← Explore all skills

CLOUD OPERATIONS / huggingface

Hugging Face SageMaker Deployment Templates

Review endpoint creation, scaling and alarm templates as one deployment plan.

“Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.”

01 / THE REASONING

Why this made the selection.

  • _common.py waits for InService but does not test inference; deploy.py creates scaling/alarms after the endpoint, while teardown.py ignores several deletion results.
  • Prepare a real-time endpoint with explicit scaling targets, tags and latency/error alarms.

02 / THE REVIEW RECORD

What we actually inspected.

Source review has boundaries.
A clear record is more useful than a “safe” badge.

Material inspected

  • skills/hf-cloud-sagemaker-production-defaults/SKILL.md
  • skills/hf-cloud-sagemaker-production-defaults/scripts/_common.py
  • skills/hf-cloud-sagemaker-production-defaults/scripts/deploy.py
  • skills/hf-cloud-sagemaker-production-defaults/scripts/teardown.py
  • LICENSE
  • README.md

Our findings

  • _common.py waits for InService but does not test inference; deploy.py creates scaling/alarms after the endpoint, while teardown.py ignores several deletion results.

Not established by this review

  • Third-party instructions and helpers were not executed; service access, host compatibility and outcomes remain untested.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

Add a skill to your workflow.

Upstream setup instructions ↗

DOCUMENTED COMMAND

npx skills add huggingface/skills/skills/hf-cloud-sagemaker-production-defaults

Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.

Optional: install the reviewed revision

Keeps the original source and installer version where recorded, while leaving your AI tools and installation scope for you to choose.

npx skills add https://github.com/huggingface/skills/tree/c3ff942be3e07116b475253f0a8fc4f54682c1a8/skills/hf-cloud-sagemaker-production-defaults
  1. Install the pinned directory interactively and retain its referenced files; inspect the source before granting tool access.
  2. Review container, role, S3 model and endpoint names; inspect create/teardown code, set notification targets and independently verify resources after deployment or cleanup.

Before you start

  • AWS CLI, boto3/botocore, model/container artifacts and scoped SageMaker, scaling and monitoring permissions

04 / FOLLOW THE EVIDENCE

The source trail.

Our notes are separate from the original resource.
Check upstream before adopting a new version.

  1. https://github.com/huggingface/skills/blob/c3ff942be3e07116b475253f0a8fc4f54682c1a8/skills/hf-cloud-sagemaker-production-defaults/SKILL.md

    Supports: summary, review, install, access, limitations

  2. https://github.com/huggingface/skills/blob/c3ff942be3e07116b475253f0a8fc4f54682c1a8/skills/hf-cloud-sagemaker-production-defaults/scripts/_common.py

    Supports: summary, review, install, access, limitations

  3. https://github.com/huggingface/skills/blob/c3ff942be3e07116b475253f0a8fc4f54682c1a8/skills/hf-cloud-sagemaker-production-defaults/scripts/deploy.py

    Supports: summary, review, install, access, limitations

  4. https://github.com/huggingface/skills/blob/c3ff942be3e07116b475253f0a8fc4f54682c1a8/skills/hf-cloud-sagemaker-production-defaults/scripts/teardown.py

    Supports: summary, review, install, access, limitations

  5. Pinned LICENSE ↗Checked

    https://github.com/huggingface/skills/blob/c3ff942be3e07116b475253f0a8fc4f54682c1a8/LICENSE

    Supports: license

  6. Pinned README.md ↗Checked

    https://github.com/huggingface/skills/blob/c3ff942be3e07116b475253f0a8fc4f54682c1a8/README.md

    Supports: summary, review, install, access, limitations

Evidence & Ask