473 skills · sorted by relevance
Coordinates specialist agents in Claude Code to work from product requirements through design, implementation, testing, deployment, and operations. Includes task queues, saved progress, parallel reviews, and recovery workflows for managing extended development work.
Build data processing pipelines for machine learning, from preprocessing to batch predictions. Uses Ray Data to handle datasets larger than memory, distribute work across CPUs and GPUs, and feed data into training frameworks.
Design AI agent analytics workflows across distributed tables and documents. Combine Knowledge Catalog for metadata, meaning information about data and its usage rules, with managed Spark processing to produce architecture diagrams, deployment guidance, and validation plans.
Run batch processing, scientific simulations, and machine learning training on Google Kubernetes Engine. Configure parallel jobs, queues that manage resource access, and distributed computation, with guidance on scaling idle capacity down and recovering from interruptions.
Set up distributed tracing in KubeSphere to follow requests across services. Covers extension installation, trace collection, automatic application instrumentation, and API queries for traces, individual processing steps, and service connections.
Configure large language model training across multiple NVIDIA GPUs with Megatron-Core. The skill helps choose how to split models and workloads, set training parameters, monitor performance, and address memory shortages or low GPU utilization.
Build data processing pipelines for machine learning, from preprocessing to batch predictions. Uses Ray Data to handle datasets larger than memory, distribute work across CPUs and GPUs, and feed data into training frameworks.
Organize PyTorch training code with LightningModule and Trainer. This skill guides training, validation, logging, model checkpoint saving, early stopping when progress stalls, and configuration for running the same model across multiple GPUs.
Guides LLM training with verl using rewards to improve model responses. Covers data preparation, reward functions, GRPO and PPO configuration, distributed GPU training, and troubleshooting memory shortages or unstable training.
Design controlled failure experiments for distributed systems to examine how services recover. Produce failure injection scripts, monitoring plans, rollback procedures, and exercise guides, then turn findings into documented improvements.
Write Apache Cassandra distributed tests that simulate multiple nodes within one JVM, the Java runtime. The guide covers cluster setup, queries, node restarts, message dropping for failure scenarios, and troubleshooting problems caused by isolated class loading.
Review Apache Pinot changes for concurrency and state safety, including locks, shared callbacks, lifecycle changes, and distributed metadata. Use it to examine how changes affect shared state when multiple operations run at the same time.
Coordinate multiple AI agents for research, development, testing, and system analysis. It guides role assignment, communication structures, parallel and sequential tasks, shared memory, progress monitoring, and recovery, bringing separate contributions into reports or coordinated development workflows.
Train, deploy, and run predictions with neural networks using Flow Nexus and E2B sandboxes, isolated computing environments. Use existing model templates, distribute training across multiple environments, and check training progress and model performance.
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor, scatter_tensor, domain parallelism, sequence/spatial sharding, ring attention, DeviceMesh + DDP/FSDP2 hybrid parallelism, or physicsnemo.domain_parallel. Do NOT use for generic PyTorch DDP/FSDP setup without domain parallelism, picking a PhysicsNeMo model or example (use physicsnemo-discover), or non-distributed training questions.
The English summary is being prepared. Showing the original description.
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
The English summary is being prepared. Showing the original description.
Design scalable distributed systems using structured approaches for load balancing, caching, database scaling, and message queues. Use when the user mentions "system design", "scale this", "high availability", "rate limiter", "design a URL shortener", "design Twitter", "design Uber", "design a news feed", "system design interview", "capacity planning", or "distributed architecture". Also trigger when estimating infrastructure requirements, choosing between microservices and monoliths, or designing for millions of concurrent users. Covers common system designs (TinyURL, feeds, chat) and back-of-the-envelope estimation. For data fundamentals, see ddia-systems. For resilience, see release-it.
The English summary is being prepared. Showing the original description.
Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choice", "which database should I use", "SQL or NoSQL", "replication lag", "partitioning strategy", "consistency vs availability", "stream processing", "ACID transactions", "eventual consistency", "my queries are slow at scale", or "data is inconsistent across replicas". Also trigger when choosing a datastore, designing data pipelines, or debugging distributed-system consistency issues. Covers data models, batch/stream processing, and distributed consensus. For system design, see system-design. For resilience, see release-it.
The English summary is being prepared. Showing the original description.
You are a debugging expert specializing in setting up comprehensive debugging environments, distributed tracing, and diagnostic tools. Configure debugging workflows, implement tracing solutions, and establish troubleshooting practices for development and production environments.
The English summary is being prepared. Showing the original description.
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
The English summary is being prepared. Showing the original description.
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
The English summary is being prepared. Showing the original description.
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.
The English summary is being prepared. Showing the original description.
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus
The English summary is being prepared. Showing the original description.
Configure scheduled tasks and distributed locking with ShedLock in Spring Boot. Use when implementing @Scheduled tasks or distributed locking with ShedLock in Spring Boot.
The English summary is being prepared. Showing the original description.