Agent skills for Claude Desktop

Diagnose and fix CoreWeave GPU scheduling, pod, and networking errors.

Run distributed GPU training jobs on CoreWeave with multi-node PyTorch.

Optimize CoreWeave GPU cloud costs with right-sizing and scheduling.

Handle training data and model artifacts on CoreWeave persistent storage.

Deploy inference services on CoreWeave with Helm charts and Kustomize.

Deploy a GPU workload on CoreWeave with kubectl.

Incident response runbook for CoreWeave GPU workload failures.

Migrate ML workloads from AWS/GCP/Azure to CoreWeave GPU cloud.

Optimize CoreWeave GPU inference latency and throughput.

Reference architecture for CoreWeave GPU cloud deployments.

Production-ready patterns for CoreWeave GPU workload management with

Create and manage database migrations with proper rollback methods, focused changes, and zero-downtime deployment considerations.

Define database models with clear naming, appropriate data types, proper constraints, and relationship definitions.

Write secure, performant database queries using parameterized statements, proper indexing, and query optimization techniques.

Apply diagonal-cut corners and chamfered edges to buttons, cards, panels, and container shells.

ML/AI engineer — LLM integrations, prompt engineering, model pipelines, evals, RAG.

CosmoSIS cosmological parameter estimation skill for MCMC sampling and likelihood analysis

Empowers Claude with human-like web browsing, real-time search, and dynamic interaction capabilities using Chrome DevTools Protocol (CDP).

Automated search for counterexamples to mathematical conjectures

Create detailed text-to-image prompts for album and song cover artwork optimized for Midjourney, DALL-E, and other AI image generators

Use when writing the cover letter and editor-facing metadata for an Environmental Science & Technology (ES&T) submission.