model-selection

Name: model-selection
Author: awslabs

843stars132forks

How to install model-selection?

awslabs/agent-plugins/model-selection

$npx -y skills add awslabs/agent-plugins --skill model-selection

Installs into the current project.

Summary

Selects a base model for the user's use case by querying SageMaker Hub. Use when the user asks which model to use, wants to select or change their base model, mentions a model name or family (e.g., "Llama", "Mistral", "Nova"), or wants to evaluate a base model — always activate e

Files · 1

View on GitHub

SKILL.md

1	# Model Selection
2
3	Guides the user through selecting a base model based on their use case.
4
5	## When to Use
6
7	- User asks which model to use
8	- User wants to select or change their base model
9	- User mentions a model name or family (e.g., "Llama", "Mistral", "Nova") — the exact Hub model ID still needs to be resolved
10	- User wants to evaluate a base model before deciding whether to finetune
11
12	## Prerequisites
13
14	- A `use_case_spec.md` file exists. If not, activate the use-case-specification skill to generate it first.
15
16	## Workflow
17
18	### Step 1: Check Region
19
20	Run:
21
22	```
23	python -c "import boto3; print(boto3.session.Session().region_name)"
24	```
25
26	- `None` → STOP. Tell user: "Set your region via `export AWS_DEFAULT_REGION=us-west-2` or `aws configure`."
27	- Set → store REGION in context, continue.
28
29	### Step 2: Discover Hub
30
31	1. List all available SageMaker Hubs in the user's region by calling the SageMaker `ListHubs` API using the `aws___call_aws` tool.
32	2. From the results, filter out any hub whose `HubDescription` contains "AI Registry" — these do not contain JumpStart models.
33	3. The remaining hubs are eligible (e.g., `SageMakerPublicHub` and any private hubs).
34	4. If exactly one eligible hub exists, use it automatically — do not ask the user.
35	5. If multiple eligible hubs exist, present them to the user and ask which one to use. Example:
36
37	```
38	I found the following model hubs:
39	- SageMakerPublicHub — SageMaker Public Hub
40	- Private-Hub-XYZ — Private Hub models
41	Which hub would you like to use?
42	```
43
44	6. Store the selected hub name for use in subsequent steps.
45
46	### Step 3: Select Base Model
47
48	First, retrieve all available SageMaker Hub model names by running: `python model-selection/scripts/get_model_names.py <hub-name>`.
49
50	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](https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE)"
51
52	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`.
53	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.
54
55	### Step 4: Confirm Selection
56
57	Present a summary to the user:
58
59	```
60	Here's what we've selected:
61	- Base model: [model name]
62	```
63
64	Ask if they'd like to proceed with this model.
65
66	## References
67
68	- `references/model-selection.md` — Model selection instructions and benchmark descriptions
69	- `references/model-licenses.md` — Model license information for display during model selection

People who liked this also viewed

6 picks

Type

model-selection

843stars132forks

View on GitHub

How to install model-selection?

awslabs/agent-plugins/model-selection

$npx -y skills add awslabs/agent-plugins --skill model-selection

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Model Selection
2
3	Guides the user through selecting a base model based on their use case.
4
5	## When to Use
6
7	- User asks which model to use
8	- User wants to select or change their base model
9	- User mentions a model name or family (e.g., "Llama", "Mistral", "Nova") — the exact Hub model ID still needs to be resolved
10	- User wants to evaluate a base model before deciding whether to finetune
11
12	## Prerequisites
13
14	- A `use_case_spec.md` file exists. If not, activate the use-case-specification skill to generate it first.
15
16	## Workflow
17
18	### Step 1: Check Region
19
20	Run:
21
22	```
23	python -c "import boto3; print(boto3.session.Session().region_name)"
24	```
25
26	- `None` → STOP. Tell user: "Set your region via `export AWS_DEFAULT_REGION=us-west-2` or `aws configure`."
27	- Set → store REGION in context, continue.
28
29	### Step 2: Discover Hub
30
31	1. List all available SageMaker Hubs in the user's region by calling the SageMaker `ListHubs` API using the `aws___call_aws` tool.
32	2. From the results, filter out any hub whose `HubDescription` contains "AI Registry" — these do not contain JumpStart models.
33	3. The remaining hubs are eligible (e.g., `SageMakerPublicHub` and any private hubs).
34	4. If exactly one eligible hub exists, use it automatically — do not ask the user.
35	5. If multiple eligible hubs exist, present them to the user and ask which one to use. Example:
36
37	```
38	I found the following model hubs:
39	- SageMakerPublicHub — SageMaker Public Hub
40	- Private-Hub-XYZ — Private Hub models
41	Which hub would you like to use?
42	```
43
44	6. Store the selected hub name for use in subsequent steps.
45
46	### Step 3: Select Base Model
47
48	First, retrieve all available SageMaker Hub model names by running: `python model-selection/scripts/get_model_names.py <hub-name>`.
49
50	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](https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE)"
51
52	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`.
53	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.
54
55	### Step 4: Confirm Selection
56
57	Present a summary to the user:
58
59	```
60	Here's what we've selected:
61	- Base model: [model name]
62	```
63
64	Ask if they'd like to proceed with this model.
65
66	## References
67
68	- `references/model-selection.md` — Model selection instructions and benchmark descriptions
69	- `references/model-licenses.md` — Model license information for display during model selection

People who liked this also viewed

6 picks

Type