@mkurman/unsloth-studio-skill

Agent skill for managing LLM fine-tuning through Unsloth Studio API.

Installation

npm install @mkurman/unsloth-studio-skill

# Or with pnpm
pnpm add @mkurman/unsloth-studio-skill

# Or with yarn
yarn add @mkurman/unsloth-studio-skill

Usage with skills-npm

This package ships with a built-in agent skill. Use skills-npm to install it for your AI agent:

# Install skills-npm
npm install -D skills-npm

# Add to package.json scripts
{
  "scripts": {
    "prepare": "skills-npm"
  }
}

# Or run directly
npx skills-npm

This will symlink the skill to your agent's skills directory (.claude/skills/, .cursor/skills/, etc.).

What the Skill Does

• Start, monitor, and manage LLM fine-tuning jobs
• Configure training parameters (QLoRA, LoRA, Full)
• Manage datasets (HuggingFace, local uploads)
• Export trained models (GGUF, safetensors, LoRA adapters)
• Run inference with trained models
• Docker setup and discovery for Unsloth Studio

Related

• Unsloth Studio Docs
• Agent Skills Specification
• skills-npm

License

Apache-2.0