code-reviewer
Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin. Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, generates review reports. Use when reviewing pull requests, analyzing code quality, identifying issues, generating review checklists.
86
86%
Does it follow best practices?
Impact
84%
1.78xAverage score across 6 eval scenarios
Passed
No known issues
Quality
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 a strong skill description that clearly communicates its capabilities, supported languages, and when it should be used. It uses third-person voice consistently, lists concrete actions, and includes an explicit 'Use when...' clause with natural trigger terms. The description is concise yet comprehensive, making it easy for Claude to distinguish this skill from general coding or linting skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Analyzes PRs for complexity and risk', 'checks code quality for SOLID violations and code smells', 'generates review reports'. Also specifies supported languages (TypeScript, JavaScript, Python, Go, Swift, Kotlin). | 3 / 3 |
Completeness | Clearly answers both 'what' (code review automation, analyzes PRs for complexity/risk, checks SOLID violations and code smells, generates reports) and 'when' with an explicit 'Use when...' clause listing trigger scenarios (reviewing pull requests, analyzing code quality, identifying issues, generating review checklists). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'pull requests', 'PRs', 'code quality', 'code review', 'review checklists', 'code smells', 'SOLID violations'. Covers multiple language names users might mention. Good coverage of natural variations. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly carved out niche around code review automation and PR analysis, with distinct triggers like 'pull requests', 'SOLID violations', 'code smells', and 'review checklists'. Unlikely to conflict with general coding skills or linting tools due to the specific focus on review workflows and report generation. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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-structured skill with strong actionability through executable commands and good progressive disclosure via clearly referenced external guides. The main weaknesses are some redundancy in the detection/threshold sections and the lack of an explicit end-to-end workflow showing how the three tools chain together with validation steps between them.
Suggestions
Add a 'Typical Workflow' section showing the recommended sequence: run PR analyzer → run code quality checker → feed both into report generator, with explicit validation checkpoints (e.g., check for critical issues before proceeding).
Remove the duplicated thresholds—either keep the bullet list or the table in the Code Quality Checker section, not both.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and structured lists, but some sections are slightly verbose—e.g., listing every detection item when Claude could infer many of these. The thresholds table duplicates information already stated in the bullet list above it. | 2 / 3 |
Actionability | Provides fully executable bash commands with multiple usage patterns (default, specific branches, JSON output, pre-computed analyses). Commands are copy-paste ready with clear flags and arguments. | 3 / 3 |
Workflow Clarity | The three tools are clearly described individually, and the report generator shows how to chain pre-computed analyses. However, there's no explicit end-to-end workflow showing the sequence (analyze PR → check quality → generate report) with validation checkpoints or error recovery steps. | 2 / 3 |
Progressive Disclosure | Excellent structure with a clear table of contents, concise tool overviews in the main file, and well-signaled one-level-deep references to detailed guides (checklist, coding standards, antipatterns) in separate files. | 3 / 3 |
Total | 10 / 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
- alirezarezvani/claude-skills
- Commit
967fe01
- 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.