Skill UI

This comprehensive guide details the rigorous methodology for designing, executing, and reporting experimental results in Information Retrieval (IR). It covers best practices for selecting appropriate test collections, choosing defensible metrics, performing proper statistical significance testing (e.g., paired t-tests), ensuring baseline fairness, and proactively addressing modern pitfalls like LLM contamination. Essential for publishing high-quality, auditable research in IR/NLP.

A comprehensive guide for designing rigorous Monte Carlo simulation studies, particularly for methods-heavy academic submissions (e.g., SMR). This guide covers specifying the Data Generating Process (DGP) space, selecting non-negotiable competitor methods, choosing appropriate performance metrics (e.g., power, bias, coverage), and critically reporting the limitations and failure regimes of the proposed method to ensure maximum credibility and reproducibility.

A comprehensive pre-submission checklist designed for academics submitting manuscripts to scholarly journals. It covers crucial formatting rules, such as specific citation styles (Author-Date), bibliography standards (GB/T 7714), appropriate use of footnotes, abstract/keyword length limits, and guidelines for maintaining anonymity during the review process. Essential for ensuring submissions meet strict academic publishing requirements.

This skill is designed to help researchers critically assess whether their project aligns with the scope of Social Psychology Quarterly (SPQ). It guides users to pressure-test the core contribution: the link between social structure, process, and the individual. It helps frame the research question, determine the appropriate tradition (e.g., identity theory, symbolic interaction), and decide whether the final output should be a full Article or a focused Note.

This tool acts as an orchestrator for Social Psychology Quarterly (SPQ) submissions, guiding authors through the entire manuscript lifecycle. It routes the user based on the research stage, the sociological tradition (e.g., symbolic interaction, social structure), and the article type (Article vs. Note). Its core function is ensuring the paper maintains the critical link between the individual and society, directing the user to the appropriate specialized skill for design, theory, data, and writing.

A comprehensive, end-to-end audit checklist designed for authors submitting manuscripts to high-level academic journals like SSI. It covers critical areas including LaTeX formatting, selecting the appropriate article type, writing standalone bilingual abstracts, adhering to strict international citation standards (e.g., GB/T 7714), and complying with academic ethics policies (e.g., one-submission rule). Use this guide as the final quality assurance step before submission.

A comprehensive skill designed to guide authors on whether their observational, data-intensive manuscript is suitable for The Astronomical Journal (AJ). It details the journal's specific scope, required methodological rigor (e.g., uncertainty propagation), and adherence to AAS/AASTeX standards, serving as a pre-submission fit and re-framing tool.

A comprehensive guide designed for authors preparing manuscripts for submission to World Development (WD) via Elsevier Editorial Manager. This checklist ensures authors complete the required steps for double-anonymization, verify abstract/keyword limits, and properly include all necessary declarations (e.g., funding, ethics, conflict of interest) before final submission.

This guide provides a comprehensive framework for designing rigorous and defensible evaluation sections for machine learning and information retrieval papers, particularly for top-tier conferences like WSDM. It covers the four critical evidence quadrants—Effectiveness, Validity, Efficiency, and Robustness—and details necessary protocols, such as temporal splits, proper baseline selection (including heuristics), ablation studies, and hardware-aware performance reporting. Use this when auditing or writing the experimental section of a research paper.

An autonomous system designed to continuously improve code quality by scanning codebase metrics. It functions as an agent, proposing mechanical code changes, executing them, and committing only if defined metrics improve. It supports multiple modes (Scan, Scaffold, Run) for systematic, data-driven codebase refactoring.

A comprehensive white-box security auditing workflow designed for proprietary source code. It integrates static analysis security testing (SAST) tools like Semgrep and CodeQL to detect common vulnerabilities (e.g., injection, IDOR, crypto misuse), followed by mandatory manual threat modeling and verification steps. Applicable for PR reviews and pre-deployment security checks.

Draft, review, and stress-test arbitration clauses in commercial contracts. Produces clean clause text, concise reviews, severity-rated issue lists, proposed fixes, and optional reasoning or negotiation arguments. Suitable for non-specialists while supporting deeper analysis.