Agent Code Review Swarm

作者 ruvnet6051f6702b61無授權條款74K 個星標收錄於 2026年10月8日更新於 2026年10月8日儲存庫今天更新

Agent skill for code-review-swarm - invoke with $agent-code-review-swarm

僅含說明Software Development

AI 產生的概覽

部署專門的 AI 審查代理，分析提取請求中的安全性、效能、風格與架構問題。

功能: 此技能針對 GitHub 提取請求編排多代理程式碼審查叢集。它收集 PR 詳細資料與差異，執行安全性、效能、風格、架構與無障礙等專門審查代理，並將發現、行內評論與審查狀態回寫至提取請求。它也定義審查設定、品質閘門、觸發條件與指標，以便與 CI/CD 整合。
適用情境: 當提取請求需要超越靜態分析的全面自動化審查時使用。它適合希望進行安全性、效能、架構與風格檢查並將結果發佈至 GitHub 的團隊。
執行需求: 需要已驗證的 GitHub CLI（gh）、存取 GitHub 的網路連線，以及 npx ruv-swarm 工具。此技能不附帶指令碼，僅為說明文件，並引用 mcpclaude-flowswarm_init 與 agent_spawn 等 MCP 工具。

name: code-review-swarm description: Deploy specialized AI agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis tools: mcp__claude-flow__swarm_init, mcp__claude-flow__agent_spawn, mcp__claude-flow__task_orchestrate, Bash, Read, Write, TodoWrite color: blue type: development capabilities:

Automated multi-agent code review
Security vulnerability analysis
Performance bottleneck detection
Architecture pattern validation
Style and convention enforcement priority: high hooks: pre: | echo "Starting code-review-swarm..." echo "Initializing multi-agent review system" gh auth status || (echo "GitHub CLI not authenticated" && exit 1) post: | echo "Completed code-review-swarm" echo "Review results posted to GitHub" echo "Quality gates evaluated"

Code Review Swarm - Automated Code Review with AI Agents

Overview

Deploy specialized AI agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis.

Core Features

1. Multi-Agent Review System

bash

# Initialize code review swarm with gh CLI# Get PR detailsPR_DATA=$(gh pr view 123 --json files,additions,deletions,title,body)PR_DIFF=$(gh pr diff 123)
# Initialize swarm with PR contextnpx ruv-swarm github review-init \  --pr 123 \  --pr-data "$PR_DATA" \  --diff "$PR_DIFF" \  --agents "security,performance,style,architecture,accessibility" \  --depth comprehensive
# Post initial review statusgh pr comment 123 --body "🔍 Multi-agent code review initiated"

# Initialize code review swarm with gh CLI# Get PR detailsPR_DATA=$(gh pr view 123 --json files,additions,deletions,title,body)PR_DIFF=$(gh pr diff 123)
# Initialize swarm with PR contextnpx ruv-swarm github review-init \  --pr 123 \  --pr-data "$PR_DATA" \  --diff "$PR_DIFF" \  --agents "security,performance,style,architecture,accessibility" \  --depth comprehensive
# Post initial review statusgh pr comment 123 --body "🔍 Multi-agent code review initiated"

2. Specialized Review Agents

Security Agent

bash

# Security-focused review with gh CLI# Get changed filesCHANGED_FILES=$(gh pr view 123 --json files --jq '.files[].path')
# Run security reviewSECURITY_RESULTS=$(npx ruv-swarm github review-security \  --pr 123 \  --files "$CHANGED_FILES" \  --check "owasp,cve,secrets,permissions" \  --suggest-fixes)
# Post security findingsif echo "$SECURITY_RESULTS" | grep -q "critical"; then  # Request changes for critical issues  gh pr review 123 --request-changes --body "$SECURITY_RESULTS"  # Add security label  gh pr edit 123 --add-label "security-review-required"else  # Post as comment for non-critical issues  gh pr comment 123 --body "$SECURITY_RESULTS"fi

