name: parallel-agents description: Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives. allowed-tools: Read, Glob, Grep
Native Parallel Agents
Orchestration through Antigravity's built-in Agent Tool
Overview
This skill enables coordinating multiple specialized SEO agents through Antigravity's native agent system. Unlike external scripts, this approach keeps all orchestration within Antigravity's control.
When to Use Orchestration
✅ Good for:
- Complex SEO tasks requiring multiple expertise domains
- Comprehensive audits (technical + content + AI visibility)
- Full lifecycle execution (audit → strategy → execute → monitor)
- Cross-surface optimization (Google + AI + Local + Social)
❌ Not for:
- Simple, single-domain tasks
- Quick fixes or small changes
- Tasks where one agent suffices
Native Agent Invocation
Single Agent
Use the seo-technical-architect agent to audit site health
Sequential Chain
First, use the seo-technical-architect to run a technical audit.
Then, use the seo-content-authority to build a content strategy.
Finally, use the seo-intelligence to set up monitoring.
With Context Passing
Use the seo-technical-architect to audit schema markup.
Based on those findings, have the seo-creator optimize page content.
Resume Previous Work
Resume agent [agentId] and continue with additional requirements.
Orchestration Patterns
Pattern 1: Comprehensive SEO Analysis
Agents: seo-technical-architect → [surface-agents] → synthesis
1. seo-technical-architect: Technical audit + health score
2. seo-content-authority: Content quality + E-E-A-T + authority
3. seo-ai-search: AI/GEO visibility + citability
4. seo-intelligence: Analytics + trend detection
5. Synthesize all findings
Pattern 2: Content Lifecycle
Agents: seo-content-authority → seo-creator → seo-intelligence
1. seo-content-authority: Research + strategy + gaps
2. seo-creator: Write + optimize + validate
3. seo-intelligence: Monitor impact
4. Synthesize recommendations
Pattern 3: Full Surface Coverage
Agents: seo-technical-architect → seo-ai-search → seo-local-commerce → seo-multimedia
1. seo-technical-architect: Core technical foundation
2. seo-ai-search: AI search visibility
3. seo-local-commerce: Local/maps optimization
4. seo-multimedia: Video/social/visual
5. Synthesize with prioritized actions
Available SEO Agents
| Agent | Layer | Expertise | Trigger Phrases |
|---|---|---|---|
seo-orchestrator | 🎯 Meta | Lifecycle coordination | "comprehensive", "full pipeline" |
seo-technical-architect | 🏗️ Foundation | Infrastructure & diagnostics | "audit", "technical", "migration", "fix" |
seo-content-authority | 🏗️ Foundation | Strategy & authority | "strategy", "keywords", "content gap", "backlinks" |
seo-intelligence | 🏗️ Foundation | Analytics & monitoring | "GSC", "analytics", "monitor", "rankings" |
seo-ai-search | 🌐 Surface | AI/GEO visibility | "ChatGPT", "GEO", "AI search", "citability" |
seo-multimedia | 🌐 Surface | Video, social, visual | "YouTube", "TikTok", "Zalo", "visual search" |
seo-local-commerce | 🌐 Surface | Local & commerce | "local SEO", "GBP", "NAP", "map pack" |
seo-creator | 🔧 Enabler | Content execution | "write", "optimize page", "content pipeline" |
seo-data-provider | 🔧 Enabler | Data access | "Solann API", "data source", "API key" |
Synthesis Protocol
After all agents complete, synthesize:
## Orchestration Synthesis
### Task Summary
[What was accomplished]
### Agent Contributions
| Agent | Finding |
|-------|---------|
| seo-technical-architect | Found X |
| seo-content-authority | Identified Y |
| seo-ai-search | Discovered Z |
### Consolidated Recommendations
1. **Critical**: [Issue from Agent A]
2. **Important**: [Issue from Agent B]
3. **Nice-to-have**: [Enhancement from Agent C]
### Action Items
- [ ] Fix critical technical issue
- [ ] Optimize content for E-E-A-T
- [ ] Improve AI citability
Best Practices
- 9 SEO agents available for orchestration
- Logical order — Foundation → Surface → Enabler
- Share context — Pass relevant findings to subsequent agents
- Single synthesis — One unified report, not separate outputs
- Phase-aware — Respect project phase state
Key Benefits
- ✅ Single session — All agents share context
- ✅ AI-controlled — Agent orchestrates autonomously
- ✅ Native integration — Works with built-in Explore, Plan agents
- ✅ Resume support — Can continue previous agent work
- ✅ Context passing — Findings flow between agents