', 'infrastructure drift detection', 'safe to deploy', or 'what changed in my CDK stack'.
Does it follow best practices?
Evaluation — 100%
↑ 1.09xAgent success when using this tile
Validation for skill structure
Discovery
100%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 is an exemplary skill description that excels across all dimensions. It provides specific concrete actions, comprehensive trigger terms that match natural developer language, explicit 'Use when' and 'Triggered by' clauses, and a clearly defined niche in the CDK/CloudFormation infrastructure space. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Compares deployed CloudFormation templates with locally synthesized CDK templates', 'detect drift', 'validate changes', 'ensure consistency before deployment'. Also specifies concrete use cases like 'audit IAM or security changes' and 'investigate a failing deployment'. | 3 / 3 |
Completeness | Clearly answers both what (compares CloudFormation templates with CDK templates to detect drift and validate changes) AND when (explicit 'Use when...' clause with six specific scenarios, plus a 'Triggered by phrases like...' section with seven trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'compare templates', 'check for drift', 'cfn drift', 'stack comparison', 'infrastructure drift detection', 'safe to deploy', 'what changed in my CDK stack', 'cdk diff'. These are phrases developers naturally use when working with CDK/CloudFormation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: specifically targets CloudFormation/CDK template comparison and drift detection. The combination of 'CDK', 'CloudFormation', 'drift', and 'stack comparison' creates a unique fingerprint unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary skill that demonstrates all best practices: concise executable commands, clear multi-step workflow with validation checkpoints, risk categorization table, error recovery guidance, and appropriate references to external resources. The hierarchical analysis approach and artifact preservation for audit trails show thoughtful design for real-world usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing executable commands without explaining what CloudFormation, CDK, or jq are. Every section serves a purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Fully executable bash commands throughout with specific flags, file paths, and jq queries. Copy-paste ready with clear variable placeholders like <stack-name> and <region>. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with explicit validation checkpoints (credential check, stack existence, JSON validation). Includes error recovery table and clear feedback loops with '→ If this fails' guidance. | 3 / 3 |
Progressive Disclosure | Well-structured with Quick Start for immediate use, detailed workflow steps, and clear references to external files (scripts, examples, CI config) at the end. Content is appropriately split without deep nesting. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Install with Tessl CLI
npx tessl i pantheon-ai/cfn-template-compare@0.1.1Reviewed
Table of Contents