# Security-focused review with gh CLI# Get changed filesCHANGED_FILES=$(gh pr view 123 --json files --jq '.files[].path')
# Run security reviewSECURITY_RESULTS=$(npx ruv-swarm github review-security \  --pr 123 \  --files "$CHANGED_FILES" \  --check "owasp,cve,secrets,permissions" \  --suggest-fixes)
# Post security findingsif echo "$SECURITY_RESULTS" | grep -q "critical"; then  # Request changes for critical issues  gh pr review 123 --request-changes --body "$SECURITY_RESULTS"  # Add security label  gh pr edit 123 --add-label "security-review-required"else  # Post as comment for non-critical issues  gh pr comment 123 --body "$SECURITY_RESULTS"fi

Performance Agent

bash

# Performance analysisnpx ruv-swarm github review-performance \  --pr 123 \  --profile "cpu,memory,io" \  --benchmark-against main \  --suggest-optimizations

# Performance analysisnpx ruv-swarm github review-performance \  --pr 123 \  --profile "cpu,memory,io" \  --benchmark-against main \  --suggest-optimizations

Architecture Agent

bash

# Architecture reviewnpx ruv-swarm github review-architecture \  --pr 123 \  --check "patterns,coupling,cohesion,solid" \  --visualize-impact \  --suggest-refactoring

# Architecture reviewnpx ruv-swarm github review-architecture \  --pr 123 \  --check "patterns,coupling,cohesion,solid" \  --visualize-impact \  --suggest-refactoring

3. Review Configuration

yaml

# .github$review-swarm.ymlversion: 1review:  auto-trigger: true  required-agents:    - security    - performance    - style  optional-agents:    - architecture    - accessibility    - i18n    thresholds:    security: block    performance: warn    style: suggest      rules:    security:      - no-eval      - no-hardcoded-secrets      - proper-auth-checks    performance:      - no-n-plus-one      - efficient-queries      - proper-caching    architecture:      - max-coupling: 5      - min-cohesion: 0.7      - follow-patterns

# .github$review-swarm.ymlversion: 1review:  auto-trigger: true  required-agents:    - security    - performance    - style  optional-agents:    - architecture    - accessibility    - i18n    thresholds:    security: block    performance: warn    style: suggest      rules:    security:      - no-eval      - no-hardcoded-secrets      - proper-auth-checks    performance:      - no-n-plus-one      - efficient-queries      - proper-caching    architecture:      - max-coupling: 5      - min-cohesion: 0.7      - follow-patterns

Review Agents

Security Review Agent

javascript

// Security checks performed{  "checks": [    "SQL injection vulnerabilities",    "XSS attack vectors",    "Authentication bypasses",    "Authorization flaws",    "Cryptographic weaknesses",    "Dependency vulnerabilities",    "Secret exposure",    "CORS misconfigurations"  ],  "actions": [    "Block PR on critical issues",    "Suggest secure alternatives",    "Add security test cases",    "Update security documentation"  ]}

// Security checks performed{  "checks": [    "SQL injection vulnerabilities",    "XSS attack vectors",    "Authentication bypasses",    "Authorization flaws",    "Cryptographic weaknesses",    "Dependency vulnerabilities",    "Secret exposure",    "CORS misconfigurations"  ],  "actions": [    "Block PR on critical issues",    "Suggest secure alternatives",    "Add security test cases",    "Update security documentation"  ]}

Performance Review Agent

javascript

// Performance analysis{  "metrics": [    "Algorithm complexity",    "Database query efficiency",    "Memory allocation patterns",    "Cache utilization",    "Network request optimization",    "Bundle size impact",    "Render performance"  ],  "benchmarks": [    "Compare with baseline",    "Load test simulations",    "Memory leak detection",    "Bottleneck identification"  ]}

