skills.rest
JacobPEvans
JacobPEvansCOMMUNITY
Explore all skills by this author →
GitHub

delegate-to-ai

Route tasks to specialized AI models and PAL MCP tools.

3|1|Updated Jan 1, 2026
Search Tags:#task optimization#llm#multi-model#model routing#ai delegation#pal mcp
One-click install
npx skills add https://github.com/JacobPEvans/claude-code-plugins --skill delegate-to-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: delegate-to-ai
Source: https://github.com/JacobPEvans/claude-code-plugins/tree/main/ai-delegation/skills/delegate-to-ai
Command: npx skills add https://github.com/JacobPEvans/claude-code-plugins --skill delegate-to-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the challenge of selecting the most appropriate AI model for a given task, optimizing for cost, performance, and specific capabilities.

Core Features & Use Cases

  • Intelligent Model Routing: Automatically directs tasks to specialized AI models (e.g., Gemini, DeepSeek, Ollama) based on task type and constraints.
  • PAL MCP Tool Integration: Leverages a suite of PAL MCP tools (chat, clink, consensus, codereview, planner, precommit) for diverse AI interactions.
  • Use Case: When faced with a complex code review requiring multiple perspectives, this Skill can route the task to a consensus tool utilizing various models to ensure comprehensive feedback.

Quick Start

Use the delegate-to-ai skill to route a complex code review task to the consensus tool.

Frequently Asked Questions about delegate-to-ai

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

FAQPage Schema
How do I route coding tasks to specialized AI models like Gemini or DeepSeek?▼

Multi-model AI routing allocates tasks to specialized external models based on task type and constraints. It facilitates efficient AI resource allocation for research, coding, and architecture planning by selecting the most appropriate model for cost and performance optimization.

Can I use local Ollama deployments for code review and architecture planning?▼

Yes, you can use local Ollama deployments for code review and architecture planning. The routing mechanism supports both cloud-based models and local Ollama deployments, ensuring flexible AI resource allocation across diverse development tasks.

What is the best way to get multiple AI perspectives on a complex code review?▼

The best way to get multiple AI perspectives on a complex code review is to route the task to a consensus tool. This utilizes various specialized models to ensure comprehensive feedback and thorough analysis of your codebase.

Does this AI task routing approach require specific tools for research and planning?▼

This AI task routing leverages a flexible toolset including chat, clink, consensus, codereview, and planner tools. These PAL MCP tools facilitate diverse AI interactions for research, coding, code review, and architecture planning tasks.

When should I use dynamic model routing instead of a single AI model?▼

You should use dynamic model routing when you need to optimize for cost, performance, and specific capabilities across different task types. It solves the challenge of selecting the most appropriate AI model for varying constraints like research versus coding.

Related Skills

Explore More Software Engineering Skills→
davekilleendavekilleen
461

ai-setup

Configure budget cloud and local Ollama AI models with smart routing.

Community
Advanced
tclemtclem
11

designing-before-coding

Create structured implementation plans before coding new features.

Community
Intermediate
Tony363Tony363
19

sc-code-review

Review git commits, staged changes, or branch differences with multi-model consensus.

Community
Advanced
stratagastrataga

openrouter-aider-orchestration

Coordinates AirSim and ROS for realistic drone and vehicle simulations.

Community
Advanced