Back to Details

parallel-agents

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Native Parallel Agents

原生并行Agents

Orchestration through Antigravity's built-in Agent Tool
通过Antigravity的内置Agent工具实现编排

Overview

概述

This skill enables coordinating multiple specialized agents through Antigravity's native agent system. Unlike external scripts, this approach keeps all orchestration within Antigravity's control.
该技能可通过Antigravity的原生Agent系统协调多个专业Agent。与外部脚本不同，这种方法将所有编排操作置于Antigravity的控制范围内。

When to Use Orchestration

何时使用编排

✅ Good for:
  • Complex tasks requiring multiple expertise domains
  • Code analysis from security, performance, and quality perspectives
  • Comprehensive reviews (architecture + security + testing)
  • Feature implementation needing backend + frontend + database work
❌ Not for:
  • Simple, single-domain tasks
  • Quick fixes or small changes
  • Tasks where one agent suffices
✅ 适用场景：
  • 需要多领域专业知识的复杂任务
  • 从安全、性能和质量角度进行代码分析
  • 全面评审（架构+安全+测试）
  • 需要后端+前端+数据库协同的功能实现
❌ 不适用场景：
  • 简单的单领域任务
  • 快速修复或小改动
  • 单个Agent即可完成的任务

Native Agent Invocation

原生Agent调用

Single Agent

单个Agent

Use the security-auditor agent to review authentication
Use the security-auditor agent to review authentication

Sequential Chain

顺序链

First, use the explorer-agent to discover project structure.
Then, use the backend-specialist to review API endpoints.
Finally, use the test-engineer to identify test gaps.
First, use the explorer-agent to discover project structure.
Then, use the backend-specialist to review API endpoints.
Finally, use the test-engineer to identify test gaps.

With Context Passing

上下文传递

Use the frontend-specialist to analyze React components.
Based on those findings, have the test-engineer generate component tests.
Use the frontend-specialist to analyze React components.
Based on those findings, have the test-engineer generate component tests.

Resume Previous Work

恢复之前的工作

Resume agent [agentId] and continue with additional requirements.
Resume agent [agentId] and continue with additional requirements.

Orchestration Patterns

编排模式

Pattern 1: Comprehensive Analysis

模式1：全面分析

Agents: explorer-agent → [domain-agents] → synthesis

1. explorer-agent: Map codebase structure
2. security-auditor: Security posture
3. backend-specialist: API quality
4. frontend-specialist: UI/UX patterns
5. test-engineer: Test coverage
6. Synthesize all findings
Agents: explorer-agent → [domain-agents] → synthesis

1. explorer-agent: Map codebase structure
2. security-auditor: Security posture
3. backend-specialist: API quality
4. frontend-specialist: UI/UX patterns
5. test-engineer: Test coverage
6. Synthesize all findings

Pattern 2: Feature Review

模式2：功能评审

Agents: affected-domain-agents → test-engineer

1. Identify affected domains (backend? frontend? both?)
2. Invoke relevant domain agents
3. test-engineer verifies changes
4. Synthesize recommendations
Agents: affected-domain-agents → test-engineer

1. Identify affected domains (backend? frontend? both?)
2. Invoke relevant domain agents
3. test-engineer verifies changes
4. Synthesize recommendations

Pattern 3: Security Audit

模式3：安全审计

Agents: security-auditor → penetration-tester → synthesis

1. security-auditor: Configuration and code review
2. penetration-tester: Active vulnerability testing
3. Synthesize with prioritized remediation
Agents: security-auditor → penetration-tester → synthesis

1. security-auditor: Configuration and code review
2. penetration-tester: Active vulnerability testing
3. Synthesize with prioritized remediation

