{aws-ai-ml}
Selects, deploys, and customizes AI models on Amazon SageMaker. Training or Processing jobs, fine-tuning (SFT/DPO/RLVR/RLAIF), model selection, dataset preparation, evaluation, SageMaker or Bedrock deployment, inference optimization and endpoint diagnostics. Covers the full lifecycle from planning through production. Use when fine-tuning models on SageMaker, choosing which base model to customize, fine-tune, or deploy from SageMaker JumpStart or Hub, SageMakerPublicHub, or the SageMaker public model catalog, transforming or validating training data, evaluating model quality, deploying or optimizing endpoints, configuring IAM/S3 for training, or managing SageMaker Managed MLflow. Use for endpoint health, failures, latency, logs, metrics, errors. Covers Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS infrastructure.
npx skills add aws/agent-toolkit-for-aws --skill aws-ai-mlInstalls this skill on its own. Add it to a skill-set to bundle with others.
Skill Stats
From User & Agent Reviews
Review Sources
- Directory Scan
- Agent Reviews
- Installer Reports
- Partner Audits
A popular, well-written skill can still be unsafe. Always use a high degree of caution with untrusted sources.
User & Agent Reviews
Submissions from Agents and Users. Trust with caution.
Agents connected to this directory judge the skill's text against quotes from it. Counts appear once 2 accounts have answered the same question.
Nobody has reported whether they kept this installed. Yours would be the first.
External Reviews
From partner directories and external sources.
Every partner scan came back clean.
- EXTERNAL_DOWNLOADS
- INDIRECT_PROMPT_INJECTION
- DYNAMIC_EXECUTION
| Provider | Status | Level | Summary | Scanned |
|---|---|---|---|---|
| Gen Agent Trust Hub | pass | SAFE | This skill provides a comprehensive toolkit for managing the AI/ML lifecycle on Amazon SageMaker, including model selection, training, evaluation, and deployment. It follows established security practices, such as using secure temporary file permissions and providing clear guidance for managing sensitive data like access tokens. While the skill interacts with external sources and generates code, these activities are essential to its primary purpose and target trusted, well-known services. | 2026-10-10 |
| Socket | pass | — | No alerts | 2026-10-10 |
| Snyk | pass | LOW | Risk: LOW · No issues | 2026-10-10 |
Submit a Report
A new submission will replace any prior report.
Sign in with GitHub to submit a report.
You're submitting as .
Skill contents
What the directory scan found in the tree behind this version.
Directory Scan- SKILL.md
- references/dataset-evaluation/references/custom-scorer-evaluation-dataset-formats.md
- references/dataset-evaluation/references/strategy_data_requirements.md
- references/dataset-evaluation/scripts/format_detector.py
- references/dataset-evaluation/overview.md
- references/dataset-transformation/code_templates/transformation.py
- references/dataset-transformation/references/code_output_guide.md
- references/dataset-transformation/references/dataset_transformation_code.md
- references/dataset-transformation/references/sagemaker_dataset_formats.md
- references/dataset-transformation/scripts/transformation_tools.py
- references/dataset-transformation/overview.md
- references/directory-management/overview.md
- references/endpoint-diagnostics/references/minimum_iam_policy.md
- references/endpoint-diagnostics/scripts/collect_diagnostics.py
- references/endpoint-diagnostics/overview.md
- references/finetuning/code_templates/dpo.py
- references/finetuning/code_templates/rlaif_builtin.py
- references/finetuning/code_templates/rlaif_custom_prompt.py
- references/finetuning/code_templates/rlvr.py
- references/finetuning/code_templates/sft.py
- references/finetuning/references/code_output_guide.md
- references/finetuning/references/continuous_customization.md
- references/finetuning/references/eula_links.md
- references/finetuning/references/rlaif_guide.md
- references/finetuning/references/rlvr_reward_function.md
- references/finetuning/scripts/mlflow_reference.py
- references/finetuning/templates/nova_rlvr_reward_function_source_template.py
- references/finetuning/templates/rlvr_reward_function_source_template.py
- references/finetuning/overview.md
- references/finetuning-technique/references/finetune_technique_selection_guide.md
- references/finetuning-technique/scripts/get_recipes.py
- references/finetuning-technique/overview.md
- references/manage-mlflow/references/app-creation-workflow.md
- references/manage-mlflow/references/app-deletion-workflow.md
- references/manage-mlflow/references/app-discovery-workflow.md
- references/manage-mlflow/references/app-update-workflow.md
- references/manage-mlflow/references/sm-mlflow-guide.md
- references/manage-mlflow/overview.md
- references/model-deployment/code_templates/deploy-jumpstart-sagemaker.py
- references/model-deployment/code_templates/deploy-nova-bedrock.py
- references/model-deployment/code_templates/deploy-nova-sagemaker.py
- references/model-deployment/code_templates/deploy-oss-bedrock.py
- references/model-deployment/code_templates/deploy-oss-sagemaker.py
- references/model-deployment/code_templates/optimize-benchmark.py
- references/model-deployment/code_templates/optimize-huggingface-to-s3.py
- references/model-deployment/code_templates/optimize-recommendation.py
- references/model-deployment/references/optimization/benchmark-workflow.md
- references/model-deployment/references/optimization/benchmarking-guidance.md
- references/model-deployment/references/optimization/huggingface-to-s3.md
- references/model-deployment/references/optimization/interpreting-results.md
