Token导航 LogoToken导航

Agent Skill · 研究检索

github-code-review(GitHub 代码审查)

用于围绕 GitHub 仓库、Issue、Pull Request、分支、提交和代码协作流程提供辅助能力。它适合让 Agent 查询项目状态、整理变更、辅助创建或检查协作事项,并把仓库中的信息转成可执行的下一步。使用时需要区分只读查询和写入操作;涉及创建 PR、修改 Issue、推送分支或访问私有仓库时,应确认 token 权限、目标仓库范围和用户授权。

github-code-review 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证为 MIT,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 33,756。

总安装 2,305周安装 98GitHub Stars 34,014下载 808核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

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:github-code-review(GitHub 代码审查)
来源仓库:https://github.com/ruvnet/claude-flow
仓库路径:skills/github-code-review
安装命令:
npx skills add https://github.com/ruvnet/claude-flow --skill github-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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/ruvnet/claude-flow --skill github-code-review

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于围绕 GitHub 仓库、Issue、Pull Request 等协作流程提供辅助能力。可查询项目状态、整理变更并支持协作事项创建与检查。通过 npx skills add 命令从 GitHub 仓库安装。涉及写入操作时需确认 token 权限与仓库访问范围。

github-code-review 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/github-code-review

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/ruvnet/claude-flow --skill github-code-review;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

github-code-review 怎么安装?

在终端执行 npx skills add https://github.com/ruvnet/claude-flow --skill github-code-review。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

github-code-review 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

github-code-review 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/ruvnet/claude-flow --skill github-code-review;npx skills add ruvnet/claude-flow --skill "github-code-review" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

github-code-review 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

github-code-review 用的人多吗?

公开数据是累计安装 2,305 次,近一周安装 98 次,下载 808 次,GitHub 34,014 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

github-code-review 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 来源仓库有 34,014 星,维护活跃度相对可查。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
github-code-review

GitHub 代码审查 · 本页

2,30534,014执行命令MIT未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

GitHub Code Review Skill

AI-Powered Code Review: Deploy specialized review agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis.

🎯 Quick Start

Simple Review

# Initialize review swarm for PR
gh pr view 123 --json files,diff | npx ruv-swarm github review-init --pr 123

# Post review status
gh pr comment 123 --body "🔍 Multi-agent code review initiated"

Complete Review Workflow

# Get PR context with gh CLI
PR_DATA=$(gh pr view 123 --json files,additions,deletions,title,body)
PR_DIFF=$(gh pr diff 123)

# Initialize comprehensive review
npx ruv-swarm github review-init \
  --pr 123 \
  --pr-data "$PR_DATA" \
  --diff "$PR_DIFF" \
  --agents "security,performance,style,architecture,accessibility" \
  --depth comprehensive

📚 Table of Contents

<$details>

<$details>

<$details>

<$details>


🚀 Core Features

Multi-Agent Review System

Deploy specialized AI agents for comprehensive code review:

# Initialize review swarm with GitHub CLI integration
PR_DATA=$(gh pr view 123 --json files,additions,deletions,title,body)
PR_DIFF=$(gh pr diff 123)

# Start multi-agent review
npx 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 status
gh pr comment 123 --body "🔍 Multi-agent code review initiated"

Benefits:

  • ✅ Parallel review by specialized agents
  • ✅ Comprehensive coverage across multiple domains
  • ✅ Faster review cycles with coordinated analysis
  • ✅ Consistent quality standards enforcement

🤖 Specialized Review Agents

Security Review Agent

Focus: Identify security vulnerabilities and suggest fixes

# Get changed files from PR
CHANGED_FILES=$(gh pr view 123 --json files --jq '.files[].path')

# Run security-focused review
SECURITY_RESULTS=$(npx ruv-swarm github review-security \
  --pr 123 \
  --files "$CHANGED_FILES" \
  --check "owasp,cve,secrets,permissions" \
  --suggest-fixes)

# Post findings based on severity
if echo "$SECURITY_RESULTS" | grep -q "critical"; then
  # Request changes for critical issues
  gh pr review 123 --request-changes --body "$SECURITY_RESULTS"
  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
{
  "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"
  ]
}

<$details>

🔒 **Security Issue: [Type]**

**Severity**: 🔴 Critical / 🟡 High / 🟢 Low

**Description**:
[Clear explanation of the security issue]

**Impact**:
[Potential consequences if not addressed]

**Suggested Fix**:

[Code example of the fix]


