Model Selection

SkillAI & models

This skill helps your AI pick the right base model for what you are trying to do. It looks up the models available through SageMaker Hub, compares the options, and recommends one that fits your use case. It also helps when you want to change your current model or evaluate a specific one like Llama, Mistral, or Nova.

Available today. Use it from your connected AI after setup.

After adding the skill, ask your AI which model it would choose for your task, or mention a model or model family you have in mind. It will look up the available options and walk you through the comparison.

Then ask your AI: use the Model Selection skill

What your AI can do with it

  • Recommend a base model that fits your use case
  • Search the models available in SageMaker Hub
  • Compare model options so you can see which fits best
  • Help you switch to a different base model
  • Evaluate a specific base model before you commit to it

What this skill tells your AI

The instructions your AI receives, as published by awslabs/agent-plugins in plugins/sagemaker-ai/skills/model-selection/SKILL.md and read by ahel’s review.

Guides the user through selecting a base model based on their use case.

When to Use

  • User asks which model to use
  • User wants to select or change their base model
  • User mentions a model name or family (e.g., "Llama", "Mistral", "Nova") — the exact Hub model ID still needs to be resolved
  • User wants to evaluate a base model before deciding whether to finetune

Prerequisites

  • A use_case_spec.md file exists. If not, activate the use-case-specification skill to generate it first.

Workflow

Step 1: Check Region

Run:

python -c "import boto3; print(boto3.session.Session().region_name)"
  • None → STOP. Tell user: "Set your region via export AWS_DEFAULT_REGION=us-west-2 or aws configure."
  • Set → store REGION in context, continue.

Step 2: Discover Hub

  1. List all available SageMaker Hubs in the user's region by calling the SageMaker ListHubs API using the aws___call_aws tool.

  2. From the results, filter out any hub whose HubDescription contains "AI Registry" — these do not contain JumpStart models.

  3. The remaining hubs are eligible (e.g., SageMakerPublicHub and any private hubs).

  4. If exactly one eligible hub exists, use it automatically — do not ask the user.

  5. If multiple eligible hubs exist, present them to the user and ask which one to use. Example:

    I found the following model hubs:
    - SageMakerPublicHub — SageMaker Public Hub
    - Private-Hub-XYZ — Private Hub models
    Which hub would you like to use?
    
  6. Store the selected hub name for use in subsequent steps.

Step 3: Select Base Model

First, retrieve all available SageMaker Hub model names by running: python model-selection/scripts/get_model_names.py <hub-name>.

Present all available models to the user with their licenses before making any recommendations. Cross-reference the model list with references/model-licenses.md and display each as <model name> - [<license>](<url>). For example: "Qwen3-4B - Apache 2.0"

If you already know the model the user wants to use (from conversation context or planning files), confirm that it's in the list, display its license, and move on. Otherwise, help the user pick a model following the instructions in references/model-selection.md. Important: Make sure to remember this list of available models when helping with model selection. Don't recommend a model that's not available to the user.

Step 4: Confirm Selection

Present a summary to the user:

Here's what we've selected:
- Base model: [model name]

Ask if they'd like to proceed with this model.

References

  • references/model-selection.md — Model selection instructions and benchmark descriptions
  • references/model-licenses.md — Model license information for display during model selection

Signals

GitHub stars
893
Forks
153
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
model-selection
Source
github.com/awslabs/agent-plugins