delegation

Delegate tasks to specialized subagents for parallel execution and follow-ups.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/YSheldon/Prompt-Log --skill delegation-ysheldon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: delegation
Source: https://github.com/YSheldon/Prompt-Log/tree/main/.local/skills/delegation
Command: npx skills add https://github.com/YSheldon/Prompt-Log --skill delegation-ysheldon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Delegation enables complex tasks to be split among specialized subagents, freeing you to focus on higher-level goals and ensuring faster, parallel execution.

Core Features & Use Cases

  • Orchestrate synchronous tasks with subagent and parallelize with startAsyncSubagent for independent work.
  • Manage async follow-ups via messageSubagent and obtain immediate or eventual results with messageSubagentAndGetResponse.
  • Maintain safe, auditable delegation by explicitly passing relevantSkills and controlling capabilities.

Quick Start

Prompt the AI to delegate a task to a subagent and monitor the result.

Frequently Asked Questions about delegation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I delegate tasks to subagents for parallel execution?

Delegate tasks to specialized subagents using startAsyncSubagent to parallelize independent work, freeing you to focus on higher-level goals while ensuring faster execution of complex workflows.

How does asynchronous processing work with AI subagents?

Asynchronous processing uses messageSubagent to send follow-up instructions to running subagents, while messageSubagentAndGetResponse retrieves immediate or eventual results, enabling non-blocking workflow coordination.

Can I control which capabilities a delegated subagent can access?

Yes, you can maintain safe and auditable delegation by explicitly passing relevantSkills to subagents, strictly controlling the capabilities and specific skill access available during task execution.

What is the best way to manage multi-task session planning in AI orchestration?

The best way to manage multi-task session planning is delegating tasks to specialized subagents, applying explicit function interfaces to coordinate synchronous and asynchronous workflow execution autonomously.

When should I use async subagents instead of synchronous task distribution?

Use startAsyncSubagent for independent work that benefits from parallel execution and non-blocking follow-ups, whereas synchronous subagents are better suited for sequential workflow coordination requiring immediate results.