/aws-ai-ml

by Amazon Web Servicesaws/agent-toolkit-for-aws2.8k stars

337

Selects, deploys, and customizes AI models on Amazon SageMaker. Fine-tuning (SFT, DPO, RLVR, RLAIF), model selection, dataset preparation, evaluation, deployment to SageMaker endpoints or Bedrock, inference optimization and endpoint diagnostics. Covers the full lifecycle from planning through production. Use when fine-tuning models on SageMaker, choosing/selecting which base model to customize or fine-tune from SageMaker Hub, finding a model to deploy without fine-tuning, transforming datasets for training, checking data readiness, evaluating model quality, deploying to endpoints, benchmarking or optimizing inference, setting up IAM roles and S3 buckets for training jobs, or managing a SageMaker Managed MLflow app. Also use to check endpoint health, diagnose failures, debug latency or errors, or view container logs and CloudWatch metrics. Covers Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS infrastructure.

104 files
576.6 KB
Updated 2 weeks ago
GitHub
1 warning

Ask your Agent

Use this Skill: https://skilld.dev/gh/aws/agent-toolkit-for-aws/aws-ai-ml

This session only. Nothing lands on disk.

referencesuse-case-specificationoverview.md

2 KB raw

≈505 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Use Case Specification

Multi-turn conversation to gather use case details and produce a use case specification document.

Principles

One thing at a time. Each response advances exactly one decision or collects one piece of information.
Confirm before proceeding. Wait for the user to approve the spec before considering this skill complete.
Infer, don't interrogate. Use what's already known from the conversation. Only ask when you truly can't infer.
Do NOT ask about base model selection. Model selection is handled exclusively by the model-selection reference.

Workflow

Step 0: Check for Existing Spec

Before starting discovery, check if a *_use_case_spec.md file already exists in the project. If it does, present it to the user and ask whether they want to reuse it, modify it, or start fresh.

Step 1: Determine Intent

Check the plan (PLAN.md) or conversation context to determine whether the user wants to:

Fine-tune a model → read references/spec-for-finetuning.md and follow it.
Deploy a base model → read references/spec-for-deployment.md and follow it.

If the intent is already clear from the plan (e.g., the plan includes finetuning steps vs. only model-selection + model-deployment), use that. If ambiguous and not already resolved by the planning skill, ask:

"Are you looking to fine-tune a model for your use case, or deploy a base model as-is?"

⏸ Wait for user response.

Edit Protocol

If the user requests changes pertaining to any information covered by use_case_spec.md, you must edit it accordingly and ask for confirmation again.
The user can edit use_case_spec.md directly if they want to. If the user says they've updated the file directly, read it to get the latest in your context.

References

references/spec-for-finetuning.md — Discovery and spec generation workflow for fine-tuning
references/spec-for-deployment.md — Discovery and spec generation workflow for base model deployment

Source: SKILL.md on GitHub

Third-party checks

1 warning16d3 checks · Risk SAFE

Gen Agent Trust Hub16d
This skill includes some security considerations such as the ingestion of external data for model training and the execution of generated scripts. While these warrant review, they are used within the skill's intended functionality for AI/ML model customization and deployment on Amazon SageMaker. See detailed analysis for context.
Socket16d
No alerts
Snyk16d
Risk: MEDIUM · 2 issues

Provenance

Signed by skilld at 7fcb1da. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 weeks ago

Capability

metadata: { "version": "4" }