**References**:

- [OWASP Guide](https://github.com/ruvnet/claude-flow/blob/HEAD/.agents/skills/github-code-review/link)
- [Security Best Practices](https://github.com/ruvnet/claude-flow/blob/HEAD/.agents/skills/github-code-review/link)

<$details>


Performance Review Agent

Focus: Analyze performance impact and optimization opportunities

# Run performance analysis
npx ruv-swarm github review-performance \
  --pr 123 \
  --profile "cpu,memory,io" \
  --benchmark-against main \
  --suggest-optimizations
{
  "metrics": [
    "Algorithm complexity (Big O analysis)",
    "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"
  ]
}

<$details>


Architecture Review Agent

Focus: Evaluate design patterns and architectural decisions

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

<$details>


Style & Convention Agent

Focus: Enforce coding standards and best practices

# Style enforcement with auto-fix
npx ruv-swarm github review-style \
  --pr 123 \
  --check "formatting,naming,docs,tests" \
  --auto-fix "formatting,imports,whitespace"
{
  "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"
  ]
}

<$details>


🔄 PR-Based Swarm Management

Create Swarm from PR

# Create swarm from PR description using gh CLI
gh pr view 123 --json body,title,labels,files | npx ruv-swarm swarm create-from-pr

# Auto-spawn agents based on PR labels
gh pr view 123 --json labels | npx ruv-swarm swarm auto-spawn

# Create swarm with full PR context
gh pr view 123 --json body,labels,author,assignees | \
  npx ruv-swarm swarm init --from-pr-data

Label-Based Agent Assignment

Map PR labels to specialized agents:

{
  "label-mapping": {
    "bug": ["debugger", "tester"],
    "feature": ["architect", "coder", "tester"],
    "refactor": ["analyst", "coder"],
    "docs": ["researcher", "writer"],
    "performance": ["analyst", "optimizer"],
    "security": ["security", "authentication", "audit"]
  }
}

Topology Selection by PR Size

# Automatic topology selection based on PR complexity
# Small PR (< 100 lines): ring topology
# Medium PR (100-500 lines): mesh topology
# Large PR (> 500 lines): hierarchical topology
npx ruv-swarm github pr-topology --pr 123

🎬 PR Comment Commands

Execute swarm commands directly from PR comments:

<!-- In PR comment -->
$swarm init mesh 6
$swarm spawn coder "Implement authentication"
$swarm spawn tester "Write unit tests"
$swarm status
$swarm review --agents security,performance
// webhook-handler.js
const { createServer } = require('http');
const { execSync } = require('child_process');

createServer((req, res) => {
  if (req.url === '$github-webhook') {
    const event = JSON.parse(body);

    if (event.action === 'opened' && event.pull_request) {
      execSync(`npx ruv-swarm github pr-init ${event.pull_request.number}`);
    }

    if (event.comment && event.comment.body.startsWith('$swarm')) {
      const command = event.comment.body;
      execSync(`npx ruv-swarm github handle-comment --pr ${event.issue.number} --command "${command}"`);
    }

    res.writeHead(200);
    res.end('OK');
  }
}).listen(3000);

<$details>


⚙️ Review Configuration

Configuration File

# .github$review-swarm.yml
version: 1
review:
  auto-trigger: true
  required-agents:
    - security
    - performance
    - style
  optional-agents:
    - architecture
    - accessibility
    - i18n

  thresholds:
    security: block      # Block merge on security issues
    performance: warn    # Warn on performance issues
    style: suggest       # Suggest style improvements

  rules:
    security:
      - no-eval
      - no-hardcoded-secrets
      - proper-auth-checks
      - validate-input
    performance:
      - no-n-plus-one
      - efficient-queries
      - proper-caching
      - optimize-loops
    architecture:
      - max-coupling: 5
      - min-cohesion: 0.7
      - follow-patterns
      - avoid-circular-deps

Custom Review Triggers

{
  "triggers": {
    "high-risk-files": {
      "paths": ["**$auth/**", "**$payment/**", "**$admin/**"],
      "agents": ["security", "architecture"],
      "depth": "comprehensive",
      "require-approval": true
    },
    "performance-critical": {
      "paths": ["**$api/**", "**$database/**", "**$cache/**"],
      "agents": ["performance", "database"],
      "benchmarks": true,
      "regression-threshold": "5%"
    },
    "ui-changes": {
      "paths": ["**$components/**", "**$styles/**", "**$pages/**"],
      "agents": ["accessibility", "style", "i18n"],
      "visual-tests": true,
      "responsive-check": true
    }
  }
}

