UKBAnalytica

Causal mediation analysis for UK Biobank Research Analysis Platform (RAP) cohorts using UKBAnalytica. Wraps regmedint (Valeri & VanderWeele 4-way decomposition: CDE, PNDE, TNIE, TNDE, PNIE, TE, PM) via run_mediation; supports multi-mediator screening (run_multi_mediator), visualization (plot_mediation, plot_mediation_forest) for linear, logistic, and Cox outcome models with continuous or binary mediators. Use this skill when the user asks for mediation analysis, indirect effects, natural direct / indirect effects, controlled direct effects, proportion mediated, or mediator screening across multiple candidates. Triggers: mediation analysis, indirect effect, natural direct effect, TNIE, PNDE, proportion mediated, 中介分析, /ukbsci-mediation. Hard rule: local agents must not read or inspect real UKB RAP participant-level data; generate scripts for RAP execution and interpret aggregate outputs only.

Build a UK Biobank disease cohort from a phenotype table extracted on the Research Analysis Platform (RAP), using the UKBAnalytica R package. Covers disease-definition construction and catalog lookup (get_predefined_diseases, get_disease_catalog, get_pomegranate_diseases, create_disease_definition, combine_disease_definitions), source parsers (parse_icd10_diagnoses, parse_icd9_diagnoses, parse_opcs4_procedures, parse_cancer_registry, parse_death_records, parse_self_reported_illnesses), multi-source case extraction (extract_cases_by_source, extract_disease_diagnosis, extract_disease_history, extract_disease_history_sensitivity, compare_data_sources), reusable follow-up time skeletons (ukb_time_skeleton), and the Cox-ready dataset builder build_survival_dataset() with prevalent vs incident separation and follow-up time computation, plus select_incident_by_years() for time-window stratification. Use this skill when the user asks to define a UKB disease phenotype, inspect curated/Pomegranate diagnostic codes, sep

Machine learning workflows (binary / multiclass classification and right-censored survival) for UK Biobank Research Analysis Platform (RAP) cohorts using UKBAnalytica. End-to-end pipelines (ukb_ml_workflow, ukb_ml_flow, ukb_ml_survival_workflow) cover frozen train / validation / test split, feature selection (Boruta, filter, glmnet), hyperparameter tuning (grid / random / Bayesian), final refit, test-set evaluation, model comparison, and model-agnostic interpretation via SHAP. Supports RF / XGBoost / glmnet / SVM / NNet / RPart / Naive Bayes / Logistic for classification, and RSF / GBM / coxnet for survival. Output evaluation: ROC, PR, calibration, DCA, KS, gain & lift, confusion matrix, threshold optimization, SHAP summary / dependence / force, plus plot_ml_* and plot_shap_* visualizations. Use this skill when the user asks for a UKB-based predictive model, ML pipeline, SHAP interpretation, C-index for a survival model, or comparison between several ML algorithms. Triggers: UKB ML, machine learning, XGBoost,

Publication-grade figure production for UK Biobank Research Analysis Platform (RAP) analyses built with UKBAnalytica. Wraps the package's built-in plotters — plot_forest (subgroup / regression forest), plot_calibration (clinical-model calibration), plot_regression_volcano (multi-exposure / multi-protein volcano), plot_heatmap, plot_stacked_bar, plot_violin, and plot_scatter for lightweight exploratory/manuscript panels, plus the family of survival, ML, SHAP, mediation, propensity, imputation, correlation, and enrichment plots from sibling skills — and adds a shared neutral theme (ukbsci_clinical / ukbsci_diverging / ukbsci_sequential palettes), a dual-format save helper, and a figure-contract checklist. Use this skill when the user asks for any manuscript figure derived from UKBAnalytica outputs: forest plots, volcano plots, KM curves, calibration plots, Love plots, SHAP summaries, multi-panel composites, or PDF / SVG high-resolution export. Triggers: UKB plotting, forest plot, volcano, calibration, manuscrip

