Skip to content

opensite-ai/opensite-skills / aws-ai-ml

aws-ai-ml

Verified

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.

FileKindSize
.aws-skill-metadataother18 B
SKILL.mdskill md8.1 KB
references/dataset-evaluation/overview.mdmarkdown5.4 KB
references/dataset-evaluation/references/custom-scorer-evaluation-dataset-formats.mdmarkdown3.6 KB
references/dataset-evaluation/references/strategy_data_requirements.mdmarkdown4.8 KB
references/dataset-evaluation/scripts/format_detector.pyscript26.7 KB
references/dataset-transformation/code_templates/transformation.pyscript1.5 KB
references/dataset-transformation/overview.mdmarkdown13.3 KB
references/dataset-transformation/references/code_output_guide.mdmarkdown2.8 KB
references/dataset-transformation/references/dataset_transformation_code.mdmarkdown5.2 KB
references/dataset-transformation/references/sagemaker_dataset_formats.mdmarkdown2.9 KB
references/dataset-transformation/scripts/transformation_tools.pyscript4.8 KB
references/directory-management/overview.mdmarkdown1.9 KB
references/endpoint-diagnostics/overview.mdmarkdown3.5 KB
references/endpoint-diagnostics/references/minimum_iam_policy.mdmarkdown1.2 KB
references/endpoint-diagnostics/scripts/collect_diagnostics.pyscript12.8 KB
references/finetuning-technique/overview.mdmarkdown2.1 KB
references/finetuning-technique/references/finetune_technique_selection_guide.mdmarkdown2.3 KB
references/finetuning-technique/scripts/get_recipes.pyscript817 B
references/finetuning/code_templates/dpo.pyscript6.4 KB
references/finetuning/code_templates/rlaif_builtin.pyscript5.8 KB
references/finetuning/code_templates/rlaif_custom_prompt.pyscript6.3 KB
references/finetuning/code_templates/rlvr.pyscript6.5 KB
references/finetuning/code_templates/sft.pyscript6.1 KB
references/finetuning/overview.mdmarkdown11.4 KB
references/finetuning/references/code_output_guide.mdmarkdown3.2 KB
references/finetuning/references/continuous_customization.mdmarkdown8.4 KB
references/finetuning/references/eula_links.mdmarkdown7.3 KB
references/finetuning/references/rlaif_guide.mdmarkdown3.8 KB
references/finetuning/references/rlvr_reward_function.mdmarkdown10.0 KB
references/finetuning/scripts/mlflow_reference.pyscript841 B
references/finetuning/templates/nova_rlvr_reward_function_source_template.pyscript12.8 KB
references/finetuning/templates/rlvr_reward_function_source_template.pyscript9.1 KB
references/manage-mlflow/overview.mdmarkdown4.8 KB
references/manage-mlflow/references/app-creation-workflow.mdmarkdown3.2 KB
references/manage-mlflow/references/app-deletion-workflow.mdmarkdown2.3 KB
references/manage-mlflow/references/app-discovery-workflow.mdmarkdown1.5 KB
references/manage-mlflow/references/app-update-workflow.mdmarkdown1.7 KB
references/manage-mlflow/references/sm-mlflow-guide.mdmarkdown1.3 KB
references/model-deployment/code_templates/deploy-jumpstart-sagemaker.pyscript7.5 KB
references/model-deployment/code_templates/deploy-nova-bedrock.pyscript2.0 KB
references/model-deployment/code_templates/deploy-nova-sagemaker.pyscript1.9 KB
references/model-deployment/code_templates/deploy-oss-bedrock.pyscript4.0 KB
references/model-deployment/code_templates/deploy-oss-sagemaker.pyscript2.6 KB
references/model-deployment/code_templates/optimize-benchmark.pyscript4.6 KB
references/model-deployment/code_templates/optimize-huggingface-to-s3.pyscript2.0 KB
references/model-deployment/code_templates/optimize-recommendation.pyscript6.4 KB
references/model-deployment/overview.mdmarkdown16.6 KB
references/model-deployment/references/code_output_guide.mdmarkdown3.2 KB
references/model-deployment/references/deploy-jumpstart-sagemaker.mdmarkdown14.3 KB
references/model-deployment/references/deploy-nova-bedrock.mdmarkdown4.4 KB
references/model-deployment/references/deploy-nova-sagemaker.mdmarkdown5.8 KB
references/model-deployment/references/deploy-oss-bedrock.mdmarkdown5.2 KB
references/model-deployment/references/deploy-oss-sagemaker.mdmarkdown12.9 KB
references/model-deployment/references/model-licenses.mdmarkdown11.9 KB
references/model-deployment/references/optimization/benchmark-workflow.mdmarkdown12.7 KB
references/model-deployment/references/optimization/benchmarking-guidance.mdmarkdown8.9 KB
references/model-deployment/references/optimization/huggingface-to-s3.mdmarkdown3.1 KB
references/model-deployment/references/optimization/interpreting-results.mdmarkdown8.5 KB
