sagemaker-endpoint-deployer

Sagemaker Endpoint Deployer - Auto-activating skill for ML Deployment. Triggers on: sagemaker endpoint deployer, sagemaker endpoint deployer Part of the ML Deployment skill category.

0.98x

Quality

Does it follow best practices?

Impact

87%

0.98x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/08-ml-deployment/sagemaker-endpoint-deployer/SKILL.md

Evaluation results

93%

11%

Deploy Customer Churn Prediction Model to SageMaker

Production-ready deployment code

Criteria

Without context

With context

Step-by-step structure

100%

Error handling present

20%

50%

Logging included

100%

Parameterized values

100%

Endpoint validation

100%

Endpoint health check

100%

80%

IAM role referenced

100%

Resource cleanup option

75%

100%

Model artifact S3 path

100%

Best-practice instance type

100%

Container image referenced

100%

Without context: $0.3804 · 1m 43s · 18 turns · 19 in / 6,598 out tokens

With context: $0.4971 · 2m 8s · 24 turns · 56 in / 7,570 out tokens

100%

Automated MLOps Pipeline for Fraud Detection Model

MLOps pipeline and monitoring setup

Criteria

Without context

With context

Pipeline stages documented

100%

Monitoring configuration

100%

Data capture enabled

100%

Model versioning addressed

100%

Best-practice IAM mentioned

100%

Alerting or thresholds defined

100%

Automated retraining trigger

100%

Production optimization mentioned

100%

Step-by-step organization

100%

Validation step present

100%

Without context: $0.4275 · 2m 35s · 12 turns · 54 in / 10,370 out tokens

With context: $0.6753 · 3m 40s · 24 turns · 287 in / 13,123 out tokens

68%

-14%

Optimize and Validate a High-Traffic SageMaker Recommendation Endpoint

Endpoint optimization and output validation

Criteria

Without context

With context

Auto-scaling configuration

100%

Scaling metric specified

100%

Instance type justification

75%

25%

Async inference considered

Endpoint invocation test

100%

Response schema validation

100%

Latency benchmark

100%

Cold-start mitigation

50%

Cost optimization step

75%

50%

Step-by-step guidance

100%

Error handling in validation

100%

Without context: $0.2836 · 1m 21s · 12 turns · 13 in / 5,519 out tokens

With context: $0.3187 · 1m 38s · 18 turns · 99 in / 5,927 out tokens

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: f17dd51

Evaluated: 17 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Deploy Customer Churn Prediction Model to SageMaker Automated MLOps Pipeline for Fraud Detection Model Optimize and Validate a High-Traffic SageMaker Recommendation Endpoint

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.