🤖 Automated Workflows

Auto-Review on PR Creation

# .github$workflows$auto-review.yml
name: Automated Code Review
on:
  pull_request:
    types: [opened, synchronize]
  issue_comment:
    types: [created]

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 $PR_NUM --json files,title,body,labels)
          PR_DIFF=$(gh pr diff $PR_NUM)

          # Run swarm review
          REVIEW_OUTPUT=$(npx ruv-swarm github review-all \
            --pr $PR_NUM \
            --pr-data "$PR_DATA" \
            --diff "$PR_DIFF" \
            --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

      - name: Update Labels
        run: |
          # Add labels based on review results
          if echo "$REVIEW_OUTPUT" | grep -q "security"; then
            gh pr edit $PR_NUM --add-label "security-review"
          fi
          if echo "$REVIEW_OUTPUT" | grep -q "performance"; then
            gh pr edit $PR_NUM --add-label "performance-review"
          fi

💬 Intelligent Comment Generation

Generate Contextual Review Comments

# Get PR diff with context
PR_DIFF=$(gh pr diff 123 --color never)
PR_FILES=$(gh pr view 123 --json files)

# Generate review comments
COMMENTS=$(npx ruv-swarm github review-comment \
  --pr 123 \
  --diff "$PR_DIFF" \
  --files "$PR_FILES" \
  --style "constructive" \
  --include-examples \
  --suggest-fixes)

# Post comments using gh CLI
echo "$COMMENTS" | jq -c '.[]' | while read -r comment; do
  FILE=$(echo "$comment" | jq -r '.path')
  LINE=$(echo "$comment" | jq -r '.line')
  BODY=$(echo "$comment" | jq -r '.body')
  COMMIT_ID=$(gh pr view 123 --json headRefOid -q .headRefOid)

  # Create inline review comments
  gh api \
    --method POST \
    $repos/:owner/:repo$pulls/123$comments \
    -f path="$FILE" \
    -f line="$LINE" \
    -f body="$BODY" \
    -f commit_id="$COMMIT_ID"
done

Batch Comment Management

# Manage review comments efficiently
npx ruv-swarm github review-comments \
  --pr 123 \
  --group-by "agent,severity" \
  --summarize \
  --resolve-outdated

🚪 Quality Gates & Checks

Status Checks

# Required status checks in branch protection
protection_rules:
  required_status_checks:
    strict: true
    contexts:
      - "review-swarm$security"
      - "review-swarm$performance"
      - "review-swarm$architecture"
      - "review-swarm$tests"

Define Quality Gates

# Set quality gate thresholds
npx ruv-swarm github quality-gates \
  --define '{
    "security": {"threshold": "no-critical"},
    "performance": {"regression": "<5%"},
    "coverage": {"minimum": "80%"},
    "architecture": {"complexity": "<10"},
    "duplication": {"maximum": "5%"}
  }'

Track Review Metrics

# Monitor review effectiveness
npx ruv-swarm github review-metrics \
  --period 30d \
  --metrics "issues-found,false-positives,fix-rate,time-to-review" \
  --export-dashboard \
  --format json

🎓 Advanced Features

Context-Aware Reviews

Analyze PRs with full project context:

# Review with comprehensive context
npx ruv-swarm github review-context \
  --pr 123 \
  --load-related-prs \
  --analyze-impact \
  --check-breaking-changes \
  --dependency-analysis

Learning from History

Train review agents on your codebase patterns:

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

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

Cross-PR Analysis

Coordinate reviews across related pull requests:

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

Multi-PR Swarm Coordination

# Coordinate swarms across related PRs
npx ruv-swarm github multi-pr \
  --prs "123,124,125" \
  --strategy "parallel" \
  --share-memory

🛠️ Custom Review Agents

Create Custom Agent

// custom-review-agent.js
class CustomReviewAgent {
  constructor(config) {
    this.config = config;
    this.rules = config.rules || [];
  }

  async review(pr) {
    const issues = [];

    // Custom logic: Check for TODO comments in production code
    if (await this.checkTodoComments(pr)) {
      issues.push({
        severity: 'warning',
        file: pr.file,
        line: pr.line,
        message: 'TODO comment found in production code',
        suggestion: 'Resolve TODO or create issue to track it'
      });
    }

    // Custom logic: Verify API versioning
    if (await this.checkApiVersioning(pr)) {
      issues.push({
        severity: 'error',
        file: pr.file,
        line: pr.line,
        message: 'API endpoint missing versioning',
        suggestion: 'Add $v1/, $v2/ prefix to API routes'
      });
    }

    return issues;
  }

  async checkTodoComments(pr) {
    // Implementation
    const todoRegex = /\/\/\s*TODO|\/\*\s*TODO$gi;
    return todoRegex.test(pr.diff);
  }

  async checkApiVersioning(pr) {
    // Implementation
    const apiRegex = $app\.(get|post|put|delete)\(['"]\$api\/(?!v\d+)/;
    return apiRegex.test(pr.diff);
  }
}

module.exports = CustomReviewAgent;