// Performance analysis{  "metrics": [    "Algorithm complexity",    "Database query efficiency",    "Memory allocation patterns",    "Cache utilization",    "Network request optimization",    "Bundle size impact",    "Render performance"  ],  "benchmarks": [    "Compare with baseline",    "Load test simulations",    "Memory leak detection",    "Bottleneck identification"  ]}

Style & Convention Agent

javascript

// Style enforcement{  "checks": [    "Code formatting",    "Naming conventions",    "Documentation standards",    "Comment quality",    "Test coverage",    "Error handling patterns",    "Logging standards"  ],  "auto-fix": [    "Formatting issues",    "Import organization",    "Trailing whitespace",    "Simple naming issues"  ]}

// Style enforcement{  "checks": [    "Code formatting",    "Naming conventions",    "Documentation standards",    "Comment quality",    "Test coverage",    "Error handling patterns",    "Logging standards"  ],  "auto-fix": [    "Formatting issues",    "Import organization",    "Trailing whitespace",    "Simple naming issues"  ]}

Architecture Review Agent

javascript

// Architecture analysis{  "patterns": [    "Design pattern adherence",    "SOLID principles",    "DRY violations",    "Separation of concerns",    "Dependency injection",    "Layer violations",    "Circular dependencies"  ],  "metrics": [    "Coupling metrics",    "Cohesion scores",    "Complexity measures",    "Maintainability index"  ]}

// Architecture analysis{  "patterns": [    "Design pattern adherence",    "SOLID principles",    "DRY violations",    "Separation of concerns",    "Dependency injection",    "Layer violations",    "Circular dependencies"  ],  "metrics": [    "Coupling metrics",    "Cohesion scores",    "Complexity measures",    "Maintainability index"  ]}

Advanced Review Features

1. Context-Aware Reviews

bash

# Review with full contextnpx ruv-swarm github review-context \  --pr 123 \  --load-related-prs \  --analyze-impact \  --check-breaking-changes

# Review with full contextnpx ruv-swarm github review-context \  --pr 123 \  --load-related-prs \  --analyze-impact \  --check-breaking-changes

2. Learning from History

bash

# Learn from past reviewsnpx ruv-swarm github review-learn \  --analyze-past-reviews \  --identify-patterns \  --improve-suggestions \  --reduce-false-positives

# Learn from past reviewsnpx ruv-swarm github review-learn \  --analyze-past-reviews \  --identify-patterns \  --improve-suggestions \  --reduce-false-positives

3. Cross-PR Analysis

bash

# Analyze related PRs togethernpx ruv-swarm github review-batch \  --prs "123,124,125" \  --check-consistency \  --verify-integration \  --combined-impact

# Analyze related PRs togethernpx ruv-swarm github review-batch \  --prs "123,124,125" \  --check-consistency \  --verify-integration \  --combined-impact

Review Automation

Auto-Review on Push

yaml

# .github$workflows$auto-review.ymlname: Automated Code Reviewon:  pull_request:    types: [opened, synchronize]
jobs:  swarm-review:    runs-on: ubuntu-latest    steps:      - uses: actions$checkout@v3        with:          fetch-depth: 0                - name: Setup GitHub CLI        run: echo "${{ secrets.GITHUB_TOKEN }}" | gh auth login --with-token                - name: Run Review Swarm        run: |          # Get PR context with gh CLI          PR_NUM=${{ github.event.pull_request.number }}          PR_DATA=$(gh pr view $PR_NUM --json files,title,body,labels)                    # Run swarm review          REVIEW_OUTPUT=$(npx ruv-swarm github review-all \            --pr $PR_NUM \            --pr-data "$PR_DATA" \            --agents "security,performance,style,architecture")                    # Post review results          echo "$REVIEW_OUTPUT" | gh pr review $PR_NUM --comment -F -                    # Update PR status          if echo "$REVIEW_OUTPUT" | grep -q "approved"; then            gh pr review $PR_NUM --approve          elif echo "$REVIEW_OUTPUT" | grep -q "changes-requested"; then            gh pr review $PR_NUM --request-changes -b "See review comments above"          fi

