Give your AI agents clinical database access, research automation, and clinician-reviewed domain knowledge for MIMIC-IV, eICU, and more.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
Identify Sepsis-3 patients using the consensus definition (SOFA >= 2 + suspected infection). Use for sepsis cohort studies, outcome research, or quality metrics.
Skill Claude CodeCodex
Identify suspected infection events using antibiotic administration plus culture timing. Use as a component of Sepsis-3 definition or for infection research.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
Calculate SIRS (Systemic Inflammatory Response Syndrome) criteria for ICU patients. Use for historical sepsis definitions, inflammatory response assessment, or research comparing SIRS vs Sepsis-3.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
Classify ventilation status into InvasiveVent, NonInvasiveVent, HFNC, SupplementalOxygen, Tracheostomy, or None from charting data. Use for ventilation duration analysis, respiratory support characterization, or as a component of severity scores (SOFA respiratory, OASIS).
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
Calculate rolling urine output rates (mL/kg/hr) over 6/12/24-hour windows for ICU patients. Use for KDIGO AKI staging (urine output criterion) or SOFA renal component.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
Calculate norepinephrine-equivalent dose for vasopressor comparison. Use for hemodynamic support quantification, shock severity assessment, or vasopressor weaning studies.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
Calculate APACHE IV (Acute Physiology and Chronic Health Evaluation IV) score for ICU mortality prediction. Use for severity assessment, hospital mortality prediction, ICU benchmarking, or case-mix adjustment. eICU has pre-computed scores; MIMIC-IV requires custom implementation with diagnosis mapping challenges.
Skill Claude CodeCodex
Guided workflow for statistical and ML analysis of clinical data. Use when planning or executing research analyses on MIMIC, eICU, or similar EHR data. Ensures methodological rigor through structured consultation, assumption checking, and stepwise execution with audit trails.
Skill Claude CodeCodex
Avoid common methodological mistakes in clinical research with EHR databases. Covers immortal time bias, information leakage, selection bias, and other critical pitfalls.
Skill Claude CodeCodex
Generate equity-focused cohort selection flow diagrams. Tracks demographic, socioeconomic, and outcome variables at each exclusion step and calculates SMD to detect selection bias. Use for cohort construction, CONSORT-style diagrams, or bias detection in clinical ML/research.
Skill Claude CodeCodex
Identify first ICU stays and first hospital admissions for cohort selection. Use to exclude readmissions, create independent observations, or build adult patient cohorts.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: