rails-architecture-review
Use when reviewing Rails application structure, identifying fat models or controllers, auditing callbacks, concerns, service extraction, domain boundaries, or general Rails architecture decisions. Covers controller orchestration, model responsibilities, and abstraction quality.
92
91%
Does it follow best practices?
Impact
91%
1.49xAverage score across 3 eval scenarios
Passed
No known issues
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.
This is a strong skill description with excellent trigger term coverage and clear 'Use when' guidance specific to Rails architecture review. The main weakness is that the 'what it does' portion is somewhat abstract—it describes topics covered rather than concrete actions or outputs the skill produces. Adding specific deliverables (e.g., 'generates refactoring recommendations', 'produces architecture diagrams') would strengthen it.
Suggestions
Add more concrete action verbs describing outputs, e.g., 'Recommends refactoring strategies for fat models, suggests service object extractions, identifies callback chains that should be simplified.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Rails architecture) and mentions several actions like 'reviewing structure', 'identifying fat models', 'auditing callbacks', 'service extraction', but these read more as topic areas than concrete actions. It lacks specific verbs describing what the skill produces or outputs. | 2 / 3 |
Completeness | The description opens with an explicit 'Use when...' clause that clearly defines when to trigger the skill, and the second sentence covers what it does ('Covers controller orchestration, model responsibilities, and abstraction quality'). Both what and when are addressed explicitly. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a Rails developer would use: 'fat models', 'fat controllers', 'callbacks', 'concerns', 'service extraction', 'domain boundaries', 'Rails architecture', 'controller orchestration', 'model responsibilities', 'abstraction quality'. These are highly natural trigger terms. | 3 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Rails-specific architecture review with highly distinctive terms like 'fat models', 'concerns', 'callbacks', and 'service extraction'. This is unlikely to conflict with general code review or non-Rails skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
92%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 architecture review skill that is concise, actionable, and clearly structured. It provides concrete code examples, severity levels, a clear review workflow, and a structured output format. The only minor weakness is that all content is inline rather than using progressive disclosure to separate the quick reference from detailed examples and common mistakes.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It uses tables for quick reference, avoids explaining what Rails concepts are, and assumes Claude already understands Rails architecture. Every section adds actionable value without padding. | 3 / 3 |
Actionability | Provides concrete Ruby code examples showing both bad and good patterns, specific severity classifications, clear output format instructions, and actionable improvement suggestions. The review order gives a specific sequence to follow, and findings include structured fields (severity, area, risk, improvement). | 3 / 3 |
Workflow Clarity | The review order provides a clear 6-step sequence for conducting the review. The output style section specifies what to include in each finding and what to append at the end. For a review skill (non-destructive), this level of workflow guidance is appropriate and well-structured. | 3 / 3 |
Progressive Disclosure | The Integration table references related skills clearly, which is good. However, the content is moderately long (~130 lines) and some sections like the detailed examples or the common mistakes table could potentially be split into a reference file. The structure is good but everything is inline in one file. | 2 / 3 |
Total | 11 / 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.
- Repository
- igmarin/rails-agent-skills
- Commit
ae8ea63
- 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.