Core Skills

Skill 24 of 130

AWS AI ML

Selects, deploys, and customizes AI models on Amazon SageMaker.

3 minutes · 750 words · 3 sections

Install

$ npx skills add aws/agent-toolkit-for-aws --skill aws-ai-ml

$ npx skills add aws/agent-toolkit-for-aws

» /plugin marketplace add aws/agent-toolkit-for-aws

The first command installs just this skill, by the name in its SKILL.md; the second installs the whole repository.

AWS AI/ML Model Customization

Domain expertise for fine-tuning and deploying models on Amazon SageMaker. Covers the full model customization lifecycle from planning through production deployment.

Routing

Match the user’s intent to the appropriate reference folder and load only that content.

User intent	Reference	When to use
Plan a model customization project, discover scope of work, resume or modify a plan	references/planning/ (opens in a new tab)	User’s request relates to model customization or deployment (fine-tuning, training, building, customizing, reviewing data, deploying or standing up a model — including selecting or deploying an off-the-shelf or base model with no training — or getting advice on approach). Always co-activate with other intents to discover full scope. Load this reference FIRST when the request matches multiple rows in this table — read its plan templates before routing to a single-action reference.
Define the business problem, success criteria, or use case spec	references/use-case-specification/ (opens in a new tab)	User says “define my use case”, “capture requirements”, “what should I decide up front”, or as default first step in any plan. Skip only if user explicitly declines.
Select or change a base model	references/model-selection/ (opens in a new tab)	User asks which model to use, mentions a model name or family, or wants to evaluate what’s available. Always activate model-selection even for known model names because the exact Hub model ID must be resolved. Recommended: route to use-case-specification first to capture requirements — this produces better filtering results. Routing to use-case-specification first is not required if user provides a specific model name/ID or declines. If intent is ambiguous (fine-tune vs deploy as-is), model-selection MUST confirm which path before proceeding. Base model filtering for deployment MUST go through select-for-deployment.md and its scripts for any final recommendation.
Choose a fine-tuning technique (SFT, DPO, RLVR, RLAIF)	references/finetuning-technique/ (opens in a new tab)	User has decided to fine-tune and needs to choose a technique, or technique needs validation against the selected model’s recipes. Requires a base model to be selected first.
Validate dataset quality and format	references/dataset-evaluation/ (opens in a new tab)	User says “is my dataset okay”, “check my training data”, “I have my own data”, or before starting any fine-tuning job.
Transform or convert a dataset between formats	references/dataset-transformation/ (opens in a new tab)	User says “transform”, “convert”, “reformat”, or dataset schema needs to change. Always use this rather than writing inline transformation code.
Generate fine-tuning code and start training	references/finetuning/ (opens in a new tab)	User says “start training”, “fine-tune my model”, “I’m ready to train”, or plan reaches the finetuning step. Supports SFT, DPO, RLVR, RLAIF trainers.
Evaluate or benchmark a trained model	references/model-evaluation/ (opens in a new tab)	User says “evaluate my model”, “run a benchmark”, “test model performance”, “compare models”. Supports LLM-as-Judge and Custom Scorer.
Deploy, benchmark, or optimize a model on an endpoint or Bedrock	references/model-deployment/ (opens in a new tab)	User says “deploy my model”, “create an endpoint”, or “make it available” (plain deploy) — or, for the inference-optimization sub-workflows on SageMaker Real-Time Endpoints only, “benchmark my endpoint” / “compare benchmark runs” (benchmarking), or states a performance/cost/latency/throughput goal for a new deployment such as “find the cheapest instance” (recommendations). Handles Nova vs OSS deployment pathways.
Set up IAM roles, S3 buckets, SDK configuration	references/sdk-getting-started/ (opens in a new tab)	User says “set up”, “getting started”, “check my environment”, “configure SDK”, or as first step in any plan involving SageMaker training/evaluation/deployment.
Manage project directory and artifacts	references/directory-management/ (opens in a new tab)	Starting a new project, resuming existing one, or when PLAN.md needs to be associated with a project directory.
Set up, update, or delete a SageMaker Managed MLflow app	references/manage-mlflow/ (opens in a new tab)	User says “set up MLflow”, “create MLflow app”, “update my MLflow app”, “delete my MLflow app”, “I need an MLflow server”, asks “what is SageMaker MLflow”, or a workflow needs an MLflow backend and none is connected.
Diagnose a failing or unhealthy SageMaker endpoint	references/endpoint-diagnostics/ (opens in a new tab)	User reports endpoint errors, latency, inference failures, or a deployment that failed. “What’s the status of my endpoint?”, “Is my endpoint erroring?”, “My endpoint failed — why?”, “How many instances are running behind my endpoint?”, “Is the latency my model or SageMaker?”, “Show me the container logs for my endpoint.” NOT for training-job issues, endpoint deletion, scaling changes, or new deployments.

