Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计通过

code-review-workflow代码审查工作流程

Agent Skill

code-review-workflow 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

535

周安装

23

GitHub Stars

315

下载量

188
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-workflow(代码审查工作流程)
来源仓库:https://github.com/codewithmukesh/dotnet-claude-kit
仓库路径:skills/code-review-workflow
安装命令:
npx skills add https://github.com/codewithmukesh/dotnet-claude-kit --skill code-review-workflow
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/codewithmukesh/dotnet-claude-kit --skill code-review-workflow

简介

Code Review Workflow 采用 Roslyn MCP 工具优先策略,仅在必要时读取源码获取补充上下文。

  • 适用于 .NET 项目审查,利用编译器诊断信息提升问题发现效率。
  • 输出遵循固定结构:总结→关键问题→警告→建议→架构合规→测试覆盖→优点说明。
  • 所有发现按严重等级分类,Critical 问题必须修复才能推进后续流程。
  • code-review-workflow 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Code Review Workflow

Core Principles

  1. MCP-first analysis — Use Roslyn MCP tools before reading source files. detect_antipatterns catches more than manual scanning, get_diagnostics finds what the compiler knows, and find_references reveals blast radius. Only read files for context that tools can't provide.
  2. Structured output — Every review follows the same format: Summary → Critical → Warnings → Suggestions → Architecture Compliance → Test Coverage → What's Good. Consistent structure makes reviews actionable and scannable.
  3. Severity-based findings — Categorize every finding as Critical (must fix before merge), Warning (should fix, creates tech debt), or Suggestion (nice to have). Never mix severities — a cosmetic issue next to a security bug buries the important finding.
  4. Actionable suggestions — Every finding includes: what's wrong, why it matters, and how to fix it. "This is bad" is not a review comment. "This creates N+1 queries because X. Fix by adding .Include() or using a projection" is.
  5. Acknowledge good work — Always include a "What's Good" section. Positive reinforcement of good patterns is as important as flagging bad ones.

Patterns

Full PR Review Flow

Use for non-trivial PRs (3+ files changed, new features, refactors). Execute steps in order:

Step 1: Understand the change scope Get changed files from git diff or user input. Categorize:

  • New files (features, tests, configs)
  • Modified files (which layers? domain, application, infrastructure, API?)
  • Deleted files (was anything depending on them?)

Step 2: Automated analysis Run MCP tools on changed files:

→ detect_antipatterns (file: each changed .cs file)
  Catch: async void, sync-over-async, DateTime.Now, new HttpClient(), broad catch, etc.

→ get_diagnostics (scope: file, path: each changed file)
  Catch: new compiler warnings, nullability issues, unused variables

→ get_public_api (typeName: each modified type)
  Check: API surface changes — new public members, removed members, signature changes

Step 3: Blast radius assessment For each changed public API:

→ find_references (symbolName: changedMethod)
  Count callers. High count = high risk. Flag breaking changes.

Step 4: Architecture compliance

→ get_project_graph
  Verify: dependency direction is correct (Domain → nothing, Infra → Domain, Api → Application)
  Flag: circular references, wrong-direction dependencies

Step 5: Test coverage check

→ get_test_coverage_map (projectFilter: changed project)
  Check: do test files exist for every changed type?
  Flag: new types without tests, modified logic without test updates

Step 6: Manual review Read changed files for things tools can't catch:

  • Business logic correctness
  • Naming clarity and consistency
  • Error handling completeness
  • Concurrency safety
  • Security: input validation, authorization checks, data exposure

Step 7: Produce review

## Review Summary
[1-2 sentence overall assessment: scope, risk level, recommendation]

## Critical (must fix)
- **[File:Line] [Title]** — [What's wrong]. [Why it matters]. [How to fix].
- ...

## Warnings (should fix)
- **[File:Line] [Title]** — [What's wrong]. [Impact if not fixed]. [Suggested fix].
- ...

## Suggestions (nice to have)
- **[File:Line] [Title]** — [Current approach]. [Better alternative]. [Why].
- ...

## Architecture Compliance
[Dependency direction check results. Layer violation findings. Module boundary enforcement.]

## Test Coverage
[Which changed types have tests. Which are missing. Specific test scenarios to add.]

## What's Good
- [Positive finding 1 — reinforce good patterns]
- [Positive finding 2]
- ...

Quick Review

Use for small changes (1-2 files, bug fixes, config changes). Lightweight — skip blast radius and architecture checks.

