Finetuning

by awslabs

Finetuning is an AI Engineering skill for Claude Code, published by awslabs in agent-plugins.

867 stars145 forkson awslabs/agent-pluginsAdded 2026/08/22Repository updated 2026/08/21

View source on GitHub Download repo ZIP

agent-pluginsagent-skillsagentsawscoding-agent-skillscoding-agents

Install in seconds

Install Finetuning

Copy Finetuning into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/awslabs/agent-plugins/tree/main/plugins/sagemaker-ai/skills/finetuning ~/.claude/skills/finetuning

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/awslabs/agent-plugins.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: plugins/sagemaker-ai/skills/finetuning/SKILL.md in awslabs/agent-plugins
Installs to: ~/.claude/skills/finetuning
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Finetuning does

Finetuning generates code for SageMaker serverless training jobs to fine-tune a base model. Use it when starting training or when a plan reaches the finetuning step, including SFT, DPO, RLVR, and RLAIF workflows.

Finetuning is cataloged under AI Engineering on DirSkills. Finetuning comes from a repository tagged agent-plugins, agent-skills, agents, aws and coding-agent-skills.

Documentation

README

Excerpt

Prerequisites

Before starting this workflow, verify:

A use_case_spec.md file exists
- If missing: Activate the use-case-specification skill first, then resume
- DON'T EVER offer to create a use case spec without activating the use-case-specification skill.
A fine-tuning technique (SFT, DPO, RLVR, RLAIF, or CPT/RFT (for Nova)) and base model have already been selected
- If missing: Activate the model-selection and/or finetuning-technique skills to collect what's missing, then resume
- Don't make recommendations on the spot. You MUST activate the appropriate skill.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Finetuning

What else does awslabs publish alongside Finetuning?
Finetuning is one of 25 skills that DirSkills catalogs from awslabs/agent-plugins, the repository it ships in. Its siblings there include AWS Architecture Diagram, AWS Lambda and AWS Lambda Durable Functions. Each one is a separate skill with its own page in this directory, installs the same way Finetuning does, and is maintained by awslabs in that same repository. The rest of the collection is listed on the awslabs/agent-plugins page.
How does Finetuning compare to other AI Engineering skills?
Finetuning ranks #1515 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Finetuning against them. Open each page to compare what they document and how they install.