code-reviewer

进行系统化的代码审查，检查代码质量、安全性和性能。当用户要求审查代码、review 或检查代码时使用

Quality

72%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/code-reviewer/SKILL.md

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides a solid framework for systematic code review with clear categorization and output structure. Its main strengths are the well-defined workflow and severity-based reporting format. However, it could be more actionable with additional concrete examples and more concise by removing obvious checklist items that Claude inherently understands.

Suggestions

Add more concrete code examples for each review dimension (e.g., show what N+1 query looks like and how to fix it)

Remove explanatory text for concepts Claude knows (e.g., 'DRY 原则' explanation, basic security concepts) to improve conciseness

Consider splitting language-specific review guidelines into separate referenced files (e.g., JAVASCRIPT_REVIEW.md, PYTHON_REVIEW.md)

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some checklist items that Claude already knows (basic security concepts, DRY principle explanations). The structure is clear but could be tightened by removing obvious items.	2 / 3
Actionability	Provides a good checklist structure and one concrete code example for SQL injection, but most guidance remains at the checklist level without executable code or specific commands for detecting issues.	2 / 3
Workflow Clarity	Clear sequential workflow with explicit ordering ('必须按以下顺序检查'), well-defined severity categories, and a structured output format with required fields (file path, line number, impact analysis, fix suggestion).	3 / 3
Progressive Disclosure	Content is well-organized with clear sections, but everything is in a single file. For a comprehensive code review skill, advanced topics (language-specific checks, security deep-dives) could be split into referenced files.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 functional skill description that clearly communicates its purpose and includes explicit trigger conditions. Its main strength is the clear 'Use when' clause with multiple trigger terms in both Chinese and English. The primary weakness is the lack of specific concrete actions - it describes the general scope but not the detailed capabilities that would help distinguish it from related skills.

Suggestions

Add specific concrete actions like 'identifies security vulnerabilities, detects performance bottlenecks, suggests refactoring improvements, checks coding standards compliance'

Include distinguishing details to differentiate from related skills, such as 'comprehensive multi-file review' or 'follows industry best practices checklist'

Dimension	Reasoning	Score
Specificity	Names the domain (code review) and mentions three areas of focus (quality, security, performance), but doesn't list specific concrete actions like 'identify vulnerabilities', 'check for memory leaks', or 'suggest refactoring patterns'.	2 / 3
Completeness	Clearly answers both what ('进行系统化的代码审查，检查代码质量、安全性和性能' - systematic code review checking quality, security, performance) and when ('当用户要求审查代码、review 或检查代码时使用' - explicit trigger clause with 'Use when...').	3 / 3
Trigger Term Quality	Includes natural keywords users would say: '审查代码' (review code), 'review', '检查代码' (check code). These are common terms in both Chinese and English that users would naturally use when requesting code reviews.	3 / 3
Distinctiveness Conflict Risk	While code review is a specific domain, it could potentially overlap with security-focused skills, performance optimization skills, or general code analysis skills. The description doesn't strongly differentiate from these adjacent capabilities.	2 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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: einverne/dotfiles
Commit: b1b2fe0

Reviewed: 4 months ago

Table of Contents

Discovery Implementation Validation

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.