Skill UI

Build local, research-only computational pathology workflows with PathML: load and tile whole-slide images, run preprocessing and QC pipelines, manage h5path data, quantify multiplex images, construct spatial graphs, and plan bounded model inference.

This skill enables the construction and analysis of phylogenetic trees using tools like MAFFT for alignment, IQ-TREE 2 for maximum likelihood inference, and FastTree for large datasets. It supports evolutionary analysis, microbial genomics, viral phylodynamics, and molecular clock studies. Visualization is handled via ETE3 or FigTree. Ideal for inferring evolutionary relationships, detecting horizontal gene transfer, and reconstructing ancestral sequences in biological research.

Build, fit, and validate Bayesian models with PyMC 6, covering hierarchical models, MCMC/NUTS sampling, variational inference, prior and posterior predictive checks, diagnostics, and LOO/WAIC model comparison.

Python library skill for statistical modeling and econometrics: OLS/GLM/mixed models, discrete choice, ARIMA time series, diagnostics, residuals, and inference with coefficient tables.

Utilize Google's TimesFM foundation model for zero-shot univariate time series forecasting without training custom models. Supports sales, sensor, and weather data with point forecasts and prediction intervals. Includes mandatory system checks for RAM and GPU before inference to prevent crashes.

Load Hugging Face Hub models, run pipeline inference, generate text, and fine-tune with the Trainer API across NLP, vision, audio, and multimodal tasks using Python and PyTorch.

This guide covers advanced usage of the Anthropic Messages API. Learn how to implement real-time streaming responses, utilize system prompts for persona control, process visual inputs (Vision), and enforce structured data output (JSON). This is essential for building sophisticated, robust, and multi-modal Claude-powered applications.

Automate the entire deployment lifecycle for ML inference services on CoreWeave GPU cloud. This workflow integrates unit testing, container image building (to GHCR), and rolling deployment to CoreWeave Kubernetes clusters via GitHub Actions. Ideal for ensuring stable, high-performance deployment of GPU-dependent models. Key features include validating GPU manifest requests and managing deployments using standard Kubernetes APIs.

A comprehensive guide and set of tools for establishing a local development workflow tailored for CoreWeave GPU deployments. This includes steps for building Docker containers, validating Kubernetes YAML manifests using dry-run, and managing the full deployment lifecycle for AI inference services before pushing to the cloud.

This guide details the process of deploying production-grade inference services on CoreWeave using KServe. It covers setting up autoscaling, GPU scheduling, and implementing scale-to-zero functionality for efficient ML model serving endpoints. Ideal for MLOps engineers deploying large language models (LLMs) or other complex AI models in a production environment.

This skill provides comprehensive guidance for deploying and managing GPU-accelerated AI inference services on CoreWeave Kubernetes (CKS). It covers best practices including containerization using NVIDIA CUDA base images, configuring specific GPU resource limits (A100/H100), setting up robust health checks, and executing controlled rolling updates. Ideal for managing multi-model inference and scaling demanding AI workloads in a cloud environment.

This skill outlines how to implement and manage Role-Based Access Control (RBAC) and namespace isolation for multi-team GPU workloads running on CoreWeave's Kubernetes platform. It provides guidance on setting strict resource quotas, preventing noisy-neighbor issues, and defining granular roles (e.g., ML Engineer, Inference Operator). This is essential for maintaining resource isolation, ensuring compliance (SOC 2, HIPAA), and managing access across large-scale cloud deployments.