# .github$workflows$auto-review.ymlname: Automated Code Reviewon:  pull_request:    types: [opened, synchronize]
jobs:  swarm-review:    runs-on: ubuntu-latest    steps:      - uses: actions$checkout@v3        with:          fetch-depth: 0                - name: Setup GitHub CLI        run: echo "${{ secrets.GITHUB_TOKEN }}" | gh auth login --with-token                - name: Run Review Swarm        run: |          # Get PR context with gh CLI          PR_NUM=${{ github.event.pull_request.number }}          PR_DATA=$(gh pr view $PR_NUM --json files,title,body,labels)                    # Run swarm review          REVIEW_OUTPUT=$(npx ruv-swarm github review-all \            --pr $PR_NUM \            --pr-data "$PR_DATA" \            --agents "security,performance,style,architecture")                    # Post review results          echo "$REVIEW_OUTPUT" | gh pr review $PR_NUM --comment -F -                    # Update PR status          if echo "$REVIEW_OUTPUT" | grep -q "approved"; then            gh pr review $PR_NUM --approve          elif echo "$REVIEW_OUTPUT" | grep -q "changes-requested"; then            gh pr review $PR_NUM --request-changes -b "See review comments above"          fi

Review Triggers

javascript

// Custom review triggers{  "triggers": {    "high-risk-files": {      "paths": ["**$auth/**", "**$payment/**"],      "agents": ["security", "architecture"],      "depth": "comprehensive"    },    "performance-critical": {      "paths": ["**$api/**", "**$database/**"],      "agents": ["performance", "database"],      "benchmarks": true    },    "ui-changes": {      "paths": ["**$components/**", "**$styles/**"],      "agents": ["accessibility", "style", "i18n"],      "visual-tests": true    }  }}

// Custom review triggers{  "triggers": {    "high-risk-files": {      "paths": ["**$auth/**", "**$payment/**"],      "agents": ["security", "architecture"],      "depth": "comprehensive"    },    "performance-critical": {      "paths": ["**$api/**", "**$database/**"],      "agents": ["performance", "database"],      "benchmarks": true    },    "ui-changes": {      "paths": ["**$components/**", "**$styles/**"],      "agents": ["accessibility", "style", "i18n"],      "visual-tests": true    }  }}

Review Comments

Intelligent Comment Generation

bash

# Generate contextual review comments with gh CLI# Get PR diff with contextPR_DIFF=$(gh pr diff 123 --color never)PR_FILES=$(gh pr view 123 --json files)
# Generate review commentsCOMMENTS=$(npx ruv-swarm github review-comment \  --pr 123 \  --diff "$PR_DIFF" \  --files "$PR_FILES" \  --style "constructive" \  --include-examples \  --suggest-fixes)
# Post comments using gh CLIecho "$COMMENTS" | jq -c '.[]' | while read -r comment; do  FILE=$(echo "$comment" | jq -r '.path')  LINE=$(echo "$comment" | jq -r '.line')  BODY=$(echo "$comment" | jq -r '.body')    # Create review with inline comments  gh api \    --method POST \    $repos/:owner/:repo$pulls/123$comments \    -f path="$FILE" \    -f line="$LINE" \    -f body="$BODY" \    -f commit_id="$(gh pr view 123 --json headRefOid -q .headRefOid)"done

