From orchestration
Guides proactive use of /orchestrate for complex multi-agent workflows with sequential/parallel execution, conditionals, retries, visualization, checkpoints, and automation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/orchestration:using-orchestrationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Proactively suggest `/orchestrate` when user describes:
Proactively suggest /orchestrate when user describes:
Clear Triggers:
Specific Phrases:
When triggers detected, suggest proactively:
This workflow would benefit from orchestration. I can use `/orchestrate` to:
- Visualize the workflow graph
- Execute agents in parallel where possible
- Handle retries and conditionals
- Provide interactive control at checkpoints
Would you like me to use `/orchestrate [workflow-syntax]` or create a reusable template?
First-time setup reminder:
If user mentions custom agents (like expert-code-implementer, code-optimizer, etc.) that aren't in the orchestration namespace:
I notice you have custom agents in your environment.
Would you like to import them to orchestration first?
Run: /orchestration:init
This will make your custom agents available in workflows as:
- orchestration:expert-code-implementer
- orchestration:code-optimizer
- etc.
Show relevant syntax based on user's needs:
Sequential: explore:"task" -> review -> implement
Parallel: [test || lint || security]
Conditional: test (if passed)~> deploy
Retry: @try -> fix -> test (if failed)~> @try
When user agrees to orchestration:
/orchestrate [workflow-syntax]npx claudepluginhub mbruhler/claude-orchestration --plugin orchestrationProvides templates for orchestrator system prompts, phase-specific agent commands like scout and builder, and result aggregation in multi-agent workflows.
Executes orchestration workflows using -> || ~> syntax with real-time ASCII visualization, interactive steering at checkpoints, error recovery, and resume from .orchestration/state.json.
Analyzes user tasks to recommend and execute optimal agent orchestration patterns: Sequential Pipeline, Parallel Subagent, Team Mode, Ralph Loop. For complex multi-step tasks or /agent-orchestrate invocation.