Skill UI

Execute complex and compute-intensive workloads directly on fully managed Hugging Face cloud infrastructure. This skill eliminates the need for local setup, allowing users to run jobs using cloud CPUs, GPUs, or TPUs. Ideal for large-scale data processing, batch inference, reproducible model training, and scheduled automation tasks, while persisting results to the Hugging Face Hub.

Automates Google Cloud IAM binding tasks by guiding users through best practices, generating production-ready code and configs, and validating outputs across compute, storage, BigQuery, Vertex AI, Cloud Run, Firebase, and other GCP services whenever iam binding creator is mentioned.

Automates iam policy creation for AWS Skills, activating when you mention the trigger, guiding best practices, generating production-ready configs, and validating outputs for compute, storage, networking, and serverless scenarios.

Automates AWS IAM role generation by guiding requests, applying best practices, and producing production-ready code/configs with validation for compute, storage, networking, and serverless workloads.

Automates AWS Lambda layer setup by providing step-by-step guidance, validating against best practices, and generating production-ready code and deployment configurations for compute, storage, and networking scenarios.

Execute comprehensive load, stress, and soak tests to validate API performance, identify scaling bottlenecks, and establish throughput baselines. This tool simulates realistic, high-volume traffic patterns using industry-standard tools like k6 or Artillery, allowing users to define complex scenarios (e.g., e-commerce checkout flows, traffic spikes) and assert performance thresholds (p95 latency, error rates). It helps pinpoint resource limitations in databases, network layers, or compute resources, ensuring the API is ready for production scalability.

This skill provides a comprehensive decision framework and set of patterns for architects designing cloud-agnostic applications across major providers like AWS, Azure, and GCP. It details service comparisons (Compute, Storage, DB), multi-cloud patterns (e.g., Best-of-Breed, DR), cost optimization strategies, and structured migration plans, ensuring robust and resilient enterprise deployments.

Enables Claude to invoke the computer-vision-processor plugin, auto-generating Python calls to run object detection, classification, and segmentation on user-provided images for detailed analysis.

PyTorch Lightning is a high-level framework built on PyTorch that significantly reduces boilerplate code in deep learning training loops. It automatically handles device management, distributed training (DDP, FSDP, DeepSpeed), mixed precision, and advanced callbacks. It allows researchers to scale models from local machines to supercomputers with minimal code changes, enabling clean, scalable, and best-practice deep learning implementations.

Automates S3 bucket policy generation within AWS, offering step-by-step guidance, safeguards best practices, and produces production-ready configurations for compute, storage, networking, and serverless scenarios.

Automates AWS SAM template building with best-practice guidance, production-ready code/config generation, validation, and coverage for compute, storage, networking, and serverless patterns when a user requests help with the SAM template builder.

Guides AWS users through generating secure security group configurations with best practices, automating code and configuration creation plus validation across compute, storage, and networking scenarios.