Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计通过

code-review代码审查

Agent Skill

code-review 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

941

周安装

40

GitHub Stars

公开资料未说明

下载量

330
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:code-review(代码审查)
来源仓库:https://github.com/loxosceles/ai-dev
仓库路径:skills/code-review
安装命令:
npx skills add https://github.com/loxosceles/ai-dev --skill code-review
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/loxosceles/ai-dev --skill code-review

简介

code-review 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。

  • 适用于代码审查、技术方案调研和开发资源查找等研究场景。
  • 通过关键词、任务或来源仓库进行信息筛选,需结合原始 README 确认具体用法。
  • 安装命令为 npx skills add https://github.com/loxosceles/ai-dev --skill code-review。
  • 使用前建议确认权限范围、维护状态及是否触发联网或文件读写操作。

SKILL.md

Code Review Guidelines

This is a strict guideline. Follow these rules exactly.

Multi-perspective code analysis strategy for comprehensive reviews.


Review Strategy

Analyze code from four parallel perspectives:

  1. Architecture - Alignment with patterns and principles
  2. Security - Vulnerabilities and risks
  3. Performance - Optimization opportunities
  4. Quality - Maintainability and conventions

Architecture Review

Check for:

  • Alignment with CORE_PRINCIPLES
  • Consistency with established patterns (see INDEX.md)
  • Proper separation of concerns
  • Module boundaries and dependencies
  • File organization

Report:

  • Pattern violations with doc references
  • Architectural inconsistencies
  • Recommendations for better alignment

Security Review

Check for:

  • Environment variable handling
  • Authentication and authorization flows
  • API endpoint security
  • Input validation and sanitization
  • Token/credential storage
  • Sensitive data exposure

Report:

  • Security vulnerabilities (critical)
  • Potential risks (warnings)
  • Best practice recommendations

Performance Review

Check for:

  • Inefficient algorithms or data structures
  • Unnecessary computations
  • Resource-intensive operations
  • Caching opportunities
  • Bundle size impact (frontend)
  • Database query optimization (backend)

Report:

  • Performance bottlenecks
  • Optimization opportunities
  • Trade-offs to consider

Quality Review

Check for:

  • Code readability and clarity
  • Naming conventions
  • Error handling
  • Code duplication
  • Test coverage
  • Documentation completeness

Report:

  • Code quality issues
  • Maintainability concerns
  • Convention violations

Output Format

Structure findings as:

✅ Strengths

Brief acknowledgment of what works well

🔴 Critical Issues

Must be fixed (security, broken functionality, principle violations)

🟡 Improvements

Important but not urgent (performance, maintainability)

💡 Suggestions

Nice-to-have enhancements (style, minor optimizations)

📋 Action Items

Numbered list of specific changes with file references


Review Process

  1. Analyze in parallel - Run all four perspectives simultaneously
  2. Synthesize findings - Combine results, remove duplicates
  3. Prioritize - Critical → Improvements → Suggestions
  4. Be specific - Reference files, patterns, and principles
  5. Be constructive - Acknowledge good patterns, explain reasoning

Progressive Improvement

If the developer corrects a behavior that this skill should have prevented, suggest a specific amendment to this skill to prevent the same correction in the future.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

38.07%
按下载量换算126

Claude

27.13%
按下载量换算90

Cursor

18.95%
按下载量换算63

Gemini CLI

9.77%
按下载量换算32

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills