Skill UI

Execute arbitrary PySpark or pure Python code directly on Fabric Spark compute using the Livy API. This method creates ephemeral sessions without generating persistent notebook artifacts. It provides full read/write access to lakehouse Delta tables, making it ideal for agent-driven ETL pipelines, quick data transformations, or analyses where session cleanup is critical. Users must manage the session lifecycle (create, run, and delete).

This skill analyzes your data warehouse to pinpoint stale, unused, or redundant tables that contribute to unnecessary storage costs. It classifies waste patterns (e.g., Zombie, Temporary) and computes safety tiers, helping users understand which assets can safely be dropped or archived to optimize spending and improve data governance.

A comprehensive guide for academics submitting AI and statistical research papers. It details how to map every claim (theoretical, algorithmic, or empirical) to verifiable evidence, covering necessary details like datasets, hyperparameters, random seeds, compute resources, and uncertainty estimates. It outlines the standards for achieving high levels of reproducibility, from descriptive to turnkey, ensuring scientific rigor for top-tier conferences.

This guide provides comprehensive standards for achieving auditability and transparency in Computer-Supported Cooperative Work (CSCW) research. It teaches researchers how to document non-shareable evidence, such as field interviews, log traces, and system deployments, by focusing on detailed analysis trails, decision logs, and rigorous process documentation, thus strengthening academic rigor.

A comprehensive guide for authors submitting to Computer Science journals, detailing how to achieve full experimental reproducibility. It systematically covers locking environments (dependencies, hardware, seeds), preventing data leakage, structuring the submission package, and creating a clear audit trail so reviewers can independently reproduce all main results from raw data.

A comprehensive guide on structuring and writing the 'Related Work' section for elite computer vision conferences like CVPR. It addresses the high velocity of academic literature, teaching advanced methods like defining explicit technical deltas, structuring arguments by research question, maintaining citation hygiene, and handling complex reviewer feedback on originality and concurrency.

A comprehensive guide for positioning novel research in elite computer vision and AI conferences (e.g., ECCV). It details how to structure the related work section by tracing academic lineage, handling concurrent work, verifying citation hygiene across venues (CVPR, ICCV, ECCV), and transforming simple bibliographies into strong, argumentative prose. Essential for improving novelty visibility.

A comprehensive guide for authors submitting data mining research to elite computer science venues like ICDM. This skill helps define the paper's fit, target the correct scope (algorithms, graph mining, etc.), and structure the manuscript to meet rigorous academic standards. It emphasizes providing sufficient evidence, rigorous baselines, and clear positioning relative to the conference's focus.

A comprehensive guide for authors submitting manuscripts to IEEE Transactions on Medical Imaging (TMI). It details the journal's specific scope, required technical rigor, necessary validation standards, and structure, emphasizing that contributions must be medical-imaging-specific rather than generic computer vision methods. This tool helps authors assess fit, re-frame their work, and anticipate submission requirements.

A comprehensive guide for designing and presenting rigorous experiments for top-tier computer science journals. It covers best practices for ensuring reproducibility, matching evidence to claims, selecting appropriate baselines, performing statistical significance testing, and handling modern challenges like LLM contamination and system scalability measurements. Essential for passing double-blind peer review.

A comprehensive guide for authors submitting to machine learning conferences like NeurIPS. It details the rigorous standards for data splitting, hyperparameter reporting, random-seed protocols, and compute transparency required for a main-track paper. It also helps authors strategically decide between the main track and the MLRC/TMLR routes based on their core contribution (replication vs. novelty).

This skill guides authors on strategically positioning data mining research for the SIAM International Conference on Data Mining (SDM). It helps adjust manuscript framing, emphasizing mathematical rigor, statistical depth, and algorithmic contribution suitable for top Computer Science venues. Use it for venue selection, understanding reviewer expectations, and structuring evidence to meet the high standards of SIAM-style research.