Propensity-score analyses for UK Biobank Research Analysis Platform (RAP) cohorts built with UKBAnalytica. Covers PS estimation via logistic regression or gradient-boosted models (estimate_propensity_score), 1:N nearest-neighbor or optimal matching (match_propensity), inverse-probability of treatment weighting (calculate_weights, ATE / ATT / ATC, stabilized, truncated), covariate balance diagnostics (assess_balance, plot_balance, plot_ps_distribution), and weighted regression with robust standard errors (run_weighted_analysis). Use this skill when the user asks for propensity score matching, PSM, IPTW, ATE / ATT, covariate balance, Love plot, PS distribution check, or a weighted Cox / logistic / linear analysis on a UKB cohort. Triggers: propensity score, PSM, IPTW, ATE, ATT, Love plot, covariate balance, 倾向评分, 倾向得分匹配, /ukbsci-propensity. Hard rule: local agents must not read or inspect real UKB RAP participant-level data; generate scripts for RAP execution and interpret aggregate outputs only.

Discover UK Biobank fields and extract phenotype data from inside an authenticated UK Biobank Research Analysis Platform (RAP) session using the UKBAnalytica R package (rap_find_dataset, rap_list_fields, rap_plan_extract, rap_extract_pheno, rap_submit_extract, ukb_metadata_setup, ukb_search_fields, ukb_field_info, ukb_extract_fields, ukb_decode, ukb_check_rap_env, ukb_create_extraction_manifest, ukb_write_extraction_manifest). Use this skill when the user asks to search UKB fields, check the RAP environment, plan/run a phenotype extraction on RAP, create an extraction manifest, choose between dx extract_dataset (sync) and table-exporter (async), decode RAP column names or coded values, or build the upstream phenotype table that feeds ukbsci-cohort. Triggers: UK Biobank RAP extract, dx extract_dataset, table-exporter, UKB field search, RAP 提取, 字段搜索, 表型提取, /ukbsci-rap-extract. Hard rule: local agents must not read or inspect real UKB RAP participant-level data; generate scripts for RAP execution and interpret a

Subgroup interaction tests and sensitivity-analysis filters for UK Biobank Research Analysis Platform (RAP) cohorts built with UKBAnalytica. Covers run_subgroup_analysis and run_multi_subgroup (stratum-specific Cox / logistic / linear / GLM / negative-binomial effects + interaction p-value), sensitivity_exclude_early_events (drop events within N years of baseline to guard against reverse causation), and sensitivity_exclude_missing_covariates (complete-case analysis with optional flow tracking), ukb_participant_flow / plot_participant_flow for cohort attrition, and ukb_sensitivity_suite for common Cox sensitivity runs. Use this skill when the user asks for subgroup analysis, interaction tests, effect modification, complete-case sensitivity, or early-event exclusion sensitivity. Subgroup analysis now supports all model families: cox, logistic, linear, glm (any GLM family including Poisson, quasi-Poisson, Gamma), and negbin (negative-binomial). Triggers: subgroup analysis, interaction p-value, effect modificatio

End-to-end orchestrator for a UK Biobank Research Analysis Platform (RAP) study using the UKBAnalytica R package. Plans, sequences, and supervises the full pipeline — from RAP phenotype extraction, through disease-cohort construction with reusable time skeletons, variable preprocessing, baseline tables, multiple imputation, regression / survival / propensity / mediation / subgroup-sensitivity analyses, machine learning, omics workflows, and final publication-ready plots — by routing each phase to the right specialist skill (ukbsci-rap-extract, ukbsci-cohort, ukbsci-preprocess, ukbsci-baseline, ukbsci-imputation, ukbsci-regression, ukbsci-survival, ukbsci-propensity, ukbsci-mediation, ukbsci-subgroup-sensitivity, ukbsci-proteomics, ukbsci-ml, ukbsci-plot). Use this skill when the user asks for an end-to-end UKB study, an analysis plan covering multiple phases, or "RAP-to-publication" guidance. Triggers: end-to-end UKB analysis, UKB pipeline, RAP to publication, full study plan, 端到端 UKB 分析, RAP 到论文, 完整流程, 项目计划,

Variable cleaning and feature construction for UK Biobank Research Analysis Platform (RAP) cohorts using UKBAnalytica. Negative-code sanitation (ukb_clean_missing), unified preprocessing with predefined variable sets (preprocess_baseline, prepare_analysis_dataset), composite variable builders (calculate_blood_pressure, calculate_air_pollution, calculate_diet_score), and curated variable-set lookups (get_variable_set, get_variable_sets, get_variable_info). Use this skill when the user asks to clean UKB negative-codes (-1, -3, -7, …), derive blood pressure / air pollution / diet score, compose an analysis-ready table, or look up predefined UKB variable sets. Triggers: UKB preprocessing, variable cleaning, derive BP, air pollution exposure, diet score, negative code, UKB 变量预处理, 缺失码处理, 复合变量, /ukbsci-preprocess. Hard rule: local agents must not read or inspect real UKB RAP participant-level data; generate scripts for RAP execution and interpret aggregate outputs only.

UK Biobank Olink / UKB-PPP proteomics post-hit analyses on the Research Analysis Platform (RAP) using UKBAnalytica. Covers protein-to-gene-symbol mapping (protein_to_gene_symbol), STRING PPI retrieval (get_protein_ppi), network metrics + node ranking (compute_protein_ppi_metrics, rank_protein_ppi_nodes), subsetting by confidence (subset_protein_ppi), community detection (run_protein_ppi_louvain, run_protein_ppi_fastgreedy, run_protein_ppi_mcl, run_protein_ppi_mcode + get_protein_mcode_res), cluster scoring (score_protein_ppi_clusters), robustness to target knockout (run_protein_ppi_robustness), GO and KEGG over-representation (run_protein_ora, run_protein_kegg_ora), and enrichment / network visualization (plot_go_ora_bar, plot_enrichment_lollipop). Use this skill when the user provides a list of significant proteins from UKB Olink hits and asks for PPI network analysis, gene-set enrichment, clustering, or network-robustness assessment. Triggers: UKB proteomics, Olink hits, UKB-PPP, STRING PPI, GO ORA, KEGG OR

Design and evaluate UK Biobank research topics from user-provided keywords, exposures, outcomes, omics layers, or clinical domains. Use this skill to perform literature-informed topic scouting, summarize existing work and its limitations, identify research gaps, propose gap-resolving epidemiological or omics study designs, verify PMID/DOI references, identify required software and UKBAnalytica functions, and return a structured academic Markdown research brief. Triggers: UK Biobank research idea, UKB topic selection, feasibility analysis, PubMed scoping review, literature gap analysis, study design, research proposal, UKB选题, 研究设计, 文献调研, gap分析, 可行性分析, /UKB-research.

Fit linear, logistic, Cox, GLM, negative-binomial, GAM, Fine-Gray competing-risk, lagged Cox, trend, PH-diagnostic, and restricted cubic spline models on UK Biobank Research Analysis Platform (RAP) cohorts built with UKBAnalytica. Wraps runmulti_lm, runmulti_logit, runmulti_cox, runmulti_glm, runmulti_negbin, runmulti_gam, run_regression, runmulti_cox_lag, runmulti_cox_zph, runmulti_competing, runmulti_trend, ukb_cox_diagnostics, run_rcs, and plot_rcs. Use this skill when the user asks to fit any regression model on the cohort, run batch regressions across multiple exposures, fit count/rate outcomes with Poisson/quasi-Poisson/Gamma GLM, fit negative-binomial for overdispersed counts, screen for non-linearity with GAM, check proportional-hazards assumptions, run a lagged sensitivity analysis, perform competing-risks Fine-Gray modeling, test a dose-response trend, or draw an exposure-response RCS curve. Triggers: UKB regression, Cox model, logistic regression, GLM, Poisson, negative binomial, GAM, batch regress

