⚡

AI EngineeringPython

Unsloth

Unsloth is an AI Engineering skill for Claude Code, published by OpenRaiser in NanoResearch.

1.4K stars95 forkson OpenRaiser/NanoResearchAdded 2026/08/19Repository updated 2026/05/26

View source on GitHub Download repo ZIP

agent-skillsagentsaiai-agentsai-scientistartificial-intelligenceautonomous-agentsautonomous-researchautoresearchclaude-codeclaude-skillsnanobotopenclaw

Install in seconds

Install Unsloth

Copy Unsloth 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/OpenRaiser/NanoResearch/tree/main/skills/vendor-ai-research/unsloth ~/.claude/skills/unsloth

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/OpenRaiser/NanoResearch.git

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

In this catalog

Source file: skills/vendor-ai-research/unsloth/SKILL.md in OpenRaiser/NanoResearch
Installs to: ~/.claude/skills/unsloth
Collection: One of 16 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Unsloth does

Unsloth provides expert guidance for fast fine-tuning with Unsloth, covering 2-5x faster training, 50-80% less memory, and LoRA/QLoRA optimization. Use it when working with Unsloth features, implementing solutions, or debugging training code.

Unsloth is cataloged under AI Engineering on DirSkills. Unsloth comes from a repository tagged agent-skills, agents, ai, ai-agents and ai-scientist.

Documentation

README

Excerpt

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.

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

Frequently asked about Unsloth

What else does OpenRaiser publish alongside Unsloth?
Unsloth is one of 16 skills that DirSkills catalogs from OpenRaiser/NanoResearch, the repository it ships in. Its siblings there include Academic Plotting, Autoresearch and Creative Thinking for Research. Each one is a separate skill with its own page in this directory, installs the same way Unsloth does, and is maintained by OpenRaiser in that same repository. The rest of the collection is listed on the OpenRaiser/NanoResearch page.
How does Unsloth compare to other AI Engineering skills?
Unsloth ranks #1082 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 Unsloth against them. Open each page to compare what they document and how they install.

More from OpenRaiser/NanoResearch

Unsloth is one of 16 skills cataloged on DirSkills from OpenRaiser/NanoResearch.

See all 16 skills →

Academic Plotting

Academic Plotting generates publication-quality figures for ML papers from research context or experimental data. It creates architecture diagrams via Gemini and data-driven charts via matplotlib/seaborn, auto-selecting chart types and highlighting key results.

Autoresearch

Autoresearch orchestrates end-to-end autonomous AI research projects using a two-loop architecture for rapid experiments and periodic synthesis, routing to domain-specific skills and producing papers; use when starting a research project or managing multi-hypothesis experiments.

Creative Thinking for Research

Creative Thinking for Research applies eight cognitive science frameworks to generate novel research directions in computer science and AI. Use it when seeking genuinely novel directions via combinatorial creativity, analogical reasoning, and constraint manipulation.

Hugging Face Accelerate

Hugging Face Accelerate simplifies distributed training for PyTorch models by adding only four lines of code. Use it to run the same script on single or multiple GPUs, with mixed precision, DeepSpeed, or FSDP.

LLM Evaluation Harness

LLM Evaluation Harness evaluates LLMs across 60+ academic benchmarks using standardized prompts and metrics. Use when benchmarking model quality, comparing models, or tracking training progress.

ML Paper Writing

ML Paper Writing drafts publication-ready ML/AI/systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use it to turn research repos into structured papers, find and verify citations, and apply conference LaTeX templates.

More AI Engineering skills

Unsloth is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #1082 by stars among them.

Browse all AI Engineering skills →

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.