Skill UI

This skill helps transform vague product or engineering ideas into structured, verifiable acceptance criteria (AC). It is crucial for high-impact changes involving security, data migration, or external APIs. By inspecting existing context and asking minimal, targeted questions, it produces clear, observable criteria, significantly de-risking the development process and ensuring handoff readiness.

This skill helps optimize and verify latency-sensitive systems such as real-time dashboards, market data feeds, and streaming agents. It involves tracking p50/p95/p99 latency, freshness age, and queue depth. You will map hot paths and run live readbacks to ensure performance. Use this when throughput or data freshness matters in engineering contexts.

A comprehensive guide for researchers and reviewers designing or auditing Automated Software Engineering (ASE) evaluations. It outlines the necessary rigor, including the use of real subject systems, establishing fair and runnable tool baselines, performing targeted ablations (especially for LLMs), defining explicit oracles, and ensuring full data and model provenance to guarantee reproducible and scientifically sound results.

A comprehensive guide for researchers submitting to ASE (Automated Software Engineering). It details mandatory requirements for ensuring research reproducibility, covering the Data Availability Statement, providing anonymized and runnable tools, pinning system provenance (commits, versions, SHAs), and managing cached LLM outputs. Essential for passing rigorous peer review.

This skill guides the design of real-data validation for academic manuscripts, specifically for forecasting and financial engineering strands. It covers data provenance, rolling out-of-sample tests, benchmark batteries, and statistical significance of improvements. It ensures robustness against look-ahead bias and parameter sensitivity, helping authors meet rigorous external review standards for empirical studies in journals like Chinese Journal of Management Science.

This comprehensive guide assists researchers targeting Environmental Science & Technology (ES&T) submissions. It provides detailed heuristics on journal positioning, scope fit, required mechanistic rigor, data presentation standards, and structural elements. Use this checklist to re-frame and strengthen your manuscript before submission, ensuring alignment with the journal's high standards in environmental chemistry, green engineering, and environmental science.

A comprehensive guide for positioning database research papers for top-tier conferences like ICDE. It teaches authors how to distinguish genuine novelty (new mechanisms) from engineering delta (implementation improvements), conduct deep literature audits, and compare their work against both academic venues and real-world production systems. Essential for improving manuscript eligibility and impact.

This guide outlines comprehensive standards for scientific reproducibility in data engineering. It details best practices for pinning hardware, software, datasets, and variance protocols, ensuring that all performance claims are verifiable and re-runnable by peers, making reproducibility a scored component of academic submission.

A comprehensive guide to the rigorous, multi-stage peer review process for top-tier data engineering conferences like ICDE. It details the two-round structure, area-chair coordination, single-blind dynamics, and the high standards set by 'builder-heavy' reviewers. Use this to strategize paper submission, understand key evaluation dimensions (novelty, soundness, evaluation), and anticipate common review objections.

A comprehensive audit checklist designed for authors submitting data-engineering systems papers to major conferences like ICDE. It covers critical areas including IEEE formatting standards, round selection strategy, Microsoft CMT conflict declarations, and the requirement for supplemental material, ensuring authors mitigate common desk-reject risks.

A comprehensive project management guide for submitting data-intensive systems papers to ICDE. It details the two-round submission cycle, setting milestones from initial evidence locking (mechanisms, workloads) to final IEEE Xplore publication. This workflow helps researchers backward-plan the entire data-engineering lifecycle, budgeting time for revisions and mitigating common submission risks.

A comprehensive methodology guide for designing and auditing empirical studies in software engineering, specifically focused on maintenance, evolution, and change impact. It outlines best practices for ensuring evidence is proportional to the claim, managing data provenance (SHAs, criteria), handling statistical confounds (survivorship, effect sizes), and integrating rigorous LLM evaluation protocols.