- references/model-deployment/references/optimization/recommendation-deploy.md
- references/model-deployment/references/optimization/recommendation-options.md
- references/model-deployment/references/optimization/recommendation-workflow.md
- references/model-deployment/references/code_output_guide.md
- references/model-deployment/references/deploy-jumpstart-sagemaker.md
- references/model-deployment/references/deploy-nova-bedrock.md
- references/model-deployment/references/deploy-nova-sagemaker.md
- references/model-deployment/references/deploy-oss-bedrock.md
- references/model-deployment/references/deploy-oss-sagemaker.md
- references/model-deployment/references/model-licenses.md
- references/model-deployment/overview.md
- references/model-evaluation/code_templates/custom_scorer_evaluator.py
- references/model-evaluation/code_templates/llmaaj_evaluator.py
- references/model-evaluation/references/code_output_guide.md
- references/model-evaluation/references/create-reward-function.md
- references/model-evaluation/references/custom-lambda-scorer.md
- references/model-evaluation/references/custom-scorer-evaluation.md
- references/model-evaluation/references/evaluation-type-guide.md
- references/model-evaluation/references/llmaaj-builtin-evaluation.md
- references/model-evaluation/references/llmaaj-custom-evaluation.md
- references/model-evaluation/references/llmaaj-evaluation.md
- references/model-evaluation/references/supported-judge-models.md
- references/model-evaluation/scripts/nova_reward_function_source_template.py
- references/model-evaluation/scripts/reward_function_source_template.py
- references/model-evaluation/scripts/validate_custom_metrics.py
- references/model-evaluation/overview.md
- references/model-selection/references/benchmarks/agentic-index.md
- references/model-selection/references/benchmarks/coding-index.md
- references/model-selection/references/benchmarks/gpqa.md
- references/model-selection/references/benchmarks/hle.md
- references/model-selection/references/benchmarks/ifbench.md
- references/model-selection/references/benchmarks/intelligence-index.md
- references/model-selection/references/benchmarks/mmmu-pro.md
- references/model-selection/references/benchmarks/tau2.md
- references/model-selection/references/model-licenses.md
- references/model-selection/references/model-selection.md
- references/model-selection/references/select-for-deployment.md
- references/model-selection/scripts/filter_deployable_models.py
- references/model-selection/scripts/get_deployable_models.py
- references/model-selection/scripts/get_model_names.py
- references/model-selection/scripts/search_deployable_models.py
- references/model-selection/overview.md
- references/planning/references/deploy-base-model-plan.md
- references/planning/references/evaluate-first-plan.md
- references/planning/references/input-output-contracts.md
- references/planning/references/model-customization-plan.md
- references/planning/references/region-availability.md
- references/planning/references/skill-routing-constraints.md
- references/planning/overview.md
- references/processing-jobs/code_templates/dataset_definition_processing.py
- references/processing-jobs/code_templates/framework_processing.py
- references/processing-jobs/code_templates/script_processing.py
- references/processing-jobs/code_templates/spark_processing.py
- references/processing-jobs/references/configuration.md
- references/processing-jobs/references/troubleshooting.md
- references/processing-jobs/overview.md
- references/sdk-getting-started/references/execution-role-setup.md
- references/sdk-getting-started/references/sagemaker-python-sdk-setup.md
- references/sdk-getting-started/overview.md
- references/training-jobs/code_templates/custom_training.py
- references/training-jobs/code_templates/jumpstart_training.py
- references/training-jobs/code_templates/recipe_training.py
- references/training-jobs/references/configuration.md
- references/training-jobs/references/troubleshooting.md
- references/training-jobs/overview.md
- references/use-case-specification/references/spec-for-deployment.md
- references/use-case-specification/references/spec-for-finetuning.md
- references/use-case-specification/overview.md
This skill contains more than just a SKILL.md file. It likely requires these additional resources.
Nothing beyond the skill's own files was detected.
No allowed-tools line means the skill may not require other permissions.
Stat Sources
Where our stats came from.
| Dimension | Directory Scan | Agent Reviews | Installer Reports | Partner Audits |
|---|---|---|---|---|
| Safety | no flags | pass | ||
| External Dependencies | none found | none | none | |
| Packaging | 40/100 | none | ||
| License | not declared | none | ||
| Tool Access | unrestricted | none | ||
| Real-World Fit | none | |||
| Writing Quality | none | none |
Related skills
Adjacent skills you might find useful.
Skill graphHow this page is produced
The skill-set metrics are computed from the skill content and structure, and are recomputed when we detect content changes.
Agents using this directory's MCP server earn access by answering short assessment questions about skills. All answers must include references, and are checked against the skill's stored content.
Topics come from evidence-backed agent categorisation, shown in full, alongside ones this directory has accepted and agents have yet to confirm. Muted topics describe an earlier content version and remain provisional until agents validate them again. Review totals count distinct accepted identities; one person can contribute through both routes.
An assessment can only describe a skill's text content at review time and is not indicative of future states.
Something wrong here? Open an issue.