Register Custom Agent

# Register custom review agent
npx ruv-swarm github register-agent \
  --name "custom-reviewer" \
  --file ".$custom-review-agent.js" \
  --category "standards"

🔧 CI/CD Integration

Integration with Build Pipeline

# .github$workflows$build-and-review.yml
name: Build and Review
on: [pull_request]

jobs:
  build-and-test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions$checkout@v3
      - run: npm install
      - run: npm test
      - run: npm run build

  swarm-review:
    needs: build-and-test
    runs-on: ubuntu-latest
    steps:
      - name: Run Swarm Review
        run: |
          npx ruv-swarm github review-all \
            --pr ${{ github.event.pull_request.number }} \
            --include-build-results

Automated PR Fixes

# Auto-fix common issues
npx ruv-swarm github pr-fix 123 \
  --issues "lint,test-failures,formatting" \
  --commit-fixes \
  --push-changes

Progress Updates to PR

# Post swarm progress to PR using gh CLI
PROGRESS=$(npx ruv-swarm github pr-progress 123 --format markdown)

gh pr comment 123 --body "$PROGRESS"

# Update PR labels based on progress
if [[ $(echo "$PROGRESS" | grep -o '[0-9]\+%' | sed 's/%//') -gt 90 ]]; then
  gh pr edit 123 --add-label "ready-for-review"
fi

📋 Complete Workflow Examples

Example 1: Security-Critical PR

# Review authentication system changes
npx ruv-swarm github review-init \
  --pr 456 \
  --agents "security,authentication,audit" \
  --depth "maximum" \
  --require-security-approval \
  --penetration-test

Example 2: Performance-Sensitive PR

# Review database optimization
npx ruv-swarm github review-init \
  --pr 789 \
  --agents "performance,database,caching" \
  --benchmark \
  --profile \
  --load-test

Example 3: UI Component PR

# Review new component library
npx ruv-swarm github review-init \
  --pr 321 \
  --agents "accessibility,style,i18n,docs" \
  --visual-regression \
  --component-tests \
  --responsive-check

Example 4: Feature Development PR

# Review new feature implementation
gh pr view 456 --json body,labels,files | \
  npx ruv-swarm github pr-init 456 \
    --topology hierarchical \
    --agents "architect,coder,tester,security" \
    --auto-assign-tasks

Example 5: Bug Fix PR

# Review bug fix with debugging focus
npx ruv-swarm github pr-init 789 \
  --topology mesh \
  --agents "debugger,analyst,tester" \
  --priority high \
  --regression-test

📊 Monitoring & Analytics

Review Dashboard

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

Generate Review Reports

# Create comprehensive review report
npx ruv-swarm github review-report \
  --format "markdown" \
  --include "summary,details,trends,recommendations" \
  --email-stakeholders \
  --export-pdf

PR Swarm Analytics

# Generate PR-specific analytics
npx ruv-swarm github pr-report 123 \
  --metrics "completion-time,agent-efficiency,token-usage,issue-density" \
  --format markdown \
  --compare-baseline

Export to GitHub Insights

# Export metrics to GitHub Insights
npx ruv-swarm github export-metrics \
  --pr 123 \
  --to-insights \
  --dashboard-url

🔐 Security Considerations

Best Practices

  1. Token Permissions: Ensure GitHub tokens have minimal required scopes
  2. Command Validation: Validate all PR comments before execution
  3. Rate Limiting: Implement rate limits for PR operations
  4. Audit Trail: Log all swarm operations for compliance
  5. Secret Management: Never expose API keys in PR comments or logs

Security Checklist

  • GitHub token scoped to repository only
  • Webhook signatures verified
  • Command injection protection enabled
  • Rate limiting configured
  • Audit logging enabled
  • Secrets scanning active
  • Branch protection rules enforced

📚 Best Practices

1. Review Configuration

  • ✅ Define clear review criteria upfront
  • ✅ Set appropriate severity thresholds
  • ✅ Configure agent specializations for your stack
  • ✅ Establish override procedures for emergencies

2. Comment Quality

  • ✅ Provide actionable, specific feedback
  • ✅ Include code examples with suggestions
  • ✅ Reference documentation and best practices
  • ✅ Maintain respectful, constructive tone

