Machine learning

Routes Cognee AI memory platform tasks across SDK memory APIs, graph/RAG retrieval, configuration, custom pipelines, session memory, CLI, API, MCP, and…

Use richzhang/colorization PyTorch colorizers for automatic image colorization, Python API calls, preprocessing/postprocessing, and runtime troubleshooting.

Use ColossalAI for distributed PyTorch training, large-model parallelism, Booster plugins, ShardFormer, Colossal-Inference, and first-party application…

Use MosaicML Composer for PyTorch training loops, speedup methods, loggers, checkpoints, distributed launch, profiling, and model export.

Route ControlNet 1.0 source-checkout tasks for annotators, Gradio inference apps, training datasets, and model/weight utilities.

Operate Core ML Tools workflows for model conversion, Core ML artifact I/O, optimization, MIL debugging, and platform-aware troubleshooting.

Routes agents using or contributing to CrewAI, including crews, flows, CLI projects, tools, MCP, memory, RAG, LLM providers, observability, files, multimodal…

Routes CS230 code-example requests to the correct PyTorch or TensorFlow vision and NLP workflows for SIGNS image classification and named-entity recognition.

cuML operating skill for GPU-accelerated classical ML, cuml.accel, Dask multi-GPU workflows, data utilities, and native source-build guidance.

Route D-FINE object-detection setup, training, architecture inspection, inference, export, and troubleshooting workflows.

Operate lucidrains DALLE-pytorch for DALL-E style VAE training, transformer training, generation, CLIP ranking, and backend troubleshooting.

Use the DALLE2-pytorch package for DALL-E 2 style text-to-image model APIs, diffusion prior/decoder training, WebDataset data layouts, and tracker/checkpoint…

Use DB-GPT 0.8.1 as an agentic AI data platform: install and configure provider profiles, operate its CLI and services, build agents and AWEL flows, ingest…

Use DeepCTR-Torch for PyTorch CTR/recommender feature columns, single-task models, DIN/DIEN sequence models, and multi-task learning workflows.

Use DeepDanbooru for anime-style image tag estimation, project and Danbooru-style dataset preparation, TensorFlow training, image evaluation, TFLite…

Use the DeepGCNs PyTorch operating guide for graph convolution layers, dynamic and dilated KNN blocks, point-cloud classification or segmentation, PPI…

Route and use the repository's PyTorch reinforcement-learning examples across tabular control, DQN, on-policy actor-critic, and off-policy continuous control.

Operate Tongyi DeepResearch and its WebAgent family: ReAct inference setup, rollout validation, benchmark evaluation, and variant routing.

Route DeepSearcher workflows for provider setup, data ingestion, RAG querying, CLI and service operation, and evaluation.

Route Deepchecks package tasks for ML data/model validation across tabular, NLP, vision, result export, and integration workflows.

Use DeepChem for molecular machine learning, data loading, featurization, model training, MoleculeNet, docking, and optional backend troubleshooting.

Use this DeepCTR repo skill for CTR/recommender feature columns, Keras models, sequence/session models, multitask models, and legacy TensorFlow Estimator…

Route DeepLabCut markerless pose-estimation workflows, project setup, PyTorch training/inference, maDLC tracking, Model Zoo, post-processing, 3D, and export…

Route DeePMD-kit package workflows for installation, data/config preparation, training, inference/model operations, integrations, and repository development.