code-review-typescript
Performs structured code reviews on TypeScript codebases covering correctness, type safety, async patterns, security, testing, and style. Use when reviewing TypeScript code, pull requests, or when asked to do a code review on a TypeScript or Node.js project.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
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 what the skill does (structured code reviews across six specific dimensions) and when to use it (TypeScript code, pull requests, Node.js projects). It uses third person voice, includes natural trigger terms, and is concise without being vague. It closely matches the good examples in the rubric.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and areas of review: correctness, type safety, async patterns, security, testing, and style. These are concrete, well-defined review dimensions. | 3 / 3 |
Completeness | Clearly answers both 'what' (structured code reviews covering correctness, type safety, async patterns, security, testing, style) and 'when' (explicit 'Use when' clause with triggers like reviewing TypeScript code, pull requests, or code review on TypeScript/Node.js projects). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'code review', 'TypeScript', 'pull requests', 'Node.js', 'code review'. These cover the most common ways a user would phrase a request for this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to TypeScript/Node.js code reviews with specific review dimensions. The combination of 'TypeScript', 'structured code review', and the enumerated review areas makes it highly distinct and unlikely to conflict with general coding or other language-specific skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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, highly actionable TypeScript code review skill with excellent concrete examples and a clear output format. Its main weakness is length—it's a comprehensive but monolithic document that includes some guidance Claude already knows (basic design principles, what `===` means). The structured output format and quick reference checklist are strong additions that make the skill immediately usable.
Suggestions
Trim sections that restate knowledge Claude already has (e.g., 'always use === in TypeScript', Single Responsibility explanation) to reduce token cost.
Consider splitting detailed per-category checklists (Security, Testing, Async) into separate reference files and keeping SKILL.md as a concise overview with links, improving progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is thorough but includes some guidance Claude already knows (e.g., explaining what `===` does, basic concepts like Single Responsibility). Several sections could be tightened—for instance, the Design & Architecture section restates well-known principles. However, the TypeScript-specific patterns and examples earn their place. | 2 / 3 |
Actionability | The skill provides concrete, executable TypeScript code examples with clear ❌/✅ patterns for each category. Line-level guidance like 'flag every `any`' and 'suggest `unknown` + type guard' gives Claude specific, actionable instructions rather than vague direction. | 3 / 3 |
Workflow Clarity | The review process is clearly sequenced: understand intent first, then check correctness, types, async, security, design, errors, testing, and style, with a structured output format (Critical/Improvements/Nits/Positives). The quick reference checklist at the end serves as a validation checkpoint. For a code review skill, this is a well-defined workflow. | 3 / 3 |
Progressive Disclosure | The content is a single monolithic file at ~200+ lines with no references to supporting files. While the sections are well-organized with clear headers, some sections (e.g., the detailed Security or Testing checklists) could be split into separate reference files to keep the main skill leaner. However, no bundle files exist to support this. | 2 / 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
- ucdavis/ai-skills-registry
- Commit
c0b2e4b
- 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.