Skill UI

This is the Azure Resource Manager SDK for .NET, designed to streamline the deployment and management of Weights & Biases (W&B) ML experiment tracking instances directly through Azure Marketplace. It allows developers to programmatically create, configure, and manage W&B environments, including setting up marketplace details, managing admin users, configuring Single Sign-On (SSO), and ensuring robust ML observability within an Azure ecosystem. Ideal for MLOps pipelines.

This is the Azure Resource Manager SDK for .NET, designed to streamline the deployment and management of Weights & Biases (W&B) ML experiment tracking instances directly through Azure Marketplace. It allows developers to programmatically create, configure, and manage W&B environments, including setting up marketplace details, managing admin users, configuring Single Sign-On (SSO), and ensuring robust ML observability within an Azure ecosystem. Ideal for MLOps pipelines.

Mastering the full lifecycle of machine learning models from data ingestion to deployment. This expertise covers building robust, production-grade MLOps pipelines using orchestrators like Kubeflow, Airflow, or Prefect. Key skills include feature store implementation with Feast, rigorous data validation, experiment tracking (e.g., MLflow), model registry management, and automated deployment workflows. Essential for automating model training and ensuring reproducibility at scale.

This skill provides complete, programmatic integration with the protocols.io API v3, enabling advanced management of scientific protocols. Use it for the entire protocol lifecycle, including discovery by DOI or keywords, creating new protocols, managing steps and materials, coordinating collaborative development, organizing workspaces, and tracking experiments. It covers authentication, file handling, and discussion management, making it ideal for automated lab workflows and scientific documentation systems.

Utilize Modal, a serverless GPU cloud, for running complex machine learning workloads, including training, fine-tuning, and inference. This tool provides a zero-config environment, eliminating the need for SSH setup or Docker management. It features automatic scale-to-zero billing and local-first execution, making high-powered GPU compute accessible for debugging and small-scale experiments.

This skill provides comprehensive commands to manage the entire AI model evaluation lifecycle using Arize. Users can list, retrieve metadata, and export results from experiments. It is ideal for comparing multiple model runs, benchmarking performance against a dataset, and analyzing model accuracy using structured evaluation workflows (CRUD operations).

A comprehensive guide and playbook for managing feature flags across services or teams. It covers flag taxonomy (Release, Experiment, Ops, Permission), naming conventions, safe rollout strategies, creation checklists, and cleanup policies to prevent technical debt. Ideal for standardizing feature flag practices and governance.

This guide helps academics determine if their manuscript aligns with the scope of China Industrial Economics, or if it should be redirected to more specialized journals (e.g., Economic Research, Management World). It provides criteria based on empirical rigor, policy quasi-experiments, and specific research focus (industry, enterprise, environment).

A comprehensive guide for designing rigorous and robust empirical programs in Information Retrieval, Data Mining, and Knowledge Management. It outlines how to meet the stringent evidence requirements for top-tier conferences, ensuring claims are substantiated across multiple evaluation dimensions (retrieval, mechanism, scalability) and incorporating best practices for reproducibility and handling modern challenges like LLM contamination.

This skill systematizes the entire academic publishing journey for long-form papers, specifically targeting the requirements of top-tier journals like the Chinese Journal of Computers (CJC). It maps out the complete timeline from initial topic selection, through experimentation, writing, submission, multi-stage peer review, revision, and final publication, providing critical checkpoints and best practices to ensure a systematic and successful process.

A comprehensive guide for structuring rigorous research designs in Human Resource Management. It addresses advanced methodological challenges such as common-method bias (CMB), endogeneity, cross-level data analysis, and multi-wave longitudinal modeling. Learn how to align theoretical claims with appropriate designs (e.g., field experiments, panel data, multi-source surveys) to ensure causal inference and methodological rigor.

This skill offers a comprehensive project management framework for the end-to-end submission process of data mining research to major conferences like ICDM. It guides users through critical milestones, including topic selection, experimental design, abstract submission, and final camera-ready preparation. It emphasizes backward planning from the final deadline, addressing unique constraints such as no-rebuttal policies, short-paper contingencies, and strict page limits.