Rules

Progressive disclosure. Load only the reference folder relevant to the current user intent. Do not load all references at once.
Best-effort help. If the user’s request falls outside this skill’s references, do not dead-end the conversation. Help them using general AWS knowledge and documentation, and inform the user that the guidance is not covered by this skill’s validated workflows.
Usage attribution. Before running any AWS CLI command or packaged script, set export AWS_SDK_UA_APP_ID=AWSSkill-SageMaker.

About this skill

Trigger

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.

The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.

Also published for: Alternate — collapsed into this chapter because the copies are the same skill.
Source: skills/core-skills/aws-ai-ml/SKILL.md

Colophon for this issue

Colophon

How this issue was made

Source

github.com/aws/agent-toolkit-for-aws, branch main, last pushed 24 September 2026.

Licence

Apache-2.0 — the text of every skill is reproduced unmodified, frontmatter included, under the upstream licence.

Discovery

130 skills found by walking the repository tree for SKILL.md, not by matching a directory convention. 19 distinct layouts observed: plugins/aws-agents-for-devsecops/skills/*/SKILL.md, plugins/aws-agents/skills/*/SKILL.md, plugins/aws-core/skills/*/SKILL.md, skills/core-skills/*/SKILL.md, skills/specialized-skills/analytics-skills/*/SKILL.md, skills/specialized-skills/database-skills/*/SKILL.md, skills/specialized-skills/ec2-skills/*/SKILL.md, skills/specialized-skills/end-user-computing-skills/*/SKILL.md, skills/specialized-skills/messaging-and-streaming-skills/*/SKILL.md, skills/specialized-skills/migration-and-modernization-skills/*/SKILL.md, skills/specialized-skills/networking-and-content-delivery-skills/*/SKILL.md, skills/specialized-skills/operations-skills/*/SKILL.md, skills/specialized-skills/quantum-computing-skills/*/SKILL.md, skills/specialized-skills/resilience-skills/*/SKILL.md, skills/specialized-skills/security-and-identity-skills/*/SKILL.md, skills/specialized-skills/serverless-skills/*/SKILL.md, skills/specialized-skills/storage-skills/*/SKILL.md, skills/specialized-skills/system-table-skills/*/SKILL.md, skills/specialized-skills/web-and-mobile-development/*/SKILL.md.

Duplicates collapsed

34 mirror copies folded into their canonical skill — republished for Alternate. Copies match on content hash and on position once a leading per-agent prefix is stripped, because the same skill is routinely shipped under a dozen agent directories with a dozen different hashes.

Issue colours

Resolved from a curated brand profile — hue 65°, chroma 0.174. Two accent tones are generated per issue and each is proven against its own ground before it ships: a single accent that passes AA on both light and dark paper is arithmetically impossible.

Heading repairs

1 repair applied to this skill so the document has one h1 and no skipped levels:

Shifted “3 headings” from h1 to h2 so the skill title is the only h1.

Spec compliance

Every skill satisfies the Agent Skills specification’s frontmatter rules.

Images

Images inside a skill come from the upstream repository. Where the author gave no alternative text we mark the image decorative rather than inventing a description — a plausible caption we made up is worse than none for the reader who depends on it.

Marketplace

A plugin manifest is published at .claude-plugin/marketplace.json by Amazon Web Services, declaring 4 plugins. It is read for editorial metadata only — never as the skill index, which is always the repository tree.

Signal

Install counts come from skills.sh. They measure downloads, not quality, and an unranked repository is not an unread one.

Agent surfaces

The whole issue is available as one markdown document at /aws/agent-toolkit-for-aws.md, and each skill at its own .md URL.

Publication

Set by Skills Docs from the source repository. Body text is Literata at the reader’s chosen size and measure; code is Geist Mono. Nothing on this page was written by us except this paragraph.

AWS AI/ML Model Customization

Domain expertise for fine-tuning and deploying models on Amazon SageMaker. Covers the full model customization lifecycle from planning through production deployment.

Routing

Match the user’s intent to the appropriate reference folder and load only that content.

