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/dataset-transformation/references/sagemaker_dataset_formats.md
View on GitHub# SageMaker Supported Dataset Formats (Offline Fallback)
This is an offline copy of the supported dataset formats from:
https://docs.aws.amazon.com/sagemaker/latest/dg/model-customize-evaluation-dataset-formats.html
**Note:** Always attempt to fetch the live documentation first. Only use this file as a fallback when internet access is unavailable (e.g., VPC environments).
## Required Fields
| Field | Required |
| ------------- | ---------------------- |
| User Prompt | Yes |
| System Prompt | No |
| Ground truth | Only for Custom Scorer |
| Category | No |
## 1. OpenAI Format
```json
{
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
},
{
"role": "assistant",
"content": "Hello to you!"
}
]
}
```
- `system` role is optional (system prompt)
- `user` role is the query
- `assistant` role is the ground truth
## 2. SageMaker Evaluation Format
```json
{
"system": "You are an English major with top marks in class who likes to give minimal word responses: ",
"query": "What is the symbol that ends the sentence as a question",
"response": "?",
"category": "Grammar"
}
```
- `system` and `category` are optional
- `response` is the ground truth
## 3. HuggingFace Prompt Completion Format
### Standard
```json
{
"prompt": "What is the symbol that ends the sentence as a question",
"completion": "?"
}
```
### Conversational
```json
{
"prompt": [
{ "role": "user", "content": "What is the symbol that ends the sentence as a question" }
],
"completion": [
{ "role": "assistant", "content": "?" }
]
}
```
- `completion` is the ground truth
## 4. HuggingFace Preference Format
### Standard
```json
{
"prompt": "The sky is",
"chosen": "blue",
"rejected": "green"
}
```
### Conversational
```json
{
"prompt": [
{ "role": "user", "content": "What color is the sky?" }
],
"chosen": [
{ "role": "assistant", "content": "It is blue." }
],
"rejected": [
{ "role": "assistant", "content": "It is green." }
]
}
```
- `chosen` is the ground truth
## 5. Verl Format
### Current (prompt as messages array)
```json
{
"data_source": "openai/gsm8k",
"prompt": [
{ "content": "You are a helpful math tutor.", "role": "system" },
{ "content": "What is 2+2?", "role": "user" }
],
"ability": "math",
"extra_info": {
"answer": "4"
},
"reward_model": {
"ground_truth": "4"
}
}
```
### Legacy (prompt as string)
```json
{
"data_source": "openai/gsm8k",
"prompt": "What is 2+2?",
"extra_info": {
"answer": "4"
}
}
```
- Ground truth via `extra_info.answer` (preferred) or `reward_model.ground_truth`
- Preserves metadata fields: `id`, `data_source`, `ability`, `reward_model`, `extra_info`, `attributes`, `difficulty`
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 |