Skill UI

Guides designing and implementing horizontal database sharding, covering key selection, migration planning, and cross-shard coordination for scalable systems.

Guides MCP server developers through the mandatory mcp-use best practices, reference files, scaffolding workflow, auth options, backend primitives, and architecture checkpoints before implementing features.

Guides Bukkit/Spigot/Paper plugin development with event architecture, NMS hooks, performance profiling, and ecosystem integration; ideal for building scalable Minecraft servers.

Guides ML engineers in building production-ready systems with PyTorch 2.x, TensorFlow, and modern tooling, covering serving pipelines, feature engineering, monitoring, and MLOps infrastructure for scalable, reliable deployments.

A comprehensive MLOps engineer skill that covers building scalable ML infrastructure, pipelines, experiment tracking, registries, and cloud-native deployments across AWS, Azure, and GCP with best practices for reliable automation.

Modal's serverless GPU cloud platform lets teams run ML training, inference, and batch jobs with pay-per-second pricing, automatic scaling, Python-native infra definitions, fast cold starts, and container caching.

Guide to training Mixture of Experts models with DeepSpeed or HuggingFace for large-scale sparse architectures like Mixtral 8x7B, focusing on routing, load balancing, and cost-efficient scaling.

Provides expert guidance on monorepo architecture, build systems, and dependency management using Nx, Turborepo, Bazel, and Lerna to set up scalable workspaces, optimize CI, and orchestrate tasks across multi-project teams.

This skill provides guidance on building and managing scalable monorepositories. It focuses on enabling efficient code sharing, ensuring consistent tooling across multiple packages and applications, and facilitating atomic, reliable changes. Use it when setting up new monorepo architectures, migrating from multi-repo setups, optimizing build/test performance, or establishing robust CI/CD pipelines for large, interconnected codebases.

Guide for automating Ncscale operations through Composio’s Rube MCP, covering connection prerequisites, mandatory schema-aware tool discovery, execution steps, and safety notes for reliable workflow orchestration.

NeMo Curator runs GPU-accelerated data curation for LLM training, covering text, image, video, and audio pipelines with fuzzy/semantic deduplication, quality classifiers, and PII/NSFW filters before scaling across RAPIDS clusters.

Guides teams through designing and building scalable modular monolith backends in NestJS, leveraging DDD, Clean Architecture, CQRS, and NX monorepos while planning evolution paths to microservices.