Skill UI

This system deploys advanced AI, NLP, and behavioral analytics to detect sophisticated Business Email Compromise (BEC) attacks. Unlike traditional filters that rely on malicious links, this solution analyzes writing style, tone, grammatical patterns, and contextual anomalies to identify pure social engineering impersonation, providing a robust defense layer against advanced phishing and fraud.

This skill provides structured procedures and Python examples for detecting internal data exfiltration. It analyzes endpoint, cloud, and email logs by establishing behavioral baselines and performing statistical anomaly detection. Use cases include investigating insider threats, monitoring DLP policy violations, and building robust User and Entity Behavior Analytics (UEBA) rules for SOC teams.

This skill implements User and Entity Behavior Analytics (UEBA) using Elasticsearch/OpenSearch. It goes beyond static rules to build behavioral baselines (e.g., login times, data volume) for users and entities. By calculating anomaly scores and performing peer group analysis, it detects suspicious activities such as data exfiltration, privilege abuse, and unauthorized access, allowing organizations to proactively identify high-risk insider threats.

This skill performs User and Entity Behavior Analytics (UEBA) to identify anomalous user activities such as impossible travel, unusual access patterns, and privilege abuse. It establishes behavioral baselines using SIEM logs and statistical analysis, helping SOC teams detect insider threats and compromised accounts by flagging deviations from normal user behavior. Use when monitoring security hygiene and suspicious activity is critical.

Organize, query, validate, and convert neuroscience datasets using the Brain Imaging Data Structure (BIDS) standard. Supports MRI, EEG, and behavioral data. Use PyBIDS for indexing and bids-validator for compliance checking. Ideal for preparing data for analysis pipelines and repository submission.

A comprehensive framework for structuring user interviews, customer discovery, or Jobs-to-be-Done (JTBD) research. This guide provides structured steps for screener creation, deep behavioral exploration (focusing on past actions, not future predictions), and systematic synthesis/pattern detection, ensuring the gathering of genuine, actionable insights.

This tool guides the conceptual development of advanced accounting research manuscripts (CAR). It helps researchers build the core theoretical engine—the economic or behavioral mechanism, or the formal model—regardless of the methodology (e.g., archival, experimental, analytical). It ensures that hypotheses are directional, falsifiable, and rigorously grounded in established economic and accounting theory.

A structured guide on translating behavioral or game-theoretic arguments into pre-specified, quantitative, and testable hypotheses for Experimental Economics (ExpEcon) manuscripts. This methodology emphasizes moving beyond informal intuition by defining the experimental game, deriving benchmark predictions, layering competing behavioral accounts, and generating comparative-statics hypotheses that treatments must adjudicate. It is essential for manuscripts aiming to robustly test theory through design.

This tool guides authors through the rigorous standards required for publishing in top experimental economics journals. It serves as a comprehensive checklist, evaluating a manuscript's fit, methodological strength, design transparency, and structural requirements (e.g., pre-registration, incentive-compatibility) against best practices in behavioral and experimental economics.

This skill provides a rigorous academic review framework for determining if a research paper significantly advances the frontiers of game theory and its applications. It assesses conceptual advances, mechanism design robustness, behavioral novelty, and cross-field reach, guiding authors on whether their work meets the high standards of top-tier academic journals like GEB. Ideal for assessing high-level theoretical or empirical contributions.

This comprehensive guide outlines the process for packaging artifacts from Human-Robot Interaction (HRI) research. Recognizing that HRI artifacts are complex, involving human subjects, robot behaviors, and extensive study materials, this skill provides guidelines for honest, ethical, and reproducible dissemination. It covers structuring de-identified data, analysis code, and behavioral specifications while adhering to participant consent and academic archiving standards.

This guide ensures that the chosen research methodology genres (e.g., behavioral empirical, analytical modeling, design science) are correctly aligned with the core research claim or phenomenon. It helps researchers identify the necessary design rigor, appropriate identification strategies (like DiD or IV), and the level of analysis required to ensure the study can genuinely support its contribution in the IS domain.