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.
Install with Tessl CLI
npx tessl i github:alirezarezvani/claude-skills --skill code-reviewer89
Quality
93%
Does it follow best practices?
Impact
84%
1.78xAverage score across 6 eval scenarios
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 well-crafted skill description that excels across all dimensions. It provides specific capabilities (PR analysis, SOLID violation detection, report generation), covers multiple programming languages, and includes an explicit 'Use when...' clause with natural trigger terms. The description is concise yet comprehensive, making it easy for Claude to select this skill appropriately.
| 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, PR analysis, quality checks, report generation) AND when with explicit 'Use when...' clause covering reviewing PRs, analyzing quality, identifying issues, and generating checklists. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'pull requests', 'PRs', 'code quality', 'code review', 'review checklists', plus specific language names. These are terms developers naturally use when requesting code review help. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on code review automation and PR analysis. The combination of PR-specific triggers, SOLID/code smell analysis, and review report generation creates a distinct identity unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%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, actionable skill with excellent conciseness and clear tool documentation. The main weakness is the lack of an integrated workflow showing how to combine the three tools in a typical code review process, including decision points and validation steps between stages.
Suggestions
Add a 'Typical Review Workflow' section showing the recommended sequence: 1) Run PR analyzer → 2) If no critical issues, run quality checker → 3) Generate report → 4) Review findings before submitting
Include validation checkpoints, e.g., 'If PR analyzer returns critical security issues, address those before proceeding with full quality analysis'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting only essential information without explaining concepts Claude already knows. Tables and bullet points maximize information density while maintaining clarity. | 3 / 3 |
Actionability | Provides fully executable bash commands with clear flags and options. Each tool section includes copy-paste ready examples with multiple usage patterns (basic, advanced, JSON output). | 3 / 3 |
Workflow Clarity | While individual tools are well-documented, there's no explicit workflow showing how to combine them for a complete code review process. Missing validation checkpoints between steps (e.g., what to do if PR analyzer finds critical issues before running quality checker). | 2 / 3 |
Progressive Disclosure | Excellent structure with clear table of contents, well-organized sections, and one-level-deep references to detailed guides (checklist, standards, antipatterns). Content is appropriately split between overview and reference materials. | 3 / 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.
- 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.