跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 review

Review

综合守则审查工作流程 -- -- 平行的专门审查 -- -- 综合

517 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

综合守则审查工作流程 -- -- 平行的专门审查 -- -- 综合

何时用

- "审查这个代码"

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:/review - Code Review Workflow、When to Use、Workflow Overview、Agent Sequence、Review Perspectives、Execution。 其中含规范建议的小节:分步指令。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

Comprehensive code review workflow - parallel specialized reviews → synthesis

/review - Code Review WorkflowWhen to UseWorkflow OverviewAgent SequenceReview PerspectivesExecutionPhase 1: Parallel ReviewsCode quality reviewArchitecture reviewChange impact reviewWait for all parallel reviewsPhase 2: Synthesis

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
review
description
Comprehensive code review workflow - parallel specialized reviews → synthesis
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「review」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-7bcac4f3aa978884-%E5%AE%A1%E6%9F%A5.html
请存为 .cursor/skills/review/SKILL.md 或 .claude/skills/review/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/parcadei/continuous-claude-v3' --list

npx skills add 'https://github.com/parcadei/continuous-claude-v3' --skill 'review'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: review description: Comprehensive code review workflow - parallel specialized reviews → synthesis

/review - Code Review Workflow

Multi-perspective code review with parallel specialists.

When to Use

  • "Review this code"
  • "Review my PR"
  • "Check this before I merge"
  • "Get feedback on implementation"
  • Before merging significant changes
  • Quality gates

Workflow Overview

         ┌──────────┐
         │  critic  │ ─┐
         │ (code)   │  │
         └──────────┘  │
                       │
         ┌──────────┐  │      ┌──────────────┐
         │plan-reviewer│ ─┼────▶ │ review-agent │
         │ (plan)   │  │      │ (synthesis)  │
         └──────────┘  │      └──────────────┘
                       │
         ┌──────────┐  │
         │plan-reviewer│ ─┘
         │ (change) │
         └──────────┘

         Parallel                Sequential
         perspectives            synthesis

Agent Sequence

| # | Agent | Focus | Execution | |---|-------|-------|-----------| | 1 | critic | Code quality, patterns, readability | Parallel | | 1 | plan-reviewer | Architecture, plan adherence | Parallel | | 1 | plan-reviewer | Change impact, risk assessment | Parallel | | 2 | review-agent | Synthesize all reviews, final verdict | After 1 |

Review Perspectives

  • critic: Is this good code? (Style, patterns, readability)
  • plan-reviewer: Does this match the design? (Architecture, plan)
  • plan-reviewer: Is this change safe? (Risk, impact, regressions)
  • review-agent: Overall assessment and recommendations

Execution

Phase 1: Parallel Reviews

# Code quality review
Task(
  subagent_type="critic",
  prompt="""
  Review code quality: [SCOPE]

  Evaluate:
  - Code style and consistency
  - Design patterns used
  - Readability and maintainability
  - Error handling
  - Test coverage

  Output: List of issues with severity (critical/major/minor)
  """,
  run_in_background=true
)

# Architecture review
Task(
  subagent_type="plan-reviewer",
  prompt="""
  Review architecture alignment: [SCOPE]

  Check:
  - Follows established patterns
  - Matches implementation plan (if exists)
  - Consistent with system design
  - No architectural violations

  Output: Alignment assessment with concerns
  """,
  run_in_background=true
)

# Change impact review
Task(
  subagent_type="plan-reviewer",
  prompt="""
  Review change impact: [SCOPE]

  Assess:
  - Risk level of changes
  - Affected systems/components
  - Backward compatibility
  - Potential regressions
  - Security implications

  Output: Risk assessment with recommendations
  """,
  run_in_background=true
)

# Wait for all parallel reviews
[Check TaskOutput for all three]

Phase 2: Synthesis

Task(
  subagent_type="review-agent",
  prompt="""
  Synthesize reviews for: [SCOPE]

  Reviews:
  - critic: [code quality findings]
  - plan-reviewer: [architecture findings]
  - plan-reviewer: [change impact findings]

  Create final review:
  - Overall verdict (APPROVE / REQUEST_CHANGES / NEEDS_DISCUSSION)
  - Prioritized action items
  - Blocking vs non-blocking issues
  - Summary for PR description
  """
)

Review Modes

Full Review

User: /review
→ All four agents, comprehensive review

Quick Review

User: /review --quick
→ critic only, fast feedback

Security Focus

User: /review --security
→ Add aegis (security agent) to parallel phase

PR Review

User: /review PR #123
→ Fetch PR diff, review changes

Example

User: /review the authentication changes

Claude: Starting /review workflow...

Phase 1: Running parallel reviews...
┌────────────────────────────────────────────┐
│ critic: Reviewing code quality...          │
│ plan-reviewer: Checking architecture...         │
│ plan-reviewer: Assessing change impact...         │
└────────────────────────────────────────────┘

critic: Found 2 issues
- [minor] Inconsistent error messages in auth.ts
- [major] Missing input validation in login()

plan-reviewer: ✅ Matches authentication plan

plan-reviewer: Medium risk
- Affects: login, signup, password reset
- Breaking change: session token format

Phase 2: Synthesizing...

┌─────────────────────────────────────────────┐
│ Review Summary                              │
├─────────────────────────────────────────────┤
│ Verdict: REQUEST_CHANGES                    │
│                                             │
│ Blocking:                                   │
│ 1. Add input validation to login()          │
│                                             │
│ Non-blocking:                               │
│ 2. Standardize error messages               │
│                                             │
│ Notes:                                      │
│ - Document session token format change      │
│ - Consider migration path for existing      │
│   sessions                                  │
└─────────────────────────────────────────────┘

Verdicts

  • APPROVE: Ready to merge, all issues are minor
  • REQUEST_CHANGES: Blocking issues must be fixed
  • NEEDS_DISCUSSION: Architectural decisions need input

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…