majiayu000 Provide architectural guidance for prompt-native agent systems. This skill covers orchestration patterns, iteration loops, state management, and agent handoffs.
The Crew Philosophy
Agents work, you orchestrate. Spawn agents for heavy lifting, keep main thread light for decisions.
State survives compaction. All branch state lives in .claude/branches/{branch}/state.json.
Handoffs are mandatory. Every task completion creates a handoff. Knowledge persists.
Iteration until done. Use loops for tasks with verifiable completion criteria.
Task Routing
| Task | Resource |
|---|---|
| Agent orchestration | references/orchestration.md |
| Iteration loops | references/iteration-loop.md |
| State persistence | references/state-management.md |
| Architecture patterns | references/architecture/ |
Workflows
| Workflow | Purpose |
|---|---|
loop.md |
Iteration loop for autonomous completion |
cancel-loop.md |
Graceful loop termination |
handoff.md |
Create context preservation documents |
compound.md |
Extract learnings into permanent knowledge |
triage.md |
Categorize and prioritize findings |
Domain Knowledge
Core Patterns
orchestration.md- Agent spawning patternsiteration-loop.md- Loop mechanics, completion promisesstate-management.md- Unified state format
Architecture (references/architecture/)
architecture-patterns.md- Prompt-native designorchestrator-patterns.md- Agent orchestrationsystem-prompt-design.md- System promptsmcp-tool-design.md- MCP tool patternsself-modification.md- Self-modifying systemsrefactoring-to-prompt-native.md- Migration patternsinfrastructure.md- Infrastructure patternsarchitecture-checklist.md- Review checklist