Discover the Best Claude Code Skills

PPT Design generates editable PowerPoint decks from prompts, README files, or structured content. It supports narrative-driven layouts, style combinations, AI images, and multiple build modes for business presentations.

Explain Like I Am turns complex topics, code, or errors into explanations matched to a specific audience level. Use it when someone asks to ELI5, simplify something, or tailor an explanation for a manager, parent, child, or other audience.

Performs deterministic Wenwang Najia hexagram casting, chart generation, and comprehensive interpretation for AI agents. Handles career, relationships, wealth, and other life questions, with safety boundaries for high-risk topics.

Create, revise, and benchmark cover letters for academic journal submissions using verified manuscript facts. Routes documents by research type (empirical, synthesis, bibliometric) for targeted editorial persuasion.

Improve an AI cover letter skill via controlled experiments with manuscript materials and expert benchmarks. Supports blind generation, route-specific training, and evaluation to avoid overfitting.

Hugging Face Community Evals runs inspect-ai and lighteval evaluations for Hugging Face Hub models on local hardware. Use it to choose an inference backend, smoke-test tasks, and run GPU evals with vLLM, Transformers, or accelerate.

HuggingFace Best Model Finder finds recommended Hugging Face models for a task by checking official benchmark leaderboards and model size. It helps when you need to compare candidates against device constraints or choose a top model to try.

HF Mem estimates the VRAM or memory needed to load Hugging Face Safetensors or GGUF model weights for inference. Use it to check whether a model fits on a GPU or instance, and optionally include KV cache estimates.

Serving Image Selection selects the correct SageMaker serving container URI for a model and region, then verifies it from the AWS catalog before deployment. Use it after choosing a deployment path and before endpoint code.

SageMaker Production Defaults creates a real-time SageMaker endpoint with a model, endpoint config, autoscaling, and CloudWatch alarms. Use it after the image and IAM role are known to deploy production serving defaults and smoke-test the endpoint.

SageMaker IAM Preflight checks for an existing SageMaker execution role before creating models, endpoints, or training jobs. It validates a provided role ARN or discovers a usable role when IAM access is failing.