skills.rest
jonnymuir
jonnymuirCOMMUNITY
Explore all skills by this author →
Website𝕏@jonnymooGitHub

Model Selection

Select optimal LLM models via hierarchical resolution and config.json overrides.

1|Updated Dec 23, 2025
Search Tags:#automation#optimization#llm#configuration#model-selection#agent-framework
One-click install
npx skills add https://github.com/jonnymuir/Umbraco.Prism --skill model-selection-jonnymuir
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Model Selection
Source: https://github.com/jonnymuir/Umbraco.Prism/tree/main/.copilot/skills/model-selection
Command: npx skills add https://github.com/jonnymuir/Umbraco.Prism --skill model-selection-jonnymuir

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of inconsistent model performance and unpredictable costs by providing a structured, hierarchical system for selecting the optimal LLM for specific agent tasks.

Core Features & Use Cases

  • Hierarchical Resolution: Automatically selects models based on a 5-layer priority system ranging from persistent user preferences to task-aware defaults.
  • Persistent Configuration: Allows users to define global or agent-specific model overrides that persist across sessions via a configuration file.
  • Intelligent Fallbacks: Implements robust fallback chains to ensure task continuity if a specific model tier becomes unavailable.

Quick Start

Instruct the system to always use a specific model for a particular agent by stating that you want to use claude-sonnet-4.6 for the researcher agent.

Frequently Asked Questions about Model Selection

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

FAQPage Schema
How do I optimize LLM costs across different agent tasks?▼

You can optimize LLM costs by using a hierarchical model selection system that enforces cost-tier constraints and provides intelligent fallbacks. This ensures the optimal LLM is chosen for specific agent tasks, balancing performance and predictable expenses.

How do I configure a specific LLM model for an individual agent?▼

To configure a specific LLM model for an agent, you instruct the system to use your desired model for that agent. This preference is then maintained as a persistent agent-specific override in a configuration file.

How does hierarchical model selection work for agent frameworks?▼

Hierarchical model selection works by evaluating a 5-layer priority system ranging from persistent user preferences to task-aware defaults. This chain ensures the most appropriate LLM is selected for agent execution based on context.

What happens if my preferred LLM becomes unavailable during agent execution?▼

If a specific model tier becomes unavailable, robust fallback logic ensures task continuity. The hierarchical resolution chain automatically selects an alternative LLM to prevent execution failure.

Do I need a configuration file to manage persistent LLM model preferences?▼

Yes, you need read and write access to a .squad/config.json file to maintain persistent model preferences. This file stores global and agent-specific overrides that persist across sessions.

Related Skills

Explore More Software Engineering Skills→
elbrunoelbruno
2

Model Selection

Resolve LLM models for agent spawns using layered configuration and task-aware selection.

Community
Intermediate
Mr-Fang-VLSIMr-Fang-VLSI
8

bscost-theory-opt

Develop theory-grounded backside cost optimization models and validate them against gate-based promotion criteria.

Community
Advanced
webmaxruwebmaxru
49

Model Selection

Resolve LLM models per agent spawn using a five-layer hierarchy and persist to .squad/config.json.

Community
Advanced
QuintenpsQuintenps

Model Selection

Resolve optimal LLM models for agent spawns via hierarchical configuration.

Community
Intermediate