code-reviewer
Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go. Includes automated code analysis, best practice checking, security scanning, and review checklist generation. Use when reviewing pull requests, providing code feedback, identifying issues, or ensuring code quality standards.
Install with Tessl CLI
npx tessl i github:sc30gsw/claude-code-customes --skill code-reviewer53
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
92%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 articulates capabilities across multiple languages with specific actions and includes an explicit 'Use when...' clause with natural trigger terms. The main weakness is potential overlap with other code-related skills (linting, general coding assistance) that might also claim 'code quality' or 'best practices' territory.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'automated code analysis', 'best practice checking', 'security scanning', and 'review checklist generation'. Also specifies supported languages (TypeScript, JavaScript, Python, Swift, Kotlin, Go). | 3 / 3 |
Completeness | Clearly answers both what (code analysis, best practice checking, security scanning, checklist generation) AND when with explicit 'Use when...' clause covering reviewing PRs, providing feedback, identifying issues, and ensuring quality standards. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'pull requests', 'code feedback', 'code review', 'code quality', 'issues'. Also lists specific language names which are common trigger terms. | 3 / 3 |
Distinctiveness Conflict Risk | While it specifies code review as the niche, terms like 'code quality' and 'best practices' could overlap with linting skills or general coding assistance skills. The PR/review focus helps but isn't fully distinctive. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a template shell with no substantive content. It lists scripts and references without explaining what they do, provides no actual code review criteria or examples, and fills space with generic platitudes ('Write clear code', 'Keep it simple') that Claude already knows. The skill fails to teach anything specific about code review.
Suggestions
Replace placeholder script descriptions with actual documentation of what each script does, its specific options, expected inputs/outputs, and example invocations with real arguments
Add concrete code review criteria with specific examples - show actual code snippets with issues and how to identify/report them
Remove generic best practices sections ('Write clear code', 'Validate all inputs') that Claude already knows - focus only on project-specific patterns or non-obvious guidance
Define a clear review workflow with specific validation steps: what to check first, how to categorize issues, what constitutes blocking vs non-blocking feedback, and how to structure review comments
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with generic placeholder content that adds no value. Descriptions like 'Automated tool for pr analyzer tasks' and 'Comprehensive analysis and optimization tool' are meaningless filler. Lists generic features ('Automated scaffolding', 'Best practices built-in') without any specifics Claude doesn't already know. | 1 / 3 |
Actionability | No concrete, executable guidance. Script commands show only placeholder syntax like `python scripts/pr_analyzer.py [options]` without explaining what options exist or what the scripts actually do. No real code examples, no specific review criteria, no actual implementation details for code review tasks. | 1 / 3 |
Workflow Clarity | No clear workflow for actually performing code reviews. Steps like 'Run Quality Checks' -> 'Review recommendations' -> 'Apply fixes' are vague and lack validation checkpoints. No guidance on how to interpret results, what constitutes a passing review, or how to handle failures. | 1 / 3 |
Progressive Disclosure | References external files appropriately (references/code_review_checklist.md, etc.) with one-level-deep structure. However, the main content is still bloated with generic information that should either be removed or moved to reference files. The structure exists but content organization is poor. | 2 / 3 |
Total | 5 / 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.