| name | orchestrating-multi-agents |
| description | Use for explicit multi-subagent orchestration when tasks are independent and parallelization improves quality or speed while preserving deterministic merge. |
Orchestrating Multi-Agents
Use this skill when a task benefits from parallel specialist analysis or implementation.
When to use
- Independent research tracks (architecture, security, performance)
- Cross-repo impact analysis
- Large review surfaces requiring specialized reviewers
- Structured synthesis from multiple viewpoints
Guardrails
- Keep one orchestrator owner for final merge.
- Split tasks by clear responsibility boundaries.
- Run only independent tasks in parallel.
- Merge into one deterministic decision/report.
- For high-risk autonomous actions, ask user before execution.
Execution pattern
- Define 2-4 parallel lanes with explicit deliverables.
- Launch subagents simultaneously.
- Require concise, structured outputs from each lane.
- Resolve conflicts explicitly (do not average contradictions).
- Produce final plan/report with rationale and chosen direction.
Naming convention
In prompts, reference agents with collision-safe namespace:
psters-ai-workflow:<category>:<agent-name>
Anti-patterns
- Parallelizing dependent tasks that need sequencing
- Letting subagents mutate broad code areas without clear ownership
- Returning multiple conflicting answers without a final merged decision
