skills.rest
quaid-app
quaid-appOFFICIAL
Explore all skills by this author →
WebsiteGitHub

Model Selection

Resolve and persist LLM model choices per agent spawn in .squad/config.json.

3|3|Updated Apr 13, 2026
Search Tags:#llm#configuration#agents#coordinator#model-selection#spawn
One-click install
npx skills add https://github.com/quaid-app/quaid --skill model-selection-quaid-app
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Model Selection
Source: https://github.com/quaid-app/quaid/tree/main/.copilot/skills/model-selection
Command: npx skills add https://github.com/quaid-app/quaid --skill model-selection-quaid-app

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill ensures every agent spawn uses a chosen LLM model by enforcing a layered resolution policy and persisting user preferences.

Core Features & Use Cases

  • Unified model resolution across agent spawns with a first-match-wins approach across multiple sources (per-agent, global config, session directives, charter preferences, and fallbacks).
  • Persistent preferences stored in .squad/config.json to survive sessions and restarts.
  • Spawn acknowledgments that include the final resolved model for transparency and auditing.

Quick Start

Spawn a new agent and let Quaid apply the 5-layer model resolution to determine and persist the chosen model.

Frequently Asked Questions about Model Selection

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

FAQPage Schema
How do I configure a specific LLM model for each agent spawn?▼

To configure an LLM model for each agent spawn, this skill applies a 5-layer resolution policy that checks per-agent overrides, global config, session directives, charter preferences, and fallbacks using a first-match-wins approach.

Where are agent model preferences stored to ensure they survive restarts?▼

Agent model preferences are persisted in the .squad/config.json file, ensuring that resolved LLM model choices survive across multiple sessions and application restarts.

What is the best way to enforce deterministic model selection across multiple agents?▼

The best way to enforce deterministic model selection is by applying layered task-aware directives and per-agent overrides that resolve the exact LLM model needed before the spawn process initiates.

Can I verify which resolved LLM model was applied during an agent spawn?▼

Yes, you can verify the resolved LLM model because this skill includes the final chosen model directly within the spawn acknowledgment for complete transparency and auditing purposes.

Does global configuration override per-agent model settings when spawning agents?▼

No, global configuration does not override per-agent settings; the resolution policy uses a first-match-wins approach where per-agent overrides take priority over global config, session directives, and fallbacks.

When should I use task-aware directives for LLM model selection?▼

You should use task-aware directives for LLM model selection when specific spawn tasks require distinct capabilities, allowing the layered resolution to dynamically evaluate and apply the most appropriate model.

Related Skills

Explore More Software Engineering Skills→
webmaxruwebmaxru
49

Model Selection

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

Community
Advanced
Izak90Izak90

Model Selection

Resolve LLM models for agent spawns using a 5-layer hierarchy.

Community
Advanced
elbrunoelbruno
2

Model Selection

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

Community
Intermediate
lbouriezlbouriez

Model Selection

Determines the LLM model for each agent spawn using a layered priority approach.

Community
Advanced