Skill UI

This comprehensive Python SDK serves as a client library for managing the full lifecycle of Machine Learning resources on Azure Machine Learning. It allows users to programmatically handle workspaces, register data and models, provision compute clusters, define complex training jobs, and build reproducible, end-to-end MLOps pipelines.

This comprehensive Python SDK serves as a client library for managing the full lifecycle of Machine Learning resources on Azure Machine Learning. It allows users to programmatically handle workspaces, register data and models, provision compute clusters, define complex training jobs, and build reproducible, end-to-end MLOps pipelines.

Personalized reports that analyze recent Claude Code chats to surface recurring challenges, highlight learning gaps, curate HackerNews resources, and deliver actionable development insights directly to your Slack DMs for targeted growth.

This skill provides foundational examples for interacting with Guidewire's core cloud APIs, including PolicyCenter, ClaimCenter, and BillingCenter. It demonstrates how to execute initial RESTful API calls, query resources (like accounts and claims), and understand common API response structures, pagination, and error handling patterns. Ideal for connectivity testing, learning Guidewire's REST structure, and prototyping basic insurance integrations.

This comprehensive workflow guides users through the end-to-end process of utilizing cloud-based GPU computing resources on Vast.ai. It covers searching for ideal GPU offers based on specs and price, provisioning an instance, running complex training or inference jobs via SSH, collecting model artifacts, and crucially, destroying the instance to prevent unexpected billing. Ideal for deep learning training and research.

Transforms existing code files into highly effective learning resources by adding context-aware educational comments. Acting as an expert educator, this tool tailors explanations—from foundational concepts for beginners to deep architectural insights for advanced practitioners—while strictly maintaining the original file's structure, encoding, and syntax. Ideal for generating self-documenting, pedagogically rich codebases.

This guide details how to set up and execute large-scale, distributed GPU training jobs on the CoreWeave platform. It covers both single-node multi-GPU setups and multi-node training utilizing PyTorch DDP and Kubernetes resources (A100/H100). This workflow is ideal for fine-tuning large language models (LLMs) or running complex deep learning models that require high-performance, shared-storage compute clusters.

This skill transforms a course syllabus (PDF, DOCX, etc.) into a highly curated, supplementary academic reading list. It parses topics and learning outcomes, calibrates content difficulty based on the target audience (undergraduate, graduate, etc.), and searches academic databases (Consensus) for recent, peer-reviewed papers. The output is a professional .docx file containing summaries, links, and advanced discussion questions, making it invaluable for educators and students needing structured, up-to-date course resources.

This skill transforms the current workspace into a comprehensive, stateful teaching environment. It guides the user through deep, multi-session learning by structuring content into core components: a defined mission, reference materials, curated resources, structured lessons, and continuous learning records. It employs educational best practices (spaced repetition, retrieval practice) to ensure long-term knowledge retention.

This skill manages the entire lifecycle of long-running deep learning training and inference jobs deployed on remote, ephemeral computing environments (e.g., AutoDL, RunPod, bare SSH, Slurm, K8s). It provides critical capabilities like resilient checkpointing, managing spot instance preemption, debugging resource failures (OOM, NaN), and ensuring safe billing teardown, making it essential for professional ML Ops on rented resources.

This skill guides users through building, deploying, and maintaining machine learning applications on Hugging Face Spaces. It provides comprehensive knowledge on selecting the optimal SDK (Gradio, Docker, Static), choosing appropriate hardware resources (ZeroGPU, dedicated GPUs, CPU-basic), and following best practices to ensure ML applications are deployed efficiently and successfully on the platform.

This tool acts as a personalized mentor for Swedish language learners. It guides users by assessing their CEFR level and recommending curated, skill-specific resources (YouTube clips, podcasts) and a structured learning path for listening, reading, writing, and speaking. It prioritizes authentic, level-appropriate content from trusted sources.