ClaudeSuperPower
SubmitLog in

finetuning

Skill

Generates code that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says "start training", "fine-tune my model", "I'm ready to train", or when the plan reaches the finetuning step. Supports SFT, DPO, RLVR, and RLAIF trainers, including RLVR Lambda reward function

0Machine Learning

Install

git clone https://github.com/awslabs/agent-plugins.git ~/.claude/skills/finetuning

What is finetuning?

Generates code that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says "start training", "fine-tune my model", "I'm ready to train", or when the plan reaches the finetuning step. Supports SFT, DPO, RLVR, and RLAIF trainers, including RLVR Lambda reward function and RLAIF custom prompt creation.

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Inherit all session tools

Declares no tool restrictions — inherits every session tool

~83 tokens of context used while enabled, before you invoke anything

Documentation

README · ~6 min read

Prerequisites

Before starting this workflow, verify:

  1. 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.

  2. 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.

  3. A base model name available on SageMakerHub has been identified

    • If missing: Activate the model-selection skill to get it

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just skills.

Plugins

All plugins →

mcp-tunnels

Connect Claude to a private MCP server through an Anthropic MCP tunnel. The /create-docker-mcp-tunnel command drives the Docker Compose quickstart end to end: certificates, proxy config, cloudflared, and a verifiable sample server.

32.9K stars

mcp-server-dev

Skills for designing and building MCP servers that work seamlessly with Claude. Guides you through deployment models (remote HTTP, MCPB, local), tool design patterns, auth, and interactive MCP apps.

32.9K stars

expo

Official Expo skills for building, deploying, upgrading, and debugging React Native apps with Expo. Covers UI development with Expo Router, SwiftUI and Jetpack Compose components, Tailwind CSS setup, API routes, data fetching, CI/CD workflows, App Store and Play Store deployment, SDK upgrades, DOM c

2.3K stars