Skill UI

This comprehensive skill analyzes sleep data to identify patterns, assess quality, and detect potential sleep disorders. It tracks trends in sleep duration, efficiency, and consistency, and performs advanced correlation analysis with other health metrics like exercise, diet, and mood. The output provides actionable, personalized recommendations based on scientific data, helping users improve their overall sleep health.

Systematically evaluates cyber-campaign evidence to attribute a cyber operation to a specific threat actor. This skill utilizes advanced analytical frameworks like the Diamond Model and Analysis of Competing Hypotheses (ACH) to weigh multiple indicators, including infrastructure overlaps, TTP consistency, malware similarity, and operational patterns, providing confidence-weighted attribution assessments for incident response.

This skill safely randomizes the order of repetitive JSON objects within an array without corrupting the data or breaking the JSON syntax. It acts as a data engineer, rigorously validating the input schema (checking for property consistency and lack of nesting) before performing the shuffle. It ensures data integrity is maintained while reordering records, making it ideal for testing, simulation, or data preparation workflows.

A comprehensive guide covering the canonical rules for Power BI report design. It enforces consistency across design identity, visual hierarchy, color discipline, chart selection, and accessibility. Focuses on structuring reports to answer specific questions and minimizing cognitive load, ensuring data effectiveness over mere aesthetics.

A comprehensive guide for conducting rigorous mechanism analysis in empirical finance and economics papers. It covers three main testing paths (Mediation, Replacing Y, Sub-samples), best practices for causal inference (e.g., recommending Bootstrap over Sobel), and the academic structure required for high-impact journals. Focuses on time consistency, theory grounding, and excluding competing explanations.

A comprehensive methodology for designing scientific and reproducible storage evaluations, particularly for high-stakes submissions. This guide covers controlling device state (aging, preconditioning, TRIM), selecting credible workloads (fio, YCSB), matching metrics (P99.9 latency, bytes-written) to claims, and rigorously testing durability and crash consistency on real hardware.

This comprehensive guide details the rigorous methodological standards required for validating new statistical estimators, tests, or algorithms. It moves beyond simple causal inference, emphasizing foundational proofs of identification, regularity conditions, asymptotic consistency, and finite-sample robustness. It serves as a checklist for assuring the credibility and reliability of methods in academic statistical journals.

A comprehensive guide to constructing rigorous empirical datasets for academic papers in finance and banking. It covers best practices for handling complex data sources (e.g., bank micro-data, central bank reports, macro series), addressing measurement biases, and ensuring full replicability, adhering to the standards of top-tier economic journals. Focus areas include merger tracking, regime transitions, and variable definition consistency.

This guide outlines the rigorous formal requirements for econometric papers, focusing on achieving the level of mathematical rigor expected by top academic journals. It covers proving identification, verifying primitive assumptions, constructing asymptotic derivations (consistency, rate, distribution), and structuring proofs for maximum verifiability in causal inference and time series analysis.

This comprehensive guide outlines best practices for creating key clinical display items, including Table 1 (baseline characteristics), Kaplan-Meier curves, Forest Plots, and CONSORT diagrams. It emphasizes statistical rigor (e.g., using standardized differences instead of P values for baseline), ensuring numbers-at-risk, and maintaining consistency across all reporting elements for high-impact medical publications.

A comprehensive guide for researchers in Pervasive Computing on ensuring the verifiable and reproducible nature of sensing data-driven claims. It mandates strict documentation practices covering dataset availability statements, sensing provenance (devices, labeling, preprocessing), cross-subject evaluation (LOSO), and consistency between published results and source data, adhering to ethical guidelines.

A comprehensive guide for maintaining consistency and completeness of references for PNAS Nexus submissions. It details the critical differences between the format-neutral requirements at submission time and the final numbered style required for publication, emphasizing the proper citation of datasets, software, and preprints.