mcpField
S
sdk-getting-started

sdk-getting-started

github.com/awslabsCloud & DevOps93270 installsUpdated 3w ago
Repository

About sdk-getting-started

A skill that runs preflight checks for SageMaker AI operations, resolving the region and execution role before asking for user input. It records the results in conversation context for later skills.

Key features

  1. 01SageMaker Python SDK version checks
  2. 02Programmatic region resolution
  3. 03Execution role validation
  4. 04Results stored for downstream skills

Use cases

  1. 01Check environment readiness before SageMaker operations
  2. 02Resolve an execution role for later workflows

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/awslabs/agent-plugins --skill sdk-getting-started

After installing, type/sdk-getting-startedin Claude Code to confirm it loaded.

Bundled filesreferences/execution-role-setup.mdreferences/sagemaker-python-sdk-setup.md

Details

From the project README

SDK Getting Started

Preflight checks to verify the user's environment can run SageMaker AI operations. The agent runs these checks directly (no code generation) and stores results in conversation context for downstream skills.

Principles

  1. Don't ask for what you can look up. Resolve region and role programmatically before asking the user.

Workflow

Read and follow references/sagemaker-python-sdk-setup.md.

References

  • references/sagemaker-python-sdk-setup.md - SageMaker Python SDK version, region, and execution role checks
  • references/execution-role-setup.md — Execution role resolution and validation

Comments

Markdown supported