Download

Skill UI

Browse and discover 5115+ curated skills

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

Search Training , found 85 results

Default Newest Most Downloaded

Pyvene Causal Interventions

pyvene-interventions

Orchestra-Research/AI-Research-SKILLs

Declarative toolkit for performing causal interventions on PyTorch models, covering activation patching, causal tracing, and interchange training so researchers can test hypotheses and reproduce experiments.

Ray Train Distributed Orchestration

Orchestra-Research/AI-Research-SKILLs

Ray Train orchestrates distributed PyTorch/TensorFlow/HuggingFace training from laptops to thousands of nodes, adding elastic scaling, hyperparameter search, and fault tolerance while keeping most code unchanged.

ROC Curve Plotter

roc-curve-plotter

jeremylongshore/claude-code-plugins-plus-skills

Automates ROC curve plotting tasks in ML training, guiding data prep, model training, tuning, tracking, and code generation for production-ready results.

RWKV Hybrid Architecture

rwkv-architecture

Orchestra-Research/AI-Research-SKILLs

RWKV hybrid architecture merges parallel Transformer training with sequential RNN inference to deliver linear-time, infinite-context generation without KV caches, enabling streaming text production and long-document processing on constrained hardware.

SimPO Preference Optimization

Orchestra-Research/AI-Research-SKILLs

SimPO offers a reference-free preference optimization workflow to align LLMs more efficiently than DPO or PPO, requiring no reference model and suited for compute-constrained single-node training with proven AlpacaEval gains.

Sklearn Pipeline Builder

sklearn-pipeline-builder

jeremylongshore/claude-code-plugins-plus-skills

Automates sklearn pipeline builder tasks within ML training, activating on relevant triggers to guide data prep, model training, hyperparameter tuning, and experiment tracking with production-ready code and standards validation.

SkyPilot Cloud Orchestration

skypilot-multi-cloud-orchestration

Orchestra-Research/AI-Research-SKILLs

SkyPilot Multi-Cloud Orchestration codifies ML workload management by spinning up clusters across AWS/GCP/Azure, auto-optimizing costs, recovering spot instances, and unifying distributed GPU training and serving workflows.

Slime RL Training

slime-rl-training

Orchestra-Research/AI-Research-SKILLs

Guides LLM post-training with reinforcement learning using the Slime (Megatron + SGLang) framework, covering GLM-style training, custom data buffers, rollout management, and Megatron-LM integration for scalable policy tuning.

SAELens Sparse Autoencoder Tool

sparse-autoencoder-training

Orchestra-Research/AI-Research-SKILLs

Guides researchers through training and analyzing Sparse Autoencoders with SAELens to decompose neural activations into interpretable concepts, understand superposition, and steer or audit transformer models with sparse feature math.

Pronunciation Training Workflow

speak-core-workflow-b

jeremylongshore/claude-code-plugins-plus-skills

Runs the Speak secondary workflow to deliver phoneme-level pronunciation training, scoring, error handling hints, and adaptive practice guidance for speech-improvement features.

Dataset Splitter Tool

splitting-datasets

jeremylongshore/claude-code-plugins-plus-skills

Automates splitting datasets into training, validation, and test subsets by generating and running Python code so you can quickly prepare data for machine learning model training and evaluation.

TensorBoard Visualization Toolkit

Orchestra-Research/AI-Research-SKILLs

TensorBoard is Google’s ML visualization toolkit for tracking training metrics, comparing experiments, inspecting model graphs, projecting embeddings, and profiling performance in PyTorch and TensorFlow workflows.

Prev 1 2 3 456 7 8 Next

Language