Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →waybarrios/hf-cloud-sagemaker-deployment-planner
Plan and coordinate the deployment of a model to Amazon SageMaker AI.
Passed 14 of 20 test cases with the skill, and 8 of 20 without it.
and 5 more in the full report
7 fixed8 passed either way6 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want to deploy the custom classification model my team fine-tuned last week onto SageMaker. What discovery questions do you need answered to build my plan?
| Checked | Without skill | With skill |
|---|---|---|
| Asks for the S3 artifact path or exact location of the model weights. | Missed | Passed |
| Does not ask the user for their AWS region. | Passed | Passed |
The instructions your model reads when the skill loads.
You are helping a user deploy a model to Amazon SageMaker. Most users invoking this skill want the model deployed with reasonable defaults, in as few questions as possible. Ask only what you need, recommend a pathway honestly, and hand off to the specialized skills.
hf-cloud-aws-context-discovery, then hf-cloud-python-env-setuphf-cloud-sagemaker-iam-preflighthf-cloud-serving-image-selectionhf-cloud-sagemaker-production-defaultsPhases 1–2 are this skill's job. The others activate when their patterns match.
You will eventually need to know:
-embed-*, starting with BAAI/bge-, sentence-transformers/* etc. is embeddings; chat/instruct models are LLMs). Only ask if it's genuinely ambiguous.Region comes from hf-cloud-aws-context-discovery — don't ask unless the user volunteers it.
Do not front-load all of these. A common minimal set is just: what model, and roughly how often will it be called? The model name usually settles the model-type question. That alone is often enough to narrow the pathway to two candidates. If the user already told you something, don't ask again.
| Pathway | When it fits | When it does not |
|---|---|---|
| Real-time endpoint | Steady traffic, sub-second to few-second latency, always-on | Very spiky or very sparse traffic (wastes money on idle) |
| Serverless inference | Spiky/intermittent, tolerates cold starts (~10s+), simpler models | LLMs above a few B params (memory/cold-start limits), strict SLAs |
| Async inference | Long inference (>60s), large payloads, queue-friendly | Interactive synchronous calls |
| Batch transform | Offline scoring over a dataset | Anything online or interactive |
| Bedrock Custom Model Import | Wants Bedrock-compatible API, supported base family, weights only | Custom inference logic, unsupported architectures |
For LLMs, real-time endpoints are the default unless traffic is explicitly spiky/sparse or inference is long-running. Serverless looks attractive for "low traffic" cases but most LLMs exceed its memory limits.
test cases passed, vs 8 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.