Metabolomics over-representation analysis (ORA) for UK Biobank Nightingale NMR metabolite data using UKBAnalytica. Covers metabolite classification (classify_metabolites), UK Biobank–to–MetaboAnalyst name mapping (metabolite_to_metaboanalyst_name), panel loading (load_ukb_metabolite_panel), ORA with a custom pathway library or MetaboAnalystR backend (run_metabolite_ora), and ggplot2 visualization of ORA results (plot_metabolite_ora_dotplot, plot_metabolite_ora_barplot). Use this skill when the user wants to interpret a list of significant metabolites from a regression or GWAS screen, identify enriched metabolic pathways, or visualize ORA results. Triggers: metabolomics, metabolite ORA, pathway enrichment, Nightingale, MetaboAnalyst, 代谢组, 代谢物富集, /ukbsci-metabolomics. Hard rule: local agents must not read or inspect real UKB RAP participant-level data; generate scripts for RAP execution and interpret aggregate outputs only.

Create, update, review, and validate Codex/OpenAI agent skills in this repository. Use when the user asks to add a new skill, revise an existing SKILL.md, design skill references/scripts/assets, audit trigger descriptions, add smoke tests, package skills under inst/skills, or align skills with UKBAnalytica/RAP privacy and reproducibility standards.

Create a stratified baseline characteristics table (Table 1) for a UK Biobank Research Analysis Platform (RAP) cohort built with UKBAnalytica. Wraps create_baseline_table() over the tableone package, producing a printable / aggregate CSV summary with appropriate chi-square / Fisher / t-test / Wilcoxon comparisons across a case-control or exposure strata column. Use this skill when the user asks for a Table 1, baseline characteristics, demographic summary, case-vs-control comparison, or stratified descriptive statistics. Triggers: Table 1, baseline table, baseline characteristics, demographics summary, UKB Table 1, 基线表, 基线特征, /ukbsci-baseline. Hard rule: local agents must not read or inspect real UKB RAP participant-level data; generate scripts for RAP execution and interpret aggregate outputs only.

Multiple imputation by chained equations and Rubin's-rules pooling for UK Biobank Research Analysis Platform (RAP) cohorts using UKBAnalytica. Wraps mice (run_imputation, create_imputation_list) and mitools::MIcombine (pool_mi_models, pool_custom_estimates) to produce m imputed datasets, fit regression models on each (fit_mi_models), and pool estimates with FMI diagnostics (S3 mi_pooled_result + plot_mi_pooled, plot_mi_diagnostics). Supports merging additional datasets (e.g. proteomics) into each imputed copy via the additional_data argument. Use this skill when the user asks for multiple imputation, MI pooling, Rubin's rules, FMI, or wants to merge per-imputation analyses across covariate / proteomics datasets. Triggers: multiple imputation, MI, mice, Rubin's rules, FMI, pool imputations, imputed dataset, 多重插补, 插补合并, /ukbsci-imputation. Hard rule: local agents must not read or inspect real UKB RAP participant-level data; generate scripts for RAP execution and interpret aggregate outputs only.

Survival visualization and post-Cox summary helpers for UK Biobank Research Analysis Platform (RAP) cohorts built with UKBAnalytica. Covers Kaplan-Meier curves with risk tables and log-rank p-values (plot_km_curve), and pairs with ukbsci-regression for time-to-event analyses. Use this skill when the user asks to draw a KM curve, show cumulative incidence, build a risk-table-augmented survival figure, or visualize stratified survival across exposure / treatment groups. Triggers: UKB KM curve, Kaplan-Meier, survival curve, log-rank, risk table, cumulative incidence, UKB 生存曲线, KM 曲线, /ukbsci-survival. Hard rule: local agents must not read or inspect real UKB RAP participant-level data; generate scripts for RAP execution and interpret aggregate outputs only.