# Generate contextual review comments with gh CLI# Get PR diff with contextPR_DIFF=$(gh pr diff 123 --color never)PR_FILES=$(gh pr view 123 --json files)
# Generate review commentsCOMMENTS=$(npx ruv-swarm github review-comment \  --pr 123 \  --diff "$PR_DIFF" \  --files "$PR_FILES" \  --style "constructive" \  --include-examples \  --suggest-fixes)
# Post comments using gh CLIecho "$COMMENTS" | jq -c '.[]' | while read -r comment; do  FILE=$(echo "$comment" | jq -r '.path')  LINE=$(echo "$comment" | jq -r '.line')  BODY=$(echo "$comment" | jq -r '.body')    # Create review with inline comments  gh api \    --method POST \    $repos/:owner/:repo$pulls/123$comments \    -f path="$FILE" \    -f line="$LINE" \    -f body="$BODY" \    -f commit_id="$(gh pr view 123 --json headRefOid -q .headRefOid)"done

Comment Templates

markdown

<!-- Security Issue Template -->🔒 **Security Issue: [Type]**
**Severity**: 🔴 Critical / 🟡 High / 🟢 Low
**Description**: [Clear explanation of the security issue]
**Impact**:[Potential consequences if not addressed]
**Suggested Fix**:```language[Code example of the fix]

<!-- Security Issue Template -->🔒 **Security Issue: [Type]**
**Severity**: 🔴 Critical / 🟡 High / 🟢 Low
**Description**: [Clear explanation of the security issue]
**Impact**:[Potential consequences if not addressed]
**Suggested Fix**:```language[Code example of the fix]

References:

OWASP Guide [blocked]
Security Best Practices [blocked]


### Batch Comment Management```bash# Manage review comments efficientlynpx ruv-swarm github review-comments \  --pr 123 \  --group-by "agent,severity" \  --summarize \  --resolve-outdated


### Batch Comment Management```bash# Manage review comments efficientlynpx ruv-swarm github review-comments \  --pr 123 \  --group-by "agent,severity" \  --summarize \  --resolve-outdated

Integration with CI/CD

Status Checks

yaml

# Required status checksprotection_rules:  required_status_checks:    contexts:      - "review-swarm$security"      - "review-swarm$performance"      - "review-swarm$architecture"

# Required status checksprotection_rules:  required_status_checks:    contexts:      - "review-swarm$security"      - "review-swarm$performance"      - "review-swarm$architecture"

Quality Gates

bash

# Define quality gatesnpx ruv-swarm github quality-gates \  --define '{    "security": {"threshold": "no-critical"},    "performance": {"regression": "<5%"},    "coverage": {"minimum": "80%"},    "architecture": {"complexity": "<10"}  }'

# Define quality gatesnpx ruv-swarm github quality-gates \  --define '{    "security": {"threshold": "no-critical"},    "performance": {"regression": "<5%"},    "coverage": {"minimum": "80%"},    "architecture": {"complexity": "<10"}  }'

Review Metrics

bash

# Track review effectivenessnpx ruv-swarm github review-metrics \  --period 30d \  --metrics "issues-found,false-positives,fix-rate" \  --export-dashboard

# Track review effectivenessnpx ruv-swarm github review-metrics \  --period 30d \  --metrics "issues-found,false-positives,fix-rate" \  --export-dashboard

Best Practices

1. Review Configuration

Define clear review criteria
Set appropriate thresholds
Configure agent specializations
Establish override procedures

2. Comment Quality

Provide actionable feedback
Include code examples
Reference documentation
Maintain respectful tone

3. Performance

Cache analysis results
Incremental reviews for large PRs
Parallel agent execution
Smart comment batching

Advanced Features

1. AI Learning

bash

# Train on your codebasenpx ruv-swarm github review-train \  --learn-patterns \  --adapt-to-style \  --improve-accuracy

# Train on your codebasenpx ruv-swarm github review-train \  --learn-patterns \  --adapt-to-style \  --improve-accuracy

2. Custom Review Agents

javascript

// Create custom review agentclass CustomReviewAgent {  async review(pr) {    const issues = [];        // Custom logic here    if (await this.checkCustomRule(pr)) {      issues.push({        severity: 'warning',        message: 'Custom rule violation',        suggestion: 'Fix suggestion'      });    }        return issues;  }}

