微信扫一扫把 Skill 的源码、资源快照、README、包体和安装信号放进一个可搜索、可筛选的公开目录。
RevMan data calculator for systematic reviews. Computes SD from SE/CI/IQR/range, calculates contrast data (OR/RR/RD/MD/SMD) from arm data, and combines study arms. Use when the user types `revman calc…
Generate funnel plots for assessing publication bias. Renders funnel plots with pseudo-95% CI lines and Egger's test. Use when the user types `revman funnel`.
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Offi…
Create and validate scientific figures in Python using Matplotlib and SciencePlots. Use when the user asks to plot data, generate a paper figure, reproduce a chart, or revise a scientific plot's layou…
Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.
AI-powered Scrum Master and Enterprise Agility Coach based on Jeff Sutherland, Taiichi Ohno, and First Principles thinking. Use when user needs help with