Skill UI

A comprehensive guide for researchers deciding the optimal conference venue for their NLP project. It analyzes whether a project is best suited for EACL, ACL, EMNLP, NAACL, or other specialized venues (like LREC-COLING or COLM). The guide considers scope, contribution type (e.g., analysis vs. new system), temporal constraints, and the trade-offs between long and short paper formats.

A comprehensive guide for revising academic papers in recommendation systems (RecSys). It covers best practices for structuring the first page, ensuring rigorous evaluation protocols (e.g., temporal splits, equal-budget baselines), and avoiding methodological overclaims, helping authors meet the standards of top-tier AI conferences.

This skill constructs a comprehensive, chronologically sorted patient timeline from raw clinical entities extracted from medical notes. It specializes in temporal normalization, resolving both absolute and relative dates (e.g., 'two days after admission') against a defined anchor date. The resulting sorted sequence of diagnoses, medications, and procedures is ready for immediate visualization or seamless export to FHIR resources.

This skill enhances raw clinical entity recognition by assigning three critical axes: Negation, Temporality, and Uncertainty (ConText). It determines the clinical status of a mention (e.g., affirmed, negated, historical, or uncertain), ensuring that basic NER results are transformed into clinically faithful assertions before grounding to standards like FHIR. Essential for accurate problem list generation and differential diagnosis support.

This skill applies consistent date shifting to clinical text, ensuring that absolute dates are obscured while critically preserving the temporal intervals between medical events. It is essential for longitudinal research or survival analysis where time-to-event data must be preserved under HIPAA Safe Harbor rules. It maintains the integrity of time differences (e.g., length of stay, visit gaps) by applying a stable, per-patient offset.

This framework provides a rigorous pre-execution review mechanism for proposed actions by AI agents or systems. It functions as a critical safety boundary, auditing the entire decision path—from initial request to proposed tool execution—without authorizing or executing anything. It verifies action conformity, evidence integrity, temporal validity, and reviewer independence to ensure system compliance and security.