machine-learning
38
ml-model-explanation
Interpret machine learning models using SHAP, LIME, feature importance, partial dependence, and attention visualization for explainability
aj-geddes
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
machine-learning
38
regression-modeling
Build predictive models using linear regression, polynomial regression, and regularized regression for continuous prediction, trend forecasting, and relationship quantification
aj-geddes
data-ai
machine-learning
38
anomaly-detection
Identify unusual patterns, outliers, and anomalies in data using statistical methods, isolation forests, and autoencoders for fraud detection and quality monitoring
aj-geddes
data-ai
machine-learning
38
model-hyperparameter-tuning
Optimize hyperparameters using grid search, random search, Bayesian optimization, and automated ML frameworks like Optuna and Hyperopt
aj-geddes
data-ai
machine-learning
38
recommendation-engine
Build recommendation systems using collaborative filtering, content-based filtering, matrix factorization, and neural network approaches
aj-geddes
data-ai
machine-learning
38
model-deployment
Deploy machine learning models to production using Flask, FastAPI, Docker, cloud platforms (AWS, GCP, Azure), and model serving frameworks
aj-geddes
data-ai
machine-learning
38
feature-engineering
Create and transform features using encoding, scaling, polynomial features, and domain-specific transformations for improved model performance and interpretability
aj-geddes
data-ai
machine-learning
31
hf-model-inference
Guidance for setting up HuggingFace model inference services with Flask APIs. This skill applies when downloading HuggingFace models, creating inference endpoints, or building ML model serving APIs. Use for tasks involving transformers library, model caching, and REST API creation for ML models.
letta-ai
data-ai
machine-learning
31
train-fasttext
This skill provides guidance for training FastText text classification models with constraints on accuracy and model size. It should be used when training fastText supervised models, optimizing model size while maintaining accuracy thresholds, or when hyperparameter tuning for text classification tasks.
letta-ai
data-ai
machine-learning
31
train-fasttext
Guidance for training FastText text classification models with constraints on model size and accuracy. This skill should be used when training FastText models, optimizing hyperparameters, or balancing trade-offs between model size and classification accuracy.
letta-ai
data-ai
machine-learning
31
mteb-leaderboard
Guidance for querying ML model leaderboards and benchmarks (MTEB, HuggingFace, embedding benchmarks). This skill applies when tasks involve finding top-performing models on specific benchmarks, comparing model performance across leaderboards, or answering questions about current benchmark standings. Covers strategies for accessing live leaderboard data, handling temporal requirements, and avoiding common pitfalls with outdated sources.
letta-ai
data-ai
machine-learning
31
hf-model-inference
Guidance for deploying HuggingFace models as inference APIs/services. This skill applies when tasks involve downloading pre-trained models from HuggingFace Hub, creating REST APIs for model inference, building Flask/FastAPI services around ML models, or setting up sentiment analysis, text classification, or other NLP inference endpoints.
letta-ai
data-ai
machine-learning
31
model-extraction-relu-logits
Guidance for extracting weight matrices from black-box ReLU neural networks using only input-output queries. This skill applies when tasked with recovering internal parameters (weights, biases) of a neural network that can only be queried for outputs, particularly two-layer ReLU networks. Use this skill for model extraction, model stealing, or neural network reverse engineering tasks.
letta-ai
data-ai
machine-learning
31
model-extraction-relu-logits
Guidance for extracting weight matrices from black-box ReLU neural networks using only input-output queries. This skill applies when tasks involve model extraction attacks, recovering hidden layer weights from neural networks, or reverse-engineering ReLU network parameters from query access.
letta-ai
data-ai
machine-learning
31
caffe-cifar-10
Guidance for building and training with the Caffe deep learning framework on CIFAR-10 dataset. This skill applies when tasks involve compiling Caffe from source, training convolutional neural networks on image classification datasets, or working with legacy deep learning frameworks that have compatibility issues with modern systems.
letta-ai
data-ai
machine-learning
31
pytorch-model-cli
Guidance for creating standalone CLI tools that perform neural network inference by extracting PyTorch model weights and reimplementing inference in C/C++. This skill applies when tasks involve converting PyTorch models to standalone executables, extracting model weights to portable formats (JSON), implementing neural network forward passes in C/C++, or creating CLI tools that load images and run inference without Python dependencies.
letta-ai
data-ai
machine-learning
31
mteb-leaderboard
This skill provides guidance for retrieving and verifying information from dynamic ML leaderboards (MTEB, Scandinavian Embedding Benchmark, HuggingFace leaderboards, etc.) with specific temporal requirements. It should be used when tasks involve finding top-performing models, rankings, or benchmark results as of a specific date, especially when the data source is frequently updated.
letta-ai
data-ai
machine-learning
31
largest-eigenval
Guidance for finding the largest eigenvalue of small dense matrices with performance optimization. This skill should be used when tasks involve computing eigenvalues (especially the dominant/largest eigenvalue), optimizing numerical linear algebra routines, or improving performance of numpy/scipy matrix operations for small matrices (typically 2-10 in size).
letta-ai
data-ai
machine-learning
31
torch-pipeline-parallelism
This skill provides guidance for implementing PyTorch pipeline parallelism for distributed training of large language models. It should be used when implementing pipeline parallel training loops, partitioning transformer models across GPUs, or working with AFAB (All-Forward-All-Backward) scheduling patterns. The skill covers model partitioning, inter-rank communication, gradient flow management, and common pitfalls in distributed training implementations.
letta-ai
data-ai
machine-learning
31
rstan-to-pystan
This skill provides guidance for translating RStan (R-based Stan interface) code to PyStan (Python-based Stan interface). It should be used when converting Stan models from R to Python, migrating Bayesian inference workflows between languages, or adapting R data preparation logic to Python equivalents.
letta-ai
data-ai
machine-learning
31
mlops-workflows
Comprehensive MLOps workflows for the complete ML lifecycle - experiment tracking, model registry, deployment patterns, monitoring, A/B testing, and production best practices with MLflow
manutej
data-ai
machine-learning
31
rstan-to-pystan
Guidance for converting R-Stan (RStan) code to Python-Stan (PyStan). This skill applies when translating Stan models and inference code from R to Python, including API mapping between RStan and PyStan 3.x, hyperparameter translation, and handling differences in output formats. Use this skill for statistical model migration, Bayesian inference code conversion, or when working with Stan models across R and Python ecosystems.
letta-ai
data-ai
machine-learning
31
pytorch-model-recovery
This skill should be used when reconstructing PyTorch models from weight files (state dictionaries), checkpoint files, or partial model artifacts. It applies when the agent needs to infer model architecture from saved weights, rebuild models without original source code, or recover models from corrupted/incomplete saves. Use this skill for tasks involving torch.load, state_dict reconstruction, architecture inference, or model recovery in CPU-constrained environments.
letta-ai
data-ai
machine-learning
31
pytorch-model-recovery
Guidance for recovering PyTorch model architectures from state dictionaries, retraining specific layers, and saving models in TorchScript format. This skill should be used when tasks involve reconstructing model architectures from saved weights, fine-tuning specific layers while freezing others, or converting models to TorchScript format.
letta-ai
data-ai