Machine learning

Routes FCOS object-detection repo tasks for inference demos, config/data setup, training/evaluation, ONNX export, and legacy PyTorch internals.

Use for Feast feature store tasks: feature repositories, definitions, CLI, retrieval, materialization, serving, RAG/vector search, integrations, and Feast…

Use FFCV to convert datasets into .beton files, build fast PyTorch loader pipelines, handle image and custom fields/transforms, and tune cache, traversal, and…

Use FlashRAG for retrieval-augmented generation research workflows: config/data validation, retrieval and index building, generation/refinement components…

Routes official FlashVSR diffusion-based streaming video super-resolution setup, model preparation, and CUDA inference for v1 and v1.1.

Repository operating skill for using Flow Forecast's flood_forecast package for time-series forecasting, data preparation, training, inference, evaluation…

Foolbox operating guidance for wrapping vision models, running adversarial attacks, measuring clean and robust accuracy, handling NumPy/PyTorch/TensorFlow/JAX…

Operate the legacy Frustum PointNets code release for KITTI or SUN RGB-D data preparation, TensorFlow runtime setup, training, inference, and 3D detection…

Use geemap for Google Earth Engine interactive mapping, geospatial conversion, visualization, timelapse, and ML helper workflows.

Get an independent second opinion or delegate work to the OTHER coding CLI — whichever model family is NOT currently active.

This skill should be used when the user asks to "align docs", "sync documentation", "update README", "update CLAUDE.md", "fix stale docs", "audit…

Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.

Router for Alpamayo R1 multimodal driving inference and trajectory sampling.

Routes BackgroundMattingV2 tasks for background matting inference, export, and training workflows.

Route Baichuan2 chat inference, deployment/quantization, and fine-tuning workflows.

Use BERT-pytorch for corpus preparation, vocabulary building, and tiny BERT pretraining workflows.

Route BERTopic topic modeling, embedding, vectorizer, labeling, visualization, and serialization workflows.

Route BiRefNet image segmentation, matting, inference, configuration, training, evaluation, and model-export workflows.

Route Chinese-LLaMA-Alpaca model reconstruction, inference/deployment, training/fine-tuning, and evaluation workflows.

Routes Chinese-LLaMA-Alpaca-2 training, inference, serving, evaluation, and integration workflows.

Use OpenAI CLIP for zero-shot image-text inference, prompt engineering, feature extraction, and responsible evaluation.

Training, inference, and deployment workflows for DAMO-YOLO object detection.

Route DeblurGAN users to data preparation, training, and single-image inference workflows.

Routes Distil-Whisper inference, PyTorch distillation training, and Flax reproduction workflows.