Download

Skill UI

Browse and discover 5066+ curated skills

All Development Artificial Intelligence Design & Creative Product & Business Data Science Marketing Soft Skills Productivity Engineering Languages

Search Training , found 53 results

Default Newest Most Downloaded

Axolotl Fine-Tuning Guide

Orchestra-Research/AI-Research-SKILLs

Guides developers through Axolotl-based LLM fine-tuning, covering YAML config patterns, LoRA/QLoRA and DPO/KTO/ORPO/GRPO workflows, FSDP tips, compressed checkpoints, and debugging best practices for reliable multimodal training.

Axolotl Fine-Tuning Guide

Orchestra-Research/AI-Research-SKILLs

Guides developers through Axolotl-based LLM fine-tuning, covering YAML config patterns, LoRA/QLoRA and DPO/KTO/ORPO/GRPO workflows, FSDP tips, compressed checkpoints, and debugging best practices for reliable multimodal training.

BLIP-2 Vision Language

blip-2-vision-language

Orchestra-Research/AI-Research-SKILLs

BLIP-2 is a vision-language pre-training framework that links frozen image encoders with LLMs to generate captions, answer visual questions, perform image-text retrieval, and drive multimodal chat with strong zero-shot accuracy.

Neural Network Builder

building-neural-networks

jeremylongshore/claude-code-plugins-plus-skills

Enables Claude to configure neural network architectures through the neural-network-builder plugin, creating or modifying models and defining layers, activation functions, and training parameters whenever network design or tuning is requested.

Confusion Matrix Generator

confusion-matrix-generator

jeremylongshore/claude-code-plugins-plus-skills

Assists ML Training workflows by automatically activating on confusion matrix generator requests, offering structured guidance, best-practice checks, and ready-to-use code snippets.

Constitutional AI Safety

constitutional-ai

Orchestra-Research/AI-Research-SKILLs

Guides setting up Constitutional AI by combining self-critique SL with RLAIF training to align generative models without human labels and reduce harmful outputs in systems like Claude.

Dataset Loader Creator

dataset-loader-creator

jeremylongshore/claude-code-plugins-plus-skills

Automates dataset loader creation within ML Training workflows, offering best-practice guidance, validation checks, and production-ready code to accelerate data prep and model tuning.

Distributed Training Setup

distributed-training-setup

jeremylongshore/claude-code-plugins-plus-skills

Guides automated distributed training setups with step-by-step practices, production-ready configs, and validation checks for ML training workflows.

LLM Evaluation Harness

evaluating-llms-harness

Orchestra-Research/AI-Research-SKILLs

Runs lm-evaluation-harness across 60+ academic benchmarks such as MMLU, HumanEval, GSM8K, TruthfulQA, and HellaSwag to benchmark HuggingFace/vLLM/API models, compare variants, track training checkpoints, and save standardized reports for research labs.

Feature Engineering Helper

feature-engineering-helper

jeremylongshore/claude-code-plugins-plus-skills

Automatically activates when you mention feature engineering helper, offering guidance on data preparation, model training, hyperparameter tuning, and experiment tracking for ML projects.

Fine-Tuning LLM Expert

fine-tuning-expert

Jeffallan/claude-skills

Hands-on guide for tuning large language models via LoRA/QLoRA/PEFT, covering dataset prep, hyperparameter config, adapter training, evaluation, and production deployment with quantization best practices.

GPTQ LLM Quantization

Orchestra-Research/AI-Research-SKILLs

Post-training 4-bit quantization for LLMs that trims memory by 4× with minimal perplexity loss, enabling 70B+ models to run faster on consumer GPUs while integrating with transformers, PEFT, and QLoRA workflows.

Language