Skill · Agent workflows

unsloth

Agent workflowsmcpdirectory↓ 19

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

Install
$ npx skills add zechenzhangAGI/AI-research-SKILLs --skill unsloth

Generic steps — the original listing is authoritative. Copy the command, run it where you keep agent skills, then confirm version and requirements in the original listing.

At a glance

  • 19 installs reported on mcpdirectory.
  • Published by zechenzhangAGI — listed by mcpdirectory. Setup details live in the original listing.

How to use

  1. Copy the Install command above.
  2. Run it where you keep agent skills.
  3. Confirm version and requirements in the original listing.

More in Agent workflows

  • php-best-practices — PHP best practices, PSR standards, and code quality guidelines.
  • coding-agent — Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
  • context-compression — This skill should be used when the user asks to "compress context", "summarize conversation history", "impleme
  • add-uint-support — Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros.
  • personal-finance-beancount — Professional personal finance advisor specializing in plain-text accounting with Beancount and Fava.
  • windows-expert — Expert guidance for Windows, PowerShell, WSL interop, and cross-platform development

More from zechenzhangAGI

  • llava — Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines
  • langchain — Framework for building LLM-powered applications with agents, chains, and RAG.
  • llama-cpp — Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware.
  • qdrant-vector-search — High-performance vector similarity search engine for RAG and semantic search.

← Back to Skills catalog · View original listing ↗

Outdated or wrong? Report this listing.