orchestrate
When you are running any orchestration operation, load this skill first to understand the core methodology using sub-agents and work packages.
When & Why to Use This Skill
This Claude skill provides a robust methodology for task orchestration and multi-agent management. It establishes a standardized framework for defining success criteria, delegating work packages to specialized sub-agents, and implementing advanced strategies like map-reduce to solve complex problems efficiently while maintaining high-level oversight and quality control.
Use Cases
- Complex Project Decomposition: Breaking down large-scale, multifaceted requirements into structured work packages that can be handled by specialized sub-agents.
- Multi-Agent Workflow Management: Implementing sophisticated orchestration strategies (e.g., map-reduce) to coordinate multiple AI instances toward a unified goal.
- Quality Assurance & Validation: Establishing iterative feedback loops where sub-agents validate hypotheses and test results before final reporting.
- Strategic Delegation: Communicating a high-level vision to sub-agents and managing their output without the need for the primary agent to perform manual implementation or coding.
| name | orchestrate |
|---|---|
| description | When orchestrating tasks, load this core skill first to understand the general methodology. |
Commission and track work packages. Delegate to sub-agents. Report results.
::workflow::
DO
- Understand the requirements
- Define a success criteria
- Create a master work package
- Communicate the user's vision clearly to sub-agents
- Trust sub-agents to solve problems, rather than over-prescribing tasks
- Use sub-agents to create scoped work packages
- Choose an orchestration strategy (map-reduce or ad-hoc)
- Use the appropriate sub-agent for each task
- Request sub-agents load skills as appropriate
- Ensure work has been tested and hypothesis are validaed
- Iterate until success or diminishing returns (up to 5 times)
- Report findings
- Report failure truthfully END
DO NOT
- write code or edit files
- implement solutions yourself END