Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计通过

review审查

Agent Skill

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

324

周安装

13

GitHub Stars

公开资料未说明

下载量

105
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:review(审查)
来源仓库:https://github.com/vitadynamics/vita-cc-market
仓库路径:skills/review
安装命令:
npx skills add https://github.com/vitadynamics/vita-cc-market --skill 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/vitadynamics/vita-cc-market --skill review

简介

用于查找、检索和筛选相关信息,适合快速定位候选结果。

  • 可根据关键词或任务场景提供线索,辅助信息收集与决策支持。
  • 安装命令:npx skills add https://github.com/vitadynamics/vita-cc-market --skill review
  • 使用前建议确认权限范围和维护状态,避免触发联网或命令执行。
  • 注意检查是否会读写文件或修改项目结构。

SKILL.md

Review Skill

Purpose: Perform exhaustive code reviews using multi-agent analysis across 13+ specialized reviewer agents.

Review Context

Review target: ${ARGUMENTS}

Review Methodology

Phase 1: Setup and Context Gathering

  1. Identify Review Target

- Determine if reviewing a PR, branch, or commit - Gather basic information about the changes

  1. Setup Work Environment

- Check if already on review branch - If not, consider using git-worktree for isolated review - Skill: git-worktree (if needed)

  1. Initial Scan

- Get overview of changed files and lines - Identify major areas of change

Phase 2: Parallel Agent Reviews (13+ Reviewers)

Launch specialized reviewer agents in parallel:

Architecture Reviewers:

  1. System Architecture Reviewer - Overall system design and boundaries
  2. Domain Model Reviewer - Business logic and data modeling
  3. API Design Reviewer - Endpoint design and contracts

Code Quality Reviewers: 4. Patterns & Practices Reviewer - Design patterns and best practices 5. Performance Reviewer - Efficiency and scalability considerations 6. Security Reviewer - Security vulnerabilities and best practices 7. Test Coverage Reviewer - Testing strategy and coverage

Language & Framework Reviewers: 8. Language-Specific Reviewer - Language idioms and conventions 9. Framework Reviewer - Framework-specific patterns and APIs

Integration & Operations Reviewers: 10. Integration Reviewer - External dependencies and APIs 11. Database Reviewer - Data modeling and query optimization 12. UI/UX Reviewer - User interface and experience considerations 13. DevOps & Observability Reviewer - Deployment, monitoring, logging

Phase 3: Analysis and Synthesis

  1. Collect Agent Findings

- Gather reports from all reviewer agents - Identify common themes and patterns - Prioritize issues by severity and impact

  1. Create Structured Review

- Categorize findings by type and priority - Provide specific, actionable feedback - Include code examples and suggestions

  1. Generate Review Summary

- Overall assessment of code quality - Key strengths and areas for improvement - Recommendations for next steps

Phase 4: Report and Follow-up

  1. Create Review Document

- Write comprehensive review report - Include detailed findings with code references - Suggest fixes and improvements

  1. Present Findings

- Share review summary with user - Highlight critical issues first - Offer to help with specific fixes

  1. Next Steps Options

- Fix issues identified in review - Run additional validation tests - Proceed with merge/approval process

Review Output

  • Structured Review Document: Detailed analysis with categorized findings
  • Priority Classification: P1 (Critical), P2 (Important), P3 (Nice-to-have)
  • Actionable Recommendations: Specific fixes and improvements
  • File Path References: Exact locations of issues (e.g., app/services/example.rb:42)

Severity Classification

P1 (Critical): Must fix before merging

  • Security vulnerabilities
  • Breaking API changes without migration
  • Data loss risks
  • Performance regressions > 50%

P2 (Important): Should fix soon

  • Code quality issues affecting maintainability
  • Missing error handling
  • Incomplete test coverage
  • Minor performance issues

P3 (Nice-to-have): Optional improvements

  • Code style nitpicks
  • Documentation improvements
  • Test optimization
  • Refactoring opportunities

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

38.79%
按下载量换算41

Claude

28.08%
按下载量换算29

Cursor

21.48%
按下载量换算23

Gemini CLI

9.1%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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