User intent	Reference	When to use
Plan a model customization project, discover scope of work, resume or modify a plan	references/planning/ (opens in a new tab)	User’s request relates to model customization or deployment (fine-tuning, training, building, customizing, reviewing data, deploying or standing up a model — including selecting or deploying an off-the-shelf or base model with no training — or getting advice on approach). Always co-activate with other intents to discover full scope. Load this reference FIRST when the request matches multiple rows in this table — read its plan templates before routing to a single-action reference.
Define the business problem, success criteria, or use case spec	references/use-case-specification/ (opens in a new tab)	User says “define my use case”, “capture requirements”, “what should I decide up front”, or as default first step in any plan. Skip only if user explicitly declines.
Select or change a base model	references/model-selection/ (opens in a new tab)	User asks which model to use, mentions a model name or family, or wants to evaluate what’s available. Always activate model-selection even for known model names because the exact Hub model ID must be resolved. Recommended: route to use-case-specification first to capture requirements — this produces better filtering results. Routing to use-case-specification first is not required if user provides a specific model name/ID or declines. If intent is ambiguous (fine-tune vs deploy as-is), model-selection MUST confirm which path before proceeding. Base model filtering for deployment MUST go through select-for-deployment.md and its scripts for any final recommendation.
Choose a fine-tuning technique (SFT, DPO, RLVR, RLAIF)	references/finetuning-technique/ (opens in a new tab)	User has decided to fine-tune and needs to choose a technique, or technique needs validation against the selected model’s recipes. Requires a base model to be selected first.
Validate dataset quality and format	references/dataset-evaluation/ (opens in a new tab)	User says “is my dataset okay”, “check my training data”, “I have my own data”, or before starting any fine-tuning job.
Transform or convert a dataset between formats	references/dataset-transformation/ (opens in a new tab)	User says “transform”, “convert”, “reformat”, or dataset schema needs to change. Always use this rather than writing inline transformation code.
Generate fine-tuning code and start training	references/finetuning/ (opens in a new tab)	User says “start training”, “fine-tune my model”, “I’m ready to train”, or plan reaches the finetuning step. Supports SFT, DPO, RLVR, RLAIF trainers.
Evaluate or benchmark a trained model	references/model-evaluation/ (opens in a new tab)	User says “evaluate my model”, “run a benchmark”, “test model performance”, “compare models”. Supports LLM-as-Judge and Custom Scorer.
Deploy, benchmark, or optimize a model on an endpoint or Bedrock	references/model-deployment/ (opens in a new tab)	User says “deploy my model”, “create an endpoint”, or “make it available” (plain deploy) — or, for the inference-optimization sub-workflows on SageMaker Real-Time Endpoints only, “benchmark my endpoint” / “compare benchmark runs” (benchmarking), or states a performance/cost/latency/throughput goal for a new deployment such as “find the cheapest instance” (recommendations). Handles Nova vs OSS deployment pathways.
Set up IAM roles, S3 buckets, SDK configuration	references/sdk-getting-started/ (opens in a new tab)	User says “set up”, “getting started”, “check my environment”, “configure SDK”, or as first step in any plan involving SageMaker training/evaluation/deployment.
Manage project directory and artifacts	references/directory-management/ (opens in a new tab)	Starting a new project, resuming existing one, or when PLAN.md needs to be associated with a project directory.
Set up, update, or delete a SageMaker Managed MLflow app	references/manage-mlflow/ (opens in a new tab)	User says “set up MLflow”, “create MLflow app”, “update my MLflow app”, “delete my MLflow app”, “I need an MLflow server”, asks “what is SageMaker MLflow”, or a workflow needs an MLflow backend and none is connected.
Diagnose a failing or unhealthy SageMaker endpoint	references/endpoint-diagnostics/ (opens in a new tab)	User reports endpoint errors, latency, inference failures, or a deployment that failed. “What’s the status of my endpoint?”, “Is my endpoint erroring?”, “My endpoint failed — why?”, “How many instances are running behind my endpoint?”, “Is the latency my model or SageMaker?”, “Show me the container logs for my endpoint.” NOT for training-job issues, endpoint deletion, scaling changes, or new deployments.

Rules

Progressive disclosure. Load only the reference folder relevant to the current user intent. Do not load all references at once.
Best-effort help. If the user’s request falls outside this skill’s references, do not dead-end the conversation. Help them using general AWS knowledge and documentation, and inform the user that the guidance is not covered by this skill’s validated workflows.
Usage attribution. Before running any AWS CLI command or packaged script, set export AWS_SDK_UA_APP_ID=AWSSkill-SageMaker.

AWS AI ML

AWS AI/ML Model Customization

Routing

Rules

About this skill

Trigger

Colophon

AWS AI ML

AWS AI/ML Model Customization

Routing

Rules

Appendix 24.1–24.103

References103 files

About this skill

Trigger

Colophon

Appendix 24.1–24.103

References103 files