skills.rest
awslabs
awslabsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

sdk-getting-started

Validates SageMaker SDK version, AWS region, and execution role before ML operations.

881|152|Updated Feb 5, 2026
Search Tags:#AWS#iam#boto3#environment validation#SDK setup#Sagemaker#execution role
One-click install
npx skills add https://github.com/awslabs/agent-plugins --skill sdk-getting-started
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sdk-getting-started
Source: https://github.com/awslabs/agent-plugins/tree/main/plugins/sagemaker-ai/skills/sdk-getting-started
Command: npx skills add https://github.com/awslabs/agent-plugins --skill sdk-getting-started

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires sagemaker, boto3, and includes references (resource) components.

What problem does it solve?

Before running SageMaker AI training, evaluation, or deployment jobs, users often hit failures caused by outdated SDK versions, missing AWS region configuration, or misconfigured IAM execution roles. This Skill runs preflight environment checks so these issues are caught and resolved upfront instead of mid-workflow.

Core Features & Use Cases

  • SDK Version Verification: Checks that the SageMaker Python SDK is installed at version 3.7.1 or higher, and installs or upgrades it when needed.
  • Region Detection: Resolves the AWS region programmatically via boto3 and stores it in conversation context for downstream steps.
  • Execution Role Validation: Auto-detects the SageMaker execution role, verifies its trust policy for sagemaker.amazonaws.com, bedrock.amazonaws.com, and lambda.amazonaws.com, and warns about missing trusts.
  • Use Case: A data scientist about to launch a SageMaker training job asks the agent to check their environment; the Skill confirms SDK 3.8.0, region us-east-1, and a valid execution role, flagging a missing Bedrock trust before any job is submitted.

Quick Start

Ask the agent to check whether my environment is set up correctly for SageMaker training jobs.

Frequently Asked Questions about sdk-getting-started

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

FAQPage Schema
How do I check my SageMaker Python SDK version?▼

Run python -c "from importlib.metadata import version; print(version('sagemaker'))" to print the installed version. SageMaker AI operations require version 3.7.1 or higher; upgrade with pip install --upgrade 'sagemaker>=3.7.1' boto3.

How do I find my SageMaker execution role ARN?▼

Run python -c "from sagemaker.core.helper.session_helper import get_execution_role; print(get_execution_role())" to auto-detect the role. If that fails, provide the full IAM role ARN manually, such as arn:aws:iam::123456789012:role/MySageMakerRole.

What trust policy does a SageMaker execution role need?▼

The role's trust policy must include sagemaker.amazonaws.com as a service principal. For Bedrock workflows add bedrock.amazonaws.com, and for RLVR reward functions add lambda.amazonaws.com, otherwise those steps will fail.

Why does pip install of the SageMaker SDK fail?▼

Install failures are usually system-level issues such as missing C build tools (gcc, python3-devel), an incompatible Python version, or network and proxy restrictions. Retrying with --no-deps or extras like [core] produces a broken partial install and should be avoided.

Does AmazonSageMakerFullAccess cover all S3 buckets?▼

No. The AmazonSageMakerFullAccess managed policy only grants S3 access to buckets with "sagemaker" in the name. If your training data lives in other buckets, attach a supplemental S3 policy to the execution role.

Related Skills

Explore More Software Engineering Skills→
huggingfacehuggingface
10.9k

hf-cloud-sagemaker-iam-preflight

Verify or create AWS SageMaker IAM execution roles with AWS CLI.

Official
Advanced
AndreKuraitAndreKurait

aws-cleanrooms

Diagnose AWS Clean Rooms permission, access, and logging issues.

Community
Advanced
aws-samplesaws-samples
37

aws-setup

Guide AWS Workshop Studio login and configure temporary AWS CLI credentials for SageMaker Studio access.

Official
Intermediate
tilmon-engineeringtilmon-engineering
3

starting-an-iteration

Load prior iteration context and initialize a new workspace with journal and TodoWrite tracker.

Official
Basic