Menu
SkillsMP has collected 51 skills from 28sungmin/m4-add-skills. Open a skill to review its source and details.
Copy this prompt into the AI assistant you're using.
Help me install Agent Skills from this repository: https://github.com/28sungmin/m4-add-skills
First review the source, SKILL.md files, and companion files. List the available Skills so I can choose. Then install the complete directories for my chosen Skills into the current project and confirm the required files are present.Showing 40 of 51 collected skills.
Inspect DICOM (X-ray) header labels — verify presence/missingness of 21 clinically important header tags and compute a curation score (0-100). Use for LYDUS data quality assessment of DICOM imaging metadata before large-scale analysis.
Detect and label de-identification–target personal information (names, IDs, addresses, dates/times/periods, other hospitals) in unstructured Korean clinical notes using regular-expression rules, wrapping each match as <LABEL>string</LABEL>.…
Check the label-curation quality of GE MUSE ECG exports — verify presence/missingness of 35 ECG header attributes (3 classes) and compute a curation score (0-100), optionally rendering the 12-lead waveform. Use for LYDUS data quality assessment of ECG-derived…
Detect demographic bias in LYDUS data quality metrics by computing all 16 QUIQ quality metrics (completeness, range/date/format/sequence validity, preciseness, fidelity, class/instance diversity, sentence/vocabulary diversity, logical accuracy,…
Validate format of medical codes (ICD-9/10/11, SNOMED-CT, RxNorm, LOINC, ATC) in a QUIQ-format table. Identifies code type from variable name/description, then validates each value against the corresponding regex. Use for data quality assessment of medical…
Source text: Mixed languages
Convert MIMIC-IV clinical data into QUIQ (Quality Intelligence Unified Query) long-format table. Use when transforming MIMIC-IV tables to QUIQ format for data quality assessment, when applying QUIQ Mapping_info rules to MIMIC-IV variables, or when building a…
Detect IQR outliers (1.5×IQR rule) in numeric variables of a QUIQ-format table and compute Range Validity (% of non-outlier values). SQL version available via DuckDB PERCENTILE_CONT. No API key required. Use for LYDUS data quality assessment of numeric value…
Generate VIA (Variable Information Archive) table from a user-provided documentation file (PDF or text). Requires a data dictionary or schema documentation to produce meaningful variable descriptions. If no document is provided, the skill will ask for one…
Source text: Mixed languages
Calculate cross-sectional consistency for categorical string variables in a QUIQ-format table using Claude CLI to group semantically equivalent values. No API key required. Use for data quality assessment when the same real-world concept may be expressed in…
Source text: Mixed languages
Validate date values in a QUIQ-format table. Checks Event_date column and Mapping_info_1='date' rows using standard format parsing, Korean date formats, and optional LLM fallback. Use for data quality assessment of temporal data.
Source text: Mixed languages
Detect logical outliers in clinical variables using a multi-model ensemble (Quantile Regression + Gradient Boosting + Autoencoder for numeric; OneClassSVM + IsolationForest + Autoencoder for categorical). Uses Claude CLI (no API key required). Use for LYDUS…
Evaluate accuracy of unstructured clinical notes and radiology reports in a QUIQ-format table using Claude CLI. Detects diagnostic, procedural, drug, demographic, and date errors in clinical notes; identifies critical errors in radiology impressions. No API…
Evaluate completeness (fidelity) of unstructured clinical notes and radiology reports in a QUIQ-format table. Uses Claude CLI to check whether required template items are mentioned in each note. No API key required. Use for LYDUS data quality assessment of…
Validate temporal ordering of date variables in a QUIQ-format table. Uses Claude CLI to automatically identify start/end date variable pairs, then checks whether start_date <= end_date for each matched record. No API key required. Use for LYDUS data quality…
Source text: Mixed languages
Measure diversity of verb-containing sentences extracted from clinical notes (Mapping_info_1 contains 'note') in a QUIQ-format table. Uses NLTK POS tagging to identify sentences with verbs, then computes unique/total ratio and coverage scores. No API key…
Source text: Mixed languages
Detect temporal distribution shifts (change points) in clinical data across years using GradientBoosting classifier + SHAP. For each year, trains a model to distinguish year-1 vs year data — AUROC ≥ 0.8 indicates a change point. No API key required. Use for…
Source text: Mixed languages
Measure diversity of noun words in clinical notes using NLTK POS tagging; computes unique/total noun ratio and top-5/10/20% coverage scores. No API key required. Use for LYDUS data quality assessment of vocabulary richness in unstructured text.