Steps:

  1. Run detect_antipatterns on changed files
  2. Run get_diagnostics on changed files
  3. Read the changed code for correctness
  4. Produce abbreviated review (Summary + Issues + What's Good)
## Quick Review
[1 sentence assessment]

### Issues
- [Finding with severity tag: 🔴 Critical / 🟡 Warning / 🔵 Suggestion]

### What's Good
- [Positive note]

Architecture Compliance Check

Standalone check for architecture-level concerns. Use when reviewing project structure changes, new project additions, or module boundary modifications.

Steps:

  1. Run get_project_graph — visualize the full dependency tree
  2. Verify dependency rules per architecture:
ArchitectureRuleViolation Example
VSAFeatures don't reference each otherFeature A imports from Feature B
Clean ArchitectureDomain has zero project referencesDomain references Infrastructure
DDDAggregates don't reference other aggregatesOrder aggregate imports Product aggregate
Modular MonolithModules communicate only via integration eventsModule A directly references Module B's DbContext
  1. Run find_references on module/layer boundary types to verify encapsulation:
→ find_references(symbolName: "OrdersDbContext")
  Should only be referenced within the Orders module.
  External references = module boundary violation.
  1. Run detect_circular_dependencies to find cycles:
→ detect_circular_dependencies(scope: projects)
  Flag any project-level cycles.

→ detect_circular_dependencies(scope: types, projectFilter: "MyApp.Application")
  Flag type-level cycles within the application layer.

Anti-patterns

Reviewing Without MCP Tools

# BAD — Reading every file manually, missing patterns across the codebase
"Let me read OrderService.cs... looks fine to me."
# Missed: 3 DateTime.Now usages, 1 async void, 2 compiler warnings
# GOOD — MCP-first, then targeted file reads
→ detect_antipatterns: Found 3 DateTime.Now (AP004), 1 async void (AP001)
→ get_diagnostics: 2 CS8600 warnings in OrderService.cs
"I found 6 issues via static analysis. Let me read the files for business logic review..."

Vague Feedback

# BAD
"The code could be better."
"This doesn't look right."
"Consider refactoring this."
# GOOD
"OrderService.cs:47 — `DateTime.Now` should be `TimeProvider.GetUtcNow()`.
DateTime.Now is untestable and uses local timezone. Inject TimeProvider
via primary constructor and call GetUtcNow()."

Missing Security Checks

# BAD — Only checking code style and patterns
"Code looks clean, approved!"
# Missed: SQL injection in raw query, missing authorization attribute, exposed PII in logs
# GOOD — Security is a review dimension
"## Critical
- **OrderController.cs:23** Missing `[Authorize]` — endpoint exposes order data without auth
- **SearchService.cs:45** SQL injection — user input concatenated into raw SQL. Use parameterized query.
## Suggestions
- **LoggingMiddleware.cs:12** PII exposure — email logged at Information level. Mask or use Debug level."

Blocking on Style, Ignoring Substance

# BAD — 10 comments about naming, 0 about the race condition
"Rename `svc` to `service`. Use `var` instead of explicit type. Add XML docs."
# GOOD — Prioritize by impact
"## Critical
- Race condition in OrderService.ProcessAsync — concurrent calls can double-charge
## Suggestions
- Consider renaming `svc` to `service` for clarity"

Decision Guide

ScenarioReview TypeMCP Tools
Feature PR (3+ files)Full PR ReviewAll tools
Bug fix (1-2 files)Quick Reviewdetect_antipatterns, get_diagnostics
Config/infra changesQuick Review + Manualget_project_graph
New project/module addedArchitecture Complianceget_project_graph, detect_circular_dependencies
Refactor PRFull PR Review + ArchitectureAll tools + find_references (blast radius)
Security-sensitive changeFull PR Review → escalate to security-auditordetect_antipatterns + manual security review
Test-only changesQuick Reviewget_diagnostics only
Performance-critical pathFull PR Review → escalate to performance-analystget_diagnostics + manual review

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

35.5%
按下载量换算67

Claude

28.59%
按下载量换算54

Cursor

17.71%
按下载量换算33

Gemini CLI

8.57%
按下载量换算16

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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