arn-infra-review-change
This skill should be used when the user says "review infra change", "infrastructure review", "review infrastructure", "infra quality review", "arn infra review", "check infra change", "review infrastructure change", "infra change review", "quality check infrastructure", "arn-infra-review-change", "post-deployment review", or wants to perform a comprehensive post-execution quality review of completed infrastructure changes, producing a structured review report with a PASS/WARN/NEEDS_FIXES verdict.
86
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
89%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 excels at trigger term coverage and completeness, providing an extensive list of invocation phrases and clearly stating both what the skill does and when to use it. Its main weakness is that the 'what it does' portion could be more specific about the concrete actions performed during the review (e.g., checking resource configurations, validating security policies, verifying naming conventions). The heavy reliance on listing trigger phrases makes it functional but somewhat front-loaded.
Suggestions
Add more specific concrete actions describing what the review entails, e.g., 'Checks resource configurations, validates security policies, verifies naming conventions, and reviews IAM permissions' to improve specificity.
Restructure to lead with concrete capabilities first, then follow with the 'Use when...' clause containing trigger terms, rather than leading with the trigger phrase list.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'comprehensive post-execution quality review of completed infrastructure changes' and 'structured review report with a PASS/WARN/NEEDS_FIXES verdict,' which names the domain and some actions but doesn't list multiple concrete specific actions (e.g., what exactly is checked, what the report contains beyond the verdict). | 2 / 3 |
Completeness | The description explicitly answers both 'what' (performs a comprehensive post-execution quality review of completed infrastructure changes, producing a structured review report with a PASS/WARN/NEEDS_FIXES verdict) and 'when' (with a detailed list of trigger phrases and the condition 'wants to perform a comprehensive post-execution quality review'). | 3 / 3 |
Trigger Term Quality | The description includes an extensive list of natural trigger phrases users would say, such as 'review infra change', 'infrastructure review', 'check infra change', 'post-deployment review', and several variations. This provides excellent coverage of how users would naturally invoke this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to post-execution infrastructure change quality reviews with a particular verdict format (PASS/WARN/NEEDS_FIXES). The numerous specific trigger phrases like 'arn infra review' and 'arn-infra-review-change' make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, highly actionable skill with excellent workflow clarity and comprehensive error handling. Its main weakness is length—the content is somewhat verbose for what could be a more concise orchestration skill, and the monolithic structure could benefit from splitting presentation templates and agent invocation details into separate reference files. The skill excels at guiding Claude through a complex multi-step review process with clear decision points and user interaction patterns.
Suggestions
Consider extracting the three experience-level presentation formats (Expert/Intermediate/Beginner) and the agent invocation template into separate reference files to reduce the main skill's length and improve progressive disclosure.
Tighten the introductory paragraphs—the first two paragraphs largely restate what the YAML description already conveys and could be condensed to 1-2 sentences.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some verbosity that could be tightened—e.g., the introductory paragraphs explaining what the skill does, the detailed prerequisite checks that repeat patterns from other skills, and the full agent invocation template with extensive comments. Some sections like the experience level derivation chain are necessarily detailed but could be more compact. | 2 / 3 |
Actionability | The skill provides highly concrete, step-by-step guidance with specific glob patterns, exact file paths, structured agent invocation templates, precise JSON file names, and clear presentation formats for each experience level. Every step tells Claude exactly what to do, read, write, and present. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 5 steps with explicit validation checkpoints: checking prerequisites, confirming review scope with the user before proceeding, handling missing phase reports with warnings, and a dedicated Step 5 that branches on verdict with specific remediation paths. The error handling section covers failure modes with recovery actions. | 3 / 3 |
Progressive Disclosure | The skill references external files (experience-derivation.md, report template JSON) appropriately, but the main SKILL.md itself is quite long and monolithic. The agent invocation template, three experience-level presentation formats, and three verdict handling blocks could potentially be split into reference files. No bundle files were provided to verify referenced paths exist. | 2 / 3 |
Total | 10 / 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
- AppsVortex/arness
- Commit
1fe948f
- 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.