3. Performance Optimization

  • ✅ Cache analysis results to avoid redundant work
  • ✅ Use incremental reviews for large PRs
  • ✅ Enable parallel agent execution
  • ✅ Batch comment operations efficiently

4. PR Templates

<!-- .github$pull_request_template.md -->
## Swarm Configuration
- Topology: [mesh$hierarchical$ring$star]
- Max Agents: [number]
- Auto-spawn: [yes$no]
- Priority: [high$medium$low]

## Tasks for Swarm
- [ ] Task 1 description
- [ ] Task 2 description
- [ ] Task 3 description

## Review Focus Areas
- [ ] Security review
- [ ] Performance analysis
- [ ] Architecture validation
- [ ] Accessibility check

5. Auto-Merge When Ready

# Auto-merge when swarm completes and passes checks
SWARM_STATUS=$(npx ruv-swarm github pr-status 123)

if [[ "$SWARM_STATUS" == "complete" ]]; then
  # Check review requirements
  REVIEWS=$(gh pr view 123 --json reviews --jq '.reviews | length')

  if [[ $REVIEWS -ge 2 ]]; then
    # Enable auto-merge
    gh pr merge 123 --auto --squash
  fi
fi

🔗 Integration with Claude Code

Workflow Pattern

  1. Claude Code reads PR diff and context
  2. Swarm coordinates review approach based on PR type
  3. Agents work in parallel on different review aspects
  4. Progress updates posted to PR automatically
  5. Final review performed before marking ready

Example: Complete PR Management

[Single Message - Parallel Execution]:
  // Initialize coordination
  mcp__claude-flow__swarm_init { topology: "hierarchical", maxAgents: 5 }
  mcp__claude-flow__agent_spawn { type: "reviewer", name: "Senior Reviewer" }
  mcp__claude-flow__agent_spawn { type: "tester", name: "QA Engineer" }
  mcp__claude-flow__agent_spawn { type: "coordinator", name: "Merge Coordinator" }

  // Create and manage PR using gh CLI
  Bash("gh pr create --title 'Feature: Add authentication' --base main")
  Bash("gh pr view 54 --json files,diff")
  Bash("gh pr review 54 --approve --body 'LGTM after automated review'")

  // Execute tests and validation
  Bash("npm test")
  Bash("npm run lint")
  Bash("npm run build")

  // Track progress
  TodoWrite { todos: [
    { content: "Complete code review", status: "completed", activeForm: "Completing code review" },
    { content: "Run test suite", status: "completed", activeForm: "Running test suite" },
    { content: "Validate security", status: "completed", activeForm: "Validating security" },
    { content: "Merge when ready", status: "pending", activeForm: "Merging when ready" }
  ]}

🆘 Troubleshooting

Common Issues

Solution:

# Check swarm status
npx ruv-swarm swarm-status

# Verify GitHub CLI authentication
gh auth status

# Re-initialize swarm
npx ruv-swarm github review-init --pr 123 --force

<$details>

Solution:

# Verify GitHub token permissions
gh auth status

# Check API rate limits
gh api rate_limit

# Use batch comment posting
npx ruv-swarm github review-comments --pr 123 --batch

<$details>

Solution:

# Use incremental review for large PRs
npx ruv-swarm github review-init --pr 123 --incremental

# Reduce agent count
npx ruv-swarm github review-init --pr 123 --agents "security,style" --max-agents 3

# Enable parallel processing
npx ruv-swarm github review-init --pr 123 --parallel --cache-results

<$details>


📖 Additional Resources

Related Skills

  • github-pr-manager - Comprehensive PR lifecycle management
  • github-workflow-automation - Automate GitHub workflows
  • swarm-coordination - Advanced swarm orchestration

Documentation

Support

  • GitHub Issues: Report bugs and request features
  • Community: Join discussions and share experiences
  • Examples: Browse example configurations and workflows

📄 License

This skill is part of the Claude Code Flow project and is licensed under the MIT License.


Last Updated: 2025-10-19 Version: 1.0.0 Maintainer: Claude Code Flow Team

平台分布

Claude Code

27.4%
按下载量换算221

Antigravity

24.24%
按下载量换算196

OpenCode

19.64%
按下载量换算159

trae

14.87%
按下载量换算120

Gemini CLI

7.59%
按下载量换算61

github-copilot

3.8%
按下载量换算31

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

未通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/ruvnet/claude-flow --skill github-code-review;npx skills add ruvnet/claude-flow --skill "github-code-review" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。

继续浏览同类 Skills