delegation

Select AI subagents from Kimi K2.5, GLM, and MiniMax using a decision matrix and fallback protocol.

Updated Dec 15, 2025
One-click install
npx skills add https://github.com/OpenSourceSam/v2_heras_garden --skill delegation-opensourcesam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: delegation
Source: https://github.com/OpenSourceSam/v2_heras_garden/tree/main/.claude/skills/delegation
Command: npx skills add https://github.com/OpenSourceSam/v2_heras_garden --skill delegation-opensourcesam

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a structured approach to selecting the most appropriate AI subagent (Kimi K2.5, GLM, MiniMax) for a given task, optimizing for cost, speed, and capability, while strictly avoiding the use of Claude models as subagents.

Core Features & Use Cases

  • Provider Selection Matrix: A clear table guiding the choice of subagent based on task type (reasoning, vision, creative, research, etc.).
  • Automatic Fallback Protocol: Defines a safe and cost-effective fallback chain when a primary subagent fails.
  • Delegation Patterns: Illustrates common workflows for research, batch analysis, creative exploration, and code review using subagents.
  • Token Economics: Provides cost comparisons to encourage efficient model usage.
  • Use Case: When tasked with analyzing a batch of images, this Skill would recommend and configure Kimi K2.5 due to its vision capabilities, or if that fails, it would intelligently fall back to GLM or MiniMax, ensuring the task is completed efficiently and cost-effectively.

Quick Start

Use the delegation skill to select the best subagent for a complex reasoning task.

Frequently Asked Questions about delegation

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

FAQPage Schema
How do I select the best AI subagent for task delegation?

AI subagent delegation uses a provider selection matrix to match task types like reasoning, vision, or research with models such as Kimi K2.5, GLM, or MiniMax for optimal capability and cost.

What happens if my primary AI subagent fails during background execution?

An automatic fallback protocol defines a safe, cost-effective fallback chain to switch subagents if the primary model fails, ensuring tasks like batch image analysis complete efficiently without manual intervention.

How do I optimize token economics across different AI orchestration models?

Token economics are optimized by comparing provider cost profiles and using delegation patterns that allocate tasks to the most cost-effective subagent, balancing speed and capability for efficient orchestration.

Can I use Claude models as subagents for AI delegation?

No, the AI delegation protocol enforces strict rules against using Claude models as subagents, directing orchestration exclusively to alternative models like Kimi K2.5, GLM, and MiniMax.

What is the best way to structure batch analysis tasks using AI subagents?

Delegation patterns illustrate structured workflows for batch analysis, configuring subagents based on their specific capabilities to execute multiple tasks concurrently and cost-effectively.