rails-code-review
Reviews Rails pull requests, focusing on controller/model conventions, migration safety, query performance, and Rails Way compliance. Covers routing, ActiveRecord, security, caching, and background jobs. Use when reviewing existing Rails code for quality.
81
73%
Does it follow best practices?
Impact
91%
1.49xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./rails-code-review/SKILL.mdQuality
Discovery
85%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 description that clearly communicates the skill's purpose and scope. It lists specific Rails-related review areas and includes an explicit 'Use when' clause. The main weakness is that trigger terms could better cover natural user language variations like 'PR review' or 'Ruby on Rails'.
Suggestions
Add natural user-facing trigger terms like 'PR review', 'Ruby on Rails', 'RoR', and 'code review' to improve discoverability when users phrase requests differently.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and areas: controller/model conventions, migration safety, query performance, Rails Way compliance, routing, ActiveRecord, security, caching, and background jobs. | 3 / 3 |
Completeness | Clearly answers both what ('Reviews Rails pull requests, focusing on controller/model conventions, migration safety, query performance, and Rails Way compliance') and when ('Use when reviewing existing Rails code for quality'). | 3 / 3 |
Trigger Term Quality | Includes good domain terms like 'Rails', 'pull requests', 'ActiveRecord', 'migration', 'controller/model', but misses common user variations like 'PR review', 'Ruby on Rails', 'code review', or 'N+1 queries'. The terms are somewhat technical rather than how users naturally phrase requests. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific to Rails pull request reviews with distinct triggers around Rails-specific concepts like ActiveRecord, migration safety, and Rails Way compliance. Unlikely to conflict with generic code review or non-Rails skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid review-oriented skill with excellent workflow clarity including self-review gates, severity categorization, and re-review triggers. Its main weaknesses are the lack of concrete code examples showing good vs. bad patterns (reducing actionability for a code review skill) and moderate verbosity in areas where Claude already understands Rails conventions. The content would benefit from being more example-driven and splitting the detailed review checklist into a reference file.
Suggestions
Add concrete before/after code examples for the most critical checks (e.g., show an N+1 query and its fix with `includes`, show `permit!` vs proper strong params) to increase actionability.
Move the detailed 15-item Review Order into a separate REVIEW_CHECKLIST.md and keep only the Quick Reference table and workflow in SKILL.md to improve progressive disclosure and conciseness.
Trim explanations of standard Rails concepts (e.g., 'RESTful resources/resource', 'skinny controllers') to just the check criteria, since Claude already knows these patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient with tables and structured lists, but includes some content Claude already knows (e.g., explaining what RESTful routing means, basic Rails conventions). The Integration table at the end and some of the Review Order items are somewhat verbose for what could be more tightly expressed. | 2 / 3 |
Actionability | The skill provides concrete checklists, severity levels, and specific anti-patterns to look for, which is good for a review skill. However, it lacks executable examples — no code snippets showing what bad vs. good code looks like for each check, and the guidance remains at the 'check for X' level rather than showing how to identify and fix issues concretely. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced: HARD-GATE defines when to self-review, Review Order provides a numbered sequence, severity levels define categorization, and the Re-Review Loop provides explicit feedback loops with clear triggers for when re-review is mandatory vs. skippable. This is a well-structured multi-step process with validation checkpoints. | 3 / 3 |
Progressive Disclosure | The Integration table references related skills clearly, which is good progressive disclosure. However, the main content is somewhat monolithic — the 15-item Review Order section could benefit from being split into a separate detailed reference file, with SKILL.md serving as a leaner overview pointing to it. | 2 / 3 |
Total | 9 / 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.