references/model-deployment/references/optimization/recommendation-deploy.mdmarkdown1.5 KB
references/model-deployment/references/optimization/recommendation-options.mdmarkdown3.1 KB
references/model-deployment/references/optimization/recommendation-workflow.mdmarkdown10.3 KB
references/model-evaluation/code_templates/custom_scorer_evaluator.pyscript2.5 KB
references/model-evaluation/code_templates/llmaaj_evaluator.pyscript2.8 KB
references/model-evaluation/overview.mdmarkdown5.2 KB
references/model-evaluation/references/code_output_guide.mdmarkdown3.3 KB
references/model-evaluation/references/create-reward-function.mdmarkdown3.0 KB
references/model-evaluation/references/custom-lambda-scorer.mdmarkdown4.4 KB
references/model-evaluation/references/custom-scorer-evaluation.mdmarkdown10.5 KB
references/model-evaluation/references/evaluation-type-guide.mdmarkdown10.1 KB
references/model-evaluation/references/llmaaj-builtin-evaluation.mdmarkdown5.0 KB
references/model-evaluation/references/llmaaj-custom-evaluation.mdmarkdown2.5 KB
references/model-evaluation/references/llmaaj-evaluation.mdmarkdown14.6 KB
references/model-evaluation/references/supported-judge-models.mdmarkdown2.9 KB
references/model-evaluation/scripts/nova_reward_function_source_template.pyscript13.1 KB
references/model-evaluation/scripts/reward_function_source_template.pyscript9.2 KB
references/model-evaluation/scripts/validate_custom_metrics.pyscript3.5 KB
references/model-selection/overview.mdmarkdown10.3 KB
references/model-selection/references/benchmarks/agentic-index.mdmarkdown2.8 KB
references/model-selection/references/benchmarks/coding-index.mdmarkdown2.8 KB
references/model-selection/references/benchmarks/gpqa.mdmarkdown2.8 KB
references/model-selection/references/benchmarks/hle.mdmarkdown2.8 KB
references/model-selection/references/benchmarks/ifbench.mdmarkdown2.8 KB
references/model-selection/references/benchmarks/intelligence-index.mdmarkdown2.8 KB
references/model-selection/references/benchmarks/mmmu-pro.mdmarkdown3.0 KB
references/model-selection/references/benchmarks/tau2.mdmarkdown2.8 KB
references/model-selection/references/model-licenses.mdmarkdown7.3 KB
references/model-selection/references/model-selection.mdmarkdown8.2 KB
references/model-selection/references/select-for-deployment.mdmarkdown19.8 KB
references/model-selection/scripts/filter_deployable_models.pyscript10.1 KB
references/model-selection/scripts/get_deployable_models.pyscript21.7 KB
references/model-selection/scripts/get_model_names.pyscript1.4 KB
references/model-selection/scripts/search_deployable_models.pyscript34.9 KB
references/planning/overview.mdmarkdown10.3 KB
references/planning/references/deploy-base-model-plan.mdmarkdown699 B
references/planning/references/evaluate-first-plan.mdmarkdown1.8 KB
references/planning/references/input-output-contracts.mdmarkdown3.1 KB
references/planning/references/model-customization-plan.mdmarkdown1.5 KB
references/planning/references/region-availability.mdmarkdown1.2 KB
references/planning/references/skill-routing-constraints.mdmarkdown2.7 KB
references/processing-jobs/code_templates/dataset_definition_processing.pyscript4.1 KB
references/processing-jobs/code_templates/framework_processing.pyscript3.0 KB
references/processing-jobs/code_templates/script_processing.pyscript2.9 KB
references/processing-jobs/code_templates/spark_processing.pyscript3.7 KB
references/processing-jobs/overview.mdmarkdown6.7 KB
references/processing-jobs/references/configuration.mdmarkdown4.6 KB
references/processing-jobs/references/troubleshooting.mdmarkdown2.4 KB
references/sdk-getting-started/overview.mdmarkdown643 B
references/sdk-getting-started/references/execution-role-setup.mdmarkdown2.4 KB
references/sdk-getting-started/references/sagemaker-python-sdk-setup.mdmarkdown2.1 KB
references/training-jobs/code_templates/custom_training.pyscript6.2 KB
references/training-jobs/code_templates/jumpstart_training.pyscript5.6 KB
references/training-jobs/code_templates/recipe_training.pyscript5.7 KB
references/training-jobs/overview.mdmarkdown9.1 KB
references/training-jobs/references/configuration.mdmarkdown4.0 KB
references/training-jobs/references/troubleshooting.mdmarkdown4.4 KB
references/use-case-specification/overview.mdmarkdown2.0 KB
references/use-case-specification/references/spec-for-deployment.mdmarkdown3.9 KB
references/use-case-specification/references/spec-for-finetuning.mdmarkdown2.0 KB