Source text: Mixed languages
Calculate class diversity for categorical variables in a QUIQ-format table. Use for data quality assessment of categorical variable distributions, detecting overly homogeneous or heterogeneous value distributions, and generating per-variable diversity…
Calculate classification metrics (Accuracy, Precision, Recall, F1, AUROC) per variable in a QUIQ-format table with Ground_truth labels. Use for data quality assessment when predicted values can be compared against ground truth, generating per-variable…
Source text: Mixed languages
Calculate data completeness (non-null rate) per variable in a QUIQ-format table. Use for data quality assessment to identify variables with missing values and compute overall completeness ratio.
Source text: Mixed languages
Calculate structured fidelity for clinical variables in a QUIQ-format table. Measures how frequently each clinical concept (event, diagnosis, prescription, procedure) appears per patient. Use for data quality assessment of clinical record completeness and…
Source text: Mixed languages
Calculate instance diversity and Gini-Simpson index per (variable, value) combination in a QUIQ-format table. Measures how diversely distributed patients are across occurrences of each clinical value. Use for data quality assessment of recording pattern…
Source text: Mixed languages
Calculate numeric preciseness (decimal-place consistency) for numeric variables in a QUIQ-format table. Detects the actual decimal precision of each variable and measures last-digit distribution diversity using the Gini-Simpson index. No API key required. Use…
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…
Start a structured clinical research session. Use when users describe research goals, want to analyze cohorts, investigate hypotheses, or need a rigorous research plan. Interviews the user, then produces a research protocol.
Use the M4 Python API to query clinical datasets programmatically. Use when writing code to access clinical databases, executing SQL via Python, or performing multi-step data analysis.
Diagnose and repair common M4 environment, dataset, skill installation, backend, and vitrine setup problems. Use when M4 tools, datasets, skills, or visualization are missing or broken.
Calculate Charlson Comorbidity Index (CCI) and Elixhauser Comorbidity Index for hospital admissions. Use for risk adjustment, mortality prediction, case-mix analysis, or comparing comorbidity burden across patient populations.
Identify first ICU stays and first hospital admissions for cohort selection. Use to exclude readmissions, create independent observations, or build adult patient cohorts.
Guide users through creating M4 skills with proper structure, provenance tracking, and tier assignment. Use when users want to create a new M4 skill, document a clinical concept, or contribute a skill to the M4 skills library.
Use the vitrine display API for M4 research visualization, review cards, forms, study tracking, approvals, exports, and recovery of displayed results.
Calculate OASIS (Oxford Acute Severity of Illness Score) for ICU patients. Use for mortality prediction with fewer variables than APACHE/SAPS, or when lab data is limited.
Extract and calculate Glasgow Coma Scale (GCS) for ICU patients. Use for neurological assessment, consciousness monitoring, or trauma severity scoring.
Calculate MELD (Model for End-Stage Liver Disease) score for ICU patients. Use for liver disease severity assessment, transplant prioritization, or hepatology research.
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…
Calculate LODS (Logistic Organ Dysfunction Score) for ICU patients. Use for organ dysfunction assessment across 6 systems with weighted scoring.
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…
Calculate SAPS-II (Simplified Acute Physiology Score II) for ICU patients. Use for mortality prediction, severity assessment, or international ICU benchmarking.
Identify Sepsis-3 patients using the consensus definition (SOFA >= 2 + suspected infection). Use for sepsis cohort studies, outcome research, or quality metrics.
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.