Create publication-quality scientific figures with ggplot2 including scatter plots, boxplots, heatmaps, and multi-panel layouts. Use when creating static figures for papers, presentations, or reports in R.
Combine multiple plots into publication-ready multi-panel figures using patchwork, cowplot, or matplotlib GridSpec with shared legends and panel labels. Use when combining multiple plots into publication figures.
Reusable plotting functions for common omics visualizations. Custom ggplot2/matplotlib implementations of volcano, MA, PCA, enrichment dotplots, boxplots, and survival curves. Use when creating volcano, MA, or enrichment plots.
Reads and prepares CDISC SDTM clinical trial data for analysis. Handles domain tables (DM, AE, EX, VS, LB), USUBJID-based joins, event-to-subject aggregation, and SUPPQUAL pivoting. Use when working with clinical trial datasets in CDISC/SDTM format or .xpt files.
End-to-end clinical trial analysis workflow from CDISC data loading through statistical testing to regulatory-compliant reporting. Covers data preparation, logistic regression, categorical tests, subgroup analysis, and Table 1 generation. Use when performing a complete analysis of clinical trial data.
Performs logistic regression for clinical trial outcomes including binary, ordinal, and multinomial models. Extracts odds ratios with confidence intervals, handles covariate adjustment, and provides Firth penalized regression for rare events or separation. Use when modeling binary or ordinal endpoints from clinical data.
Implements nested cross-validation and stratified splits for unbiased model evaluation on biomedical datasets. Prevents data leakage and overfitting in biomarker discovery. Use when validating classifiers or optimizing hyperparameters on omics data.
Builds classification models for omics data using RandomForest, XGBoost, and logistic regression with sklearn-compatible APIs. Includes proper preprocessing and evaluation metrics for biomarker classifiers. Use when building diagnostic or prognostic classifiers from expression or variant data.
Analyzes time-to-event data using Kaplan-Meier curves, log-rank tests, and Cox proportional hazards regression with lifelines. Builds survival models from clinical and omics features. Use when predicting patient survival or modeling time-to-event outcomes.
Refine prompts for Claude models (Opus, Sonnet, Haiku) using Anthropic's best practices. Use when preparing complex tasks for Claude.
Refine prompts for GPT models (GPT-5, GPT-5.1, Codex) using OpenAI's best practices. Use when preparing complex tasks for GPT.
Compare two containers using native portainer tool data collection and render SVG/CSV outputs.
How to discover, load, and effectively use skills to solve SkillBench tasks.
Prompt 优化助手。适用于用户想优化提示词、改进 AI 指令、为特定任务设计更好的 prompt，或需要选择合适提示框架时使用。会根据任务场景匹配合适框架，必要时先追问关键信息，再输出更清晰、更可执行的提示词版本。
Problem-solving strategies for modular arithmetic in graph number theory
Problem-solving strategies for graph algorithms in graph number theory
SaaS analytics event taxonomy, metric formulas (MRR, churn, LTV), provider-agnostic tracking, funnel analysis, cohort setup, and privacy-respecting instrumentation.
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
Dockerfile best practices, multi-stage builds, docker-compose, container networking, volume management, and image optimization.
Structured data extraction - tables, pricing, products, API endpoints with schema
Fast codebase search via WarpGrep (20x faster than grep)
Data structure selection, pub/sub patterns, Lua scripting, pipelining, and cluster topology strategies.
TDD workflow for migrations - orchestrate agents, zero main context growth