Available Agents

可用Agents

AgentExpertiseTrigger Phrases
orchestrator
Coordination"comprehensive", "multi-perspective"
security-auditor
Security"security", "auth", "vulnerabilities"
penetration-tester
Security Testing"pentest", "red team", "exploit"
backend-specialist
Backend"API", "server", "Node.js", "Express"
frontend-specialist
Frontend"React", "UI", "components", "Next.js"
test-engineer
Testing"tests", "coverage", "TDD"
devops-engineer
DevOps"deploy", "CI/CD", "infrastructure"
database-architect
Database"schema", "Prisma", "migrations"
mobile-developer
Mobile"React Native", "Flutter", "mobile"
api-designer
API Design"REST", "GraphQL", "OpenAPI"
debugger
Debugging"bug", "error", "not working"
explorer-agent
Discovery"explore", "map", "structure"
documentation-writer
Documentation"write docs", "create README", "generate API docs"
performance-optimizer
Performance"slow", "optimize", "profiling"
project-planner
Planning"plan", "roadmap", "milestones"
seo-specialist
SEO"SEO", "meta tags", "search ranking"
game-developer
Game Development"game", "Unity", "Godot", "Phaser"
Agent专业领域触发短语
orchestrator
协调管理"comprehensive", "multi-perspective"
security-auditor
安全领域"security", "auth", "vulnerabilities"
penetration-tester
安全测试"pentest", "red team", "exploit"
backend-specialist
后端开发"API", "server", "Node.js", "Express"
frontend-specialist
前端开发"React", "UI", "components", "Next.js"
test-engineer
测试保障"tests", "coverage", "TDD"
devops-engineer
DevOps领域"deploy", "CI/CD", "infrastructure"
database-architect
数据库架构"schema", "Prisma", "migrations"
mobile-developer
移动开发"React Native", "Flutter", "mobile"
api-designer
API设计"REST", "GraphQL", "OpenAPI"
debugger
调试排查"bug", "error", "not working"
explorer-agent
代码发现"explore", "map", "structure"
documentation-writer
文档撰写"write docs", "create README", "generate API docs"
performance-optimizer
性能优化"slow", "optimize", "profiling"
project-planner
项目规划"plan", "roadmap", "milestones"
seo-specialist
SEO优化"SEO", "meta tags", "search ranking"
game-developer
游戏开发"game", "Unity", "Godot", "Phaser"

Antigravity Built-in Agents

Antigravity内置Agents

These work alongside custom agents:
AgentModelPurpose
ExploreHaikuFast read-only codebase search
PlanSonnetResearch during plan mode
General-purposeSonnetComplex multi-step modifications
Use Explore for quick searches, custom agents for domain expertise.
这些Agent可与自定义Agent配合使用：
Agent模型用途
ExploreHaiku快速只读代码库搜索
PlanSonnet计划模式下的研究工作
通用型Sonnet复杂的多步骤修改
使用Explore进行快速搜索，使用自定义Agents获取领域专业知识。

Synthesis Protocol

综合协议

After all agents complete, synthesize:
markdown
undefined
所有Agent完成任务后，进行综合整理：
markdown
undefined

Orchestration Synthesis

Orchestration Synthesis

Task Summary

Task Summary

[What was accomplished]
[What was accomplished]

Agent Contributions

Agent Contributions

AgentFinding
security-auditorFound X
backend-specialistIdentified Y
AgentFinding
security-auditorFound X
backend-specialistIdentified Y

Consolidated Recommendations

Consolidated Recommendations

  1. Critical: [Issue from Agent A]
  2. Important: [Issue from Agent B]
  3. Nice-to-have: [Enhancement from Agent C]
  1. Critical: [Issue from Agent A]
  2. Important: [Issue from Agent B]
  3. Nice-to-have: [Enhancement from Agent C]

Action Items

Action Items

  • Fix critical security issue
  • Refactor API endpoint
  • Add missing tests

---
  • Fix critical security issue
  • Refactor API endpoint
  • Add missing tests

---

Best Practices

最佳实践

  1. Available agents - 17 specialized agents can be orchestrated
  2. Logical order - Discovery → Analysis → Implementation → Testing
  3. Share context - Pass relevant findings to subsequent agents
  4. Single synthesis - One unified report, not separate outputs
  5. Verify changes - Always include test-engineer for code modifications
  1. 可用Agents - 可编排17个专业Agent
  2. 合理顺序 - 发现→分析→实现→测试
  3. 共享上下文 - 将相关发现传递给后续Agent
  4. 统一综合 - 生成一份统一报告，而非多个独立输出
  5. 验证变更 - 代码修改时务必包含test-engineer

Key Benefits

核心优势

  • ✅ Single session - All agents share context
  • ✅ AI-controlled - Claude orchestrates autonomously
  • ✅ Native integration - Works with built-in Explore, Plan agents
  • ✅ Resume support - Can continue previous agent work
  • ✅ Context passing - Findings flow between agents
  • ✅ 单会话 - 所有Agent共享上下文
  • ✅ AI管控 - 由Claude自主编排
  • ✅ 原生集成 - 与内置Explore、Plan Agent兼容
  • ✅ 恢复支持 - 可继续之前的Agent工作
  • ✅ 上下文传递 - 发现成果在Agent间流转