Skill catalog

Compare Replicate models by cost, speed, quality, and capabilities.

Machine learning development with JAX, functional programming patterns, and high-performance computing.

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detect…

Deep learning framework (PyTorch Lightning / lightning package). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard, MLflow)…

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data…

Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Applies when working with AutoModel, pipelines, tokeniz…

Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature attributions, handling multi-output explanations, and producing local or global S…

Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to…

Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.

GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search…

Builds and checks Bayesian models with PyMC, including hierarchical models, NUTS MCMC, variational inference, mutable-data predictions, posterior predictive checks, diagnostics, and PSIS-LOO model comparison. Use for pr…

Applies UMAP-learn to nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows.

Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.

Builds, evaluates, and audits right-censored or competing-risk survival workflows with scikit-survival, including leakage-safe preprocessing, model selection, probability prediction, and censoring-aware metrics.

Supports PyTorch Geometric (PyG) graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with to…

Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy pa…

Performs zero-shot time-series forecasting with Google's TimesFM, including regular-grid CSV preparation, quantile forecasts, XReg covariates, and held-out evaluation. Uses the Apache-licensed TimesFM 2.5 checkpoint by…

Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.

Trains and evaluates single-agent reinforcement learning with Stable Baselines3 (PPO, SAC, DQN, TD3, DDPG, A2C), Gymnasium custom environments, vectorized rollouts, callbacks, and checkpoint normalization. Applies to re…

Solves and validates single-, multi-, and many-objective optimization with pymoo, including NSGA-II, NSGA-III, MOEA/D, constraints, Pareto approximations, reference directions, and ZDT/DTLZ benchmarks for engineering an…

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM…

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Covers the native 5.0 build and environment API, published 3.0…

Builds molecular property prediction and MoleculeNet workflows with DeepChem, including SMILES featurization, scaffold or grouped holdouts, masked labels, graph models and explicit pretrained encoder transfer. Used for…

Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes.

Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reason…

Uses the Biohub esm Python SDK for ESM3 protein generation, ESMC embeddings, and ESMFold2 all-atom folding. Applies to local model inference and Biohub hosted clients, including former Forge workflows; distinguishes the…

Builds and validates PyHealth clinical machine-learning pipelines for EHR, signals, imaging, and medical codes. Use for PyHealth dataset loading, MIMIC-III/IV, eICU or OMOP prediction tasks, patient-level evaluation, mo…

Fits probabilistic models for single-cell omics, including scVI batch integration, scANVI annotation, totalVI CITE-seq, MultiVI RNA/ATAC integration, and posterior differential expression. Use for generative modeling, r…

Featurizes small molecules with Molfeat for QSAR/QSPR, chemical similarity, virtual screening, and molecular ML. Covers ECFP/MACCS fingerprints, RDKit descriptors, pharmacophores, pretrained embeddings, configuration pe…

Builds and differentiates PennyLane quantum circuits, hybrid PyTorch or JAX models, molecular VQE and QAOA workflows. Use for variational quantum algorithms, quantum machine learning, simulator validation, and moving va…

Builds, simulates, transpiles, and executes quantum circuits with Qiskit and IBM Quantum Runtime. Use for Qiskit 2.x circuits and operators, V2 Sampler or Estimator primitives, target-aware transpilation, local or noisy…

Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-asr).

Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time d…

Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, diagnostics, data-only fetch, or install.

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestrat…

Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.

Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.

Evidence-gated workflow for MoE performance optimization in Megatron Bridge. Covers measurement contracts, the Three Walls framework, parallel folding, profiling, matched A/B tuning, and final validation.

Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backends such as DeepEP and HybridEP.

Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and Qwen3-Next long-context experiments.

Representative, point-in-time MoE training playbooks by hardware and model family. Use them as candidate seeds, then revalidate the exact runtime, semantics, topology, and steady-state throughput.

Expert guidance for deep learning, transformers, diffusion models, and LLM development with PyTorch, Transformers, Diffusers, and Gradio.

Used for finetuning NV-Generate-CTMR MR-Brain v1 for T1, T2, FLAIR, SWI, or MRA data from a NIfTI datalist. Not for clinical or production data approval.

Runs standard or fixed-channel softmax finetuning of NV-Segment-CT VISTA3D on CT NIfTI image/label datasets, with optional MONAI-native MLflow tracking and checkpoint evidence. Uses softmax for predefined, mutually excl…

Use when implementing ANY computer vision feature — image analysis, pose detection, person segmentation, subject lifting, text recognition, barcode scanning.

Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists. Not for clinical or production data approval.

Package and build custom AI models with Cog for deployment on Replicate. Use when creating a cog.yaml or predict.py, defining model inputs and outputs, loading model weights at setup time, building Docker images for ML…

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), tra…