Skill UI

This skill processes unstructured, rambling, stream-of-consciousness input (like dictation or brainstorming) into a highly structured 'echo' audit. It captures the user's core mission, locked decisions, open questions, and all model inferences, ensuring the user verifies the model's belief, not just the stated doubts. Ideal for refining fuzzy ideas before committing to work.

This guide helps researchers determine the most appropriate conference (UAI, AISTATS, NeurIPS, ICML, etc.) for their work, particularly when the core contribution revolves around uncertainty representation, probabilistic reasoning, or causal inference. It provides detailed filters and comparison points to refine the paper's scope and target audience.

This guide provides a rigorous methodology for achieving scientific reproducibility in technical and user experience papers (e.g., UIST). It details three essential 'ledgers': the Build Ledger (pinning software, hardware, and environment dependencies), the Measurement Ledger (defining precise protocols for metrics like latency and accuracy), and the Study Ledger (documenting human evaluation tasks). Following these protocols ensures that external researchers can accurately rebuild the artifact and validate reported results.

This skill enables rigorous tracking of physical units and the systematic propagation of measurement uncertainty in scientific calculations. It supports unit conversions, building comprehensive GUM uncertainty budgets, and performing dimensional and physical plausibility checks. Use it whenever a calculation requires adherence to strict metrological standards and accurate error reporting.

A specialized guide for authors aiming to submit to the Conference on Uncertainty in Artificial Intelligence (UAI). It provides expert advice on framing the core contribution—such as probabilistic reasoning, causal inference, and uncertainty modeling—and calibrating the manuscript for highly technical, statistical ML reviewers. Use this skill to refine your submission strategy, identify evidence gaps, and properly position your work relative to other top-tier AI venues like AISTATS and IJCAI.

A comprehensive guide for positioning computer science manuscripts for top-tier security conferences like USENIX Security. It covers core topics (systems, network, privacy, software security), required evidence (rigorous artifact, measurement, vulnerability analysis), and strategic advice on framing the work to meet adversarial reviewer expectations. Ideal for authors preparing high-stakes academic submissions.

This skill provides a comprehensive guide for authors targeting the USENIX Symposium on Operating Systems Design and Implementation (OSDI). It helps in positioning complex systems research, covering core scope areas like operating systems, distributed systems, and cloud infrastructure. It details how to frame the contribution, build evidence (artifacts, baselines), and distinguish the work from similar top-tier venues like SOSP and NSDI.

This detailed guide helps researchers determine the optimal top-tier venue (e.g., USENIX Security, IEEE S&P, ACM CCS) for their security research paper. It emphasizes that venue selection must be based on the committee's core expertise and the existence of reusable artifacts, measurements, or systems evidence, ensuring the work has the necessary technical depth to succeed.

A rigorous guide for drafting high-stakes, technical security papers for the USENIX Security Symposium. It mandates a threat-model-first structure, requiring authors to quantify all security claims with measurable data to avoid hyperbole. The guide also details integrating responsible disclosure narratives and adhering to strict academic formatting rules.

This guide helps researchers determine if their project qualifies as a visualization contribution (beyond general HCI or ML). It provides structured criteria for choosing the best conference venue (e.g., IEEE VIS, EuroVis, CHI) and mapping the work to one of the six core visualization areas based on contribution type and evidence maturity.

This comprehensive guide outlines the rigorous standards required for achieving experimental reproducibility in systems research papers (e.g., VLDB). It instructs authors on disclosing critical context, including hardware specifications, software configurations, data provenance, workload patterns, and handling measurement variance. Adhering to these guidelines ensures that all performance claims are fully traceable from raw data to published figures, meeting the highest standards of academic review.

A comprehensive guide for creating the two required artifacts for a WACV paper: an anonymous package for double-blind review, and a public release post-acceptance. It emphasizes reproducing deployed system claims (latency, power, robustness) and maintaining consistency across revision rounds.