Skip to main content
affpapa.org
RU EN
skill CX Codex

unsloth — Claude Code skill: fast LoRA fine-tuning

A skill that feeds your agent Unsloth docs, so fine-tuning scripts come out right: 2-5x faster training, 50-80% less memory.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add Orchestra-Research/AI-Research-SKILLs --skill unsloth -a claude-code
Open on GitHub

What unsloth does

This skill gives the agent a reference for Unsloth, the library for fast LLM fine-tuning. Ask it to write a training script or debug a crash, and it pulls the relevant docs instead of guessing from memory.

The package is a SKILL.md file plus a references/ folder with documentation scraped from official sources. There is a quick reference section with code examples and a table of contents for navigation. The agent opens a specific file when it needs detail.

The skill itself has no runtime dependencies, but the code it helps you write needs unsloth, torch, transformers, trl, datasets and peft. Without those, the examples will not run. One caveat: the docs were generated automatically, so they can lag behind a fresh library release. Worth checking the API against the official docs before you commit to a config.

What it helps with

  • write a LoRA fine-tuning script for a base model
  • figure out why training runs out of GPU memory
  • switch an existing training loop to QLoRA
  • find a working config for Llama or Qwen
  • fix an error in Unsloth training code

Example prompts for the agent

  • write a fine-tuning script for Qwen with Unsloth on my dataset
  • convert this training code to QLoRA so it fits on one GPU
  • why does my Unsloth run keep hitting OOM?

How to install unsloth

1Skills CLI (Vercel)

npx skills add Orchestra-Research/AI-Research-SKILLs --skill unsloth -a claude-code

2Manually: put the files in place

~/.claude/skills/unsloth/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/unsloth/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about unsloth

How do I install the unsloth skill in Claude?

Run npx skills add Orchestra-Research/AI-Research-SKILLs --skill unsloth -a claude-code. The skill lands at ~/.claude/skills/unsloth/SKILL.md.

What does the unsloth skill do?

It hands the agent a reference on the Unsloth library: code examples, LoRA and QLoRA settings, and notes on common fine-tuning errors.

What do I need to run the examples?

The unsloth, torch, transformers, trl, datasets and peft packages. The skill itself is just text files and needs nothing installed.

Source text

SKILL.md · MIT 
---
name: unsloth
description: Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Fine-Tuning, Unsloth, Fast Training, LoRA, QLoRA, Memory-Efficient, Optimization, Llama, Mistral, Gemma, Qwen]
dependencies: [unsloth, torch, transformers, trl, datasets, peft]
---

# Unsloth Skill

Comprehensive assistance with unsloth development, generated from official documentation.

## When to Use This Skill

This skill should be triggered when:
- Working with unsloth
- Asking about unsloth features or APIs
- Implementing unsloth solutions
- Debugging unsloth code
- Learning unsloth best practices

## Quick Reference

### Common Patterns

*Quick reference patterns will be added as you use the skill.*

## Reference Files

This skill includes comprehensive documentation in `references/`:

- **llms-txt.md** - Llms-Txt documentation

Use `view` to read specific reference files when detailed information is needed.

## Working with This Skill

### For Beginners
Start with the getting_started or tutorials reference files for foundational concepts.

### For Specific Features
Use the appropriate category reference file (api, guides, etc.) for detailed information.

### For Code Examples
The quick reference section above contains common patterns extracted from the official docs.

## Resources

### references/
Organized documentation extracted from official sources. These files contain:
- Detailed explanations
- Code examples with language annotations
- Links to original documentation
- Table of contents for quick navigation

### scripts/
Add helper scripts here for common automation tasks.

### assets/
Add templates, boilerplate, or example projects here.

## Notes

- This skill was automatically generated from official documentation
- Reference files preserve the structure and examples from source docs
- Code examples include language detection for better syntax highlighting
- Quick reference patterns are extracted from common usage examples in the docs

## Updating

To refresh this skill with updated documentation:
1. Re-run the scraper with the same configuration
2. The skill will be rebuilt with the latest information

<!-- Trigger re-upload 1763621536 -->

© Orchestra Research · MIT · Orchestra-Research/AI-Research-SKILLs

Similar skills

Everything for AI and ML →
vision-sft Seth Hobson This skill configures supervised fine-tuning for vision-language models on image and text data. Use it when adapting a VLM to a new visual domain. CX Codex 2,600installs lora-qlora-recipes Seth Hobson This skill configures LoRA and QLoRA supervised fine-tuning, from target modules to rank and learning rate. Use it when reviewing an adapter training setup. CX Codex 2,600installs huggingface-llm-trainer huggingface Runs language and vision model fine-tuning on Hugging Face Jobs with TRL or Unsloth and converts checkpoints to GGUF without local GPUs. CX Codex +1 2,200installs llm-fine-tuning devops-skills Configures infrastructure for fine-tuning open LLMs with QLoRA, LoRA, and DeepSpeed. Useful when training models on proprietary domain datasets. CX Codex +1 318installs scenario-model-training scenario-labs Walks a custom model through Scenario MCP: base model pick, dataset, epochs, previews and launch. CX Codex +1 445installs transformers-huggingface Mindrally A skill that steers your agent through Hugging Face Transformers: model loading, tokenization, Trainer fine-tuning and faster inference. CX Codex +1 758installs

From the same set66

stable-diffusion-image-generation A skill that walks your agent through Stable Diffusion image generation with HuggingFace Diffusers: text-to-image, img2img, inpainting, ControlNet. CX Codex +1 1,000installs autoresearch Manages autonomous research projects using a two-loop cycle for rapid experiment execution and periodic synthesis. CX Codex +1 999installs gguf-quantization This skill guides llama.cpp GGUF quantization from 2 to 8 bits. It helps run LLMs locally on CPUs or Apple Silicon without dedicated GPU hardware. CX Codex +1 989installs segment-anything-model A skill that walks your agent through SAM: segment objects by point, box or mask prompts, or generate every mask in an image at once. CX Codex +1 985installs prompt-guard Integrates Meta's 86M parameter Prompt Guard model to detect jailbreaks and prompt injections in user prompts and RAG contexts before reaching the LLM. CX Codex +1 974installs qdrant-vector-search This skill guides agents through Qdrant vector search for RAG and semantic search. Use it when your project needs metadata filters or scalable vector storage. CX Codex +1 969installs fine-tuning-with-trl A skill for post-training language models with TRL: SFT, DPO, PPO and GRPO recipes you can run as-is. CX Codex +1 969installs tensorboard This skill gives your agent working recipes for TensorBoard: log training metrics, inspect weight histograms, open the dashboard. Useful when comparing runs or hunting bottlenecks. CX Codex +1 956installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor