opensite-ai/opensite-skills / aws-ai-ml
aws-ai-ml
VerifiedSelects, 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.
references/model-evaluation/references/supported-judge-models.md
View on GitHub# Supported Judge Models
Reference: [Amazon Bedrock LLM-as-Judge Evaluation](https://docs.aws.amazon.com/bedrock/latest/userguide/evaluation-judge.html)
## Allowed Judge Models
The SageMaker Python SDK is the source of truth for which judge models are allowed: when you submit the evaluation job, the SDK validates the judge model and, if it is not supported, raises an error that lists the currently accepted models (and their allowed regions). The table below is a convenience reference that may lag the SDK — do not treat it as exhaustive; rely on the SDK's submit-time validation to confirm a given model is accepted:
| Model | Model ID | Regions |
| ------------------------------ | ------------------------------------------- | ----------------------------------------------- |
| Amazon Nova Pro | `amazon.nova-pro-v1:0` | us-east-1 |
| Anthropic Claude 3.5 Sonnet v1 | `anthropic.claude-3-5-sonnet-20240620-v1:0` | us-west-2, us-east-1, ap-northeast-1 |
| Anthropic Claude 3.5 Sonnet v2 | `anthropic.claude-3-5-sonnet-20241022-v2:0` | us-west-2 |
| Anthropic Claude 3 Haiku | `anthropic.claude-3-haiku-20240307-v1:0` | us-west-2, us-east-1, ap-northeast-1, eu-west-1 |
| Anthropic Claude 3.5 Haiku | `anthropic.claude-3-5-haiku-20241022-v1:0` | us-west-2 |
| Meta Llama 3.1 70B Instruct | `meta.llama3-1-70b-instruct-v1:0` | us-west-2 |
| Mistral Large | `mistral.mistral-large-2402-v1:0` | us-west-2, us-east-1, eu-west-1 |
This list applies to both built-in and custom metrics — the SDK does not distinguish between them.
Source: derived from the SageMaker SDK's internal evaluator allowlist (sagemaker SDK v3). This is an SDK internal — do not import or reference it in generated code; the SDK enforces the allowlist itself at job-submission time.
## Selection Guidance
Verify each candidate is active in the user's region. Run `aws bedrock get-foundation-model --model-identifier <model-id> --region <region>` and extract `modelDetails.modelLifecycle.status` from the response.
Only include models that return `ACTIVE`. Models marked `LEGACY` will fail at evaluation time.
Present all active models to the user and let them choose. **NEVER recommend or suggest any particular model.** Only display the list. If the user asks for guidance, you may share these general trade-offs so they can decide:
- Cost vs quality: Smaller models are faster and cheaper; larger models produce higher-quality judgments
- Task complexity: Simple tasks (QA, classification) may not need the most capable model; complex reasoning (math, multi-step) benefits from stronger models
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 119k | Updated | Claude CodeCodex | Verified | Install |
| 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: 118k | Updated | Claude CodeCodex | Verified | Install |