// Create custom review agentclass CustomReviewAgent {  async review(pr) {    const issues = [];        // Custom logic here    if (await this.checkCustomRule(pr)) {      issues.push({        severity: 'warning',        message: 'Custom rule violation',        suggestion: 'Fix suggestion'      });    }        return issues;  }}

3. Review Orchestration

bash

# Orchestrate complex reviewsnpx ruv-swarm github review-orchestrate \  --strategy "risk-based" \  --allocate-time-budget \  --prioritize-critical

# Orchestrate complex reviewsnpx ruv-swarm github review-orchestrate \  --strategy "risk-based" \  --allocate-time-budget \  --prioritize-critical

Examples

Security-Critical PR

bash

# Auth system changesnpx ruv-swarm github review-init \  --pr 456 \  --agents "security,authentication,audit" \  --depth "maximum" \  --require-security-approval

# Auth system changesnpx ruv-swarm github review-init \  --pr 456 \  --agents "security,authentication,audit" \  --depth "maximum" \  --require-security-approval

Performance-Sensitive PR

bash

# Database optimizationnpx ruv-swarm github review-init \  --pr 789 \  --agents "performance,database,caching" \  --benchmark \  --profile

# Database optimizationnpx ruv-swarm github review-init \  --pr 789 \  --agents "performance,database,caching" \  --benchmark \  --profile

UI Component PR

bash

# New component librarynpx ruv-swarm github review-init \  --pr 321 \  --agents "accessibility,style,i18n,docs" \  --visual-regression \  --component-tests

# New component librarynpx ruv-swarm github review-init \  --pr 321 \  --agents "accessibility,style,i18n,docs" \  --visual-regression \  --component-tests

Monitoring & Analytics

Review Dashboard

bash

# Launch review dashboardnpx ruv-swarm github review-dashboard \  --real-time \  --show "agent-activity,issue-trends,fix-rates"

# Launch review dashboardnpx ruv-swarm github review-dashboard \  --real-time \  --show "agent-activity,issue-trends,fix-rates"

Review Reports

bash

# Generate review reportsnpx ruv-swarm github review-report \  --format "markdown" \  --include "summary,details,trends" \  --email-stakeholders

# Generate review reportsnpx ruv-swarm github review-report \  --format "markdown" \  --include "summary,details,trends" \  --email-stakeholders

See also: swarm-pr.md [blocked], workflow-automation.md [blocked]

來源與署名

來源：ruvnet/ruflo位於.agents/skills/agent-code-review-swarm提交6051f67

授權條款：無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架

Agent Code Review Swarm

Code Review Swarm - Automated Code Review with AI Agents

Overview

Core Features

1. Multi-Agent Review System

2. Specialized Review Agents

Security Agent

Performance Agent

Architecture Agent

3. Review Configuration

Review Agents

Security Review Agent

Performance Review Agent

Style & Convention Agent

Architecture Review Agent

Advanced Review Features

1. Context-Aware Reviews

2. Learning from History

3. Cross-PR Analysis

Review Automation

Auto-Review on Push

Review Triggers

Review Comments

Intelligent Comment Generation

Comment Templates

Integration with CI/CD

Status Checks

Quality Gates

Review Metrics

Best Practices

1. Review Configuration

2. Comment Quality

3. Performance

Advanced Features

1. AI Learning

2. Custom Review Agents

3. Review Orchestration

Examples

Security-Critical PR

Performance-Sensitive PR

UI Component PR

Monitoring & Analytics

Review Dashboard

Review Reports

來源與署名

更多來自 ruvnet/ruflo 的技能

Cron Schedule

Autopilot Predict

Autopilot Loop

Worker Integration

Worker Benchmarks

Swarm Advanced

更多Software Development技能

Playground

M5 Onboard

Cardputer Buddy

Web Design Guidelines

Vercel React Native Skills

Vercel React Best Practices