Skill UI

A comprehensive guide for conducting and reporting rigorous experimental research in social and behavioral sciences. It covers various design types (vignette, lab, field), statistical requirements (effect sizes, power analysis), quality control measures (manipulation checks, confound control), and advanced techniques for establishing causality, ensuring high internal validity for academic publication.

A comprehensive skill for assessing whether a neuroscience manuscript meets the exacting standards of a top-tier journal. It guides authors through evaluating the conceptual advance, mandatory multi-level integration (molecular to behavioral), the necessity of causal intervention, and adhering to strict structural and methodological requirements (e.g., STAR Methods, data availability). Ideal for researchers aiming to refine their work before submission.

This guide assists researchers in selecting the most appropriate and rigorous methodology for Production and Operations Management (POM) manuscripts. It covers various research tracks, including analytical modeling, stochastic process theory, game theory, causal empirical identification (DiD, IV, RD), behavioral experiments, simulation, and operations data science (ML/forecasting). It ensures the research method is tightly linked to the core operational question and possesses significant practical value.

Guides the rigorous development of theoretical models and research frameworks for Production and Operations Management (POM) manuscripts. It covers analytical, empirical, and behavioral tracks, ensuring that all assumptions and mechanisms are deeply grounded in real-world operational constraints and decision-making processes, thereby building a defensible academic argument.

This skill helps authors determine the suitability of their research paper (analytical, empirical, or behavioral) for prestigious Operations Management journals like Production and Operations Management (POM). It provides detailed guidance on required scope, methodological rigor (e.g., identification strategies, model assumptions), structural requirements, and common pitfalls to ensure maximum publication potential.

A comprehensive framework for ensuring reproducibility in Web Search and Data Mining (WSDM) research. It addresses unique challenges associated with behavioral data, covering data provenance, temporal splitting discipline, bias assumption reporting, statistical rigor (seeds, variance), and the 'honesty ladder' for non-reproducible results, helping researchers publish robust and verifiable work.

This skill is designed for deep security and behavioral analysis within the Kubernetes control plane. It specializes in tracing complex interactions, including RBAC edge cases, service-account trust paths, admission webhook behavior, resource mutation, and cluster-level state drift. Use it when diagnosing why live workloads differ from manifest declarations, or when investigating cluster-wide permission issues.

A highly specialized, downstream skill for advanced threat analysis. This tool is used to recover hidden configurations, decode C2 (Command and Control) parameters, unpack staged payloads, and extract Indicators of Compromise (IOCs) from complex malware samples. It focuses on identifying the exact decode chains—including compression, encoding, and crypto steps—and linking recovered fields to observed behavioral outcomes within a sandbox environment.

This skill is designed for deep forensic analysis of asynchronous processing chains, specifically focusing on 'drift'—behavioral or configuration differences between a synchronous request path and subsequent worker-executed tasks. Use it to trace payloads, inspect worker-only state, follow retry mechanisms, handle dead-letter queues, or connect enqueued items to eventual side effects (e.g., file writes, cache updates, emails). It is a specialized downstream tool, requiring prior orchestration context.

Comprehensive workflow for analyzing suspected malware via static, dynamic, and behavioral techniques. Covers IOC extraction, YARA/Sigma rule generation, sandbox automation, and anti-analysis bypassing.

A disciplined methodology for fixing bugs and small behavioral changes with minimal impact. It involves tracing symptoms to the narrowest responsible mechanism, implementing changes only at that layer, and adding highly focused regression proofs to ensure surrounding functionality remains intact. Ideal for critical systems requiring maximum stability.

A set of behavioral guidelines derived from Andrej Karpathy's observations to help users writing, reviewing, or refactoring code with Large Language Models (LLMs). It guides developers to avoid overcomplication, make surgical changes, explicitly surface assumptions, and define verifiable success criteria, promoting clean, simple, and robust code development.