references/processing-jobs/overview.md

View on GitHub
# Processing Jobs

Run arbitrary scripts and distributed data workloads on SageMaker managed processing compute with SageMaker Python SDK v3. Covers plain scripts, framework environments, Spark, custom containers, Athena/Redshift dataset definitions, and failure diagnosis.

## When to use

Use this capability when the user asks to:

- "run my script on SageMaker" or execute Python on managed compute with S3 I/O
- run a transform with PyTorch, TensorFlow, Hugging Face, XGBoost, or sklearn dependencies
- run PySpark/Spark JAR distributed ETL or process large datasets
- run a custom processing container
- query Athena or Redshift directly into a processing job
- diagnose a failed, stopped, or stuck processing job

Dataset format conversion that is already covered by `dataset-transformation` stays there; that capability may call SageMaker Processing internally.

## Operating assumptions

| Area | Assumption |
|---|---|
| Runtime | Python supported by `sagemaker>=3.22.0,<4.0`; templates install dependencies at use time |
| Credentials | Ambient AWS credentials plus a SageMaker execution role; caller needs processing create/describe, S3, logs, ECR/DLC, `iam:PassRole`, and Athena/Redshift permissions when selected |
| Storage | Small scripts/configs may be local; processor uploads code and stages data through S3; container paths live under `/opt/ml/processing/` |
| Region | Resolve from the AWS session; processing images and S3 query/output locations must be usable in that region |
| Network | PyPI access is needed for installation; runtime egress depends on the selected container and VPC/network isolation settings |

## Decision flow

1. Check conversation and project files before asking for values.
2. Choose one branch:
   - **Single Python script or BYOC** → `code_templates/script_processing.py`
   - **Framework source directory + requirements** → `code_templates/framework_processing.py`
   - **PySpark or Spark JAR** → `code_templates/spark_processing.py`
   - **Athena or Redshift query input** → `code_templates/dataset_definition_processing.py`
   - **Existing job failure/status** → `references/troubleshooting.md`
3. Use a prebuilt image resolved through `image_uris.retrieve` when it fits. Follow the managed-image resolution and reproducibility rules in `references/configuration.md`; review the resolved URI before launch.
4. For a custom ECR image, use the read-only `aws ecr describe-images` procedure in `references/configuration.md`, present candidate tags/digests and timestamps, obtain user selection, and pin the selected digest. Never silently select a mutable `latest` tag.
5. For Athena/Redshift, SageMaker executes the query and stages results to the configured S3 URI; do not add a separate manual export step.

## Gather inputs

Use cascading fallback: conversation → project files → ask one unresolved question at a time.

Required for launch: script/app or image, role, instance type/count, max runtime, input/output mapping, and wait behavior. Additionally:

- Framework: framework, exact supported version, Python version, source directory, optional `requirements.txt`
- Spark: PySpark script or JAR, optional Spark/Python/container version overrides, dependencies, multi-instance count. Apply the version policy from `references/configuration.md`.
- BYOC: ECR image URI and command/entrypoint expectations
- Athena: catalog, database, workgroup (optional), SQL, query-result S3 URI, output format
- Redshift: cluster, database, DB user, cluster role, SQL, query-result S3 URI, output format

For a Spark JAR, infer the fully qualified main class from the JAR manifest, build file (`pom.xml`, `build.sbt`, Gradle), or application documentation. Ask the user if it remains unresolved. `SPARK_MAIN_CLASS` is required only for `APPLICATION_KIND="jar"`; clear it for PySpark.

GPU-backed Processing Jobs are supported only with a GPU processing instance, compatible CUDA/framework or BYOC image, and sufficient regional quota. This reference has not validated a dedicated GPU-processing branch, so state that limitation and verify image compatibility/quota rather than assuming a CPU image will work.

## Preflight and confirmation

Before generating code or submitting a job:

1. Verify region, execution-role trust, S3 paths, exact image availability, query permissions, and requested compute quota.
2. Validate that input/output local paths start with `/opt/ml/processing/`, because SageMaker Processing mounts input channels and collects declared outputs under that container path; paths outside it are not automatically populated or uploaded.
3. For GPU requests, additionally verify GPU-compatible image metadata and the relevant Processing instance quota.
4. Summarize branch, image/framework/version, script/query, S3 I/O, instance type/count, volume, max runtime, and wait behavior.
5. Link to [SageMaker pricing](https://aws.amazon.com/sagemaker/ai/pricing/) rather than calculating a dollar estimate.
6. Ask for explicit approval. Stop until approved.

## Generate and launch

1. Read `references/configuration.md` and the selected template.
2. Write the customized output under the project directory in notebook or script mode.
3. Keep `WAIT_FOR_COMPLETION=False` unless the user asks to block.
4. Templates submit with `wait=False`, print job name/ARN immediately, and use `logs_for_processing_job` only when waiting.
5. Report output S3 locations after completion.

## Diagnose an existing job

Read `references/troubleshooting.md`. Start with `DescribeProcessingJob`, then inspect the job's CloudWatch stream. Return failure signature, root cause category, evidence, and fix; state what was not checked.

## Out of Scope

The following are supported by SageMaker and AWS but do not have a validated workflow in this reference. If the user's request matches one of these, let them know and proceed with best-effort guidance using general AWS knowledge:

- scheduled orchestration through SageMaker Pipelines, Step Functions, or EventBridge
- Ground Truth labeling jobs
- EMR/Glue cluster administration outside the processing job
- a dedicated, end-to-end validated GPU Processing branch

## References

- `code_templates/script_processing.py` — plain script and BYOC
- `code_templates/framework_processing.py` — framework image, source directory, requirements
- `code_templates/spark_processing.py` — PySpark or Spark JAR
- `code_templates/dataset_definition_processing.py` — Athena or Redshift query input
- `references/configuration.md` — placeholders and branch settings
- `references/troubleshooting.md` — status and failure classification
- [SageMaker Processing SDK reference](https://sagemaker.readthedocs.io/en/stable/processing.html)
- [SageMaker prebuilt containers](https://docs.aws.amazon.com/sagemaker/latest/dg/docker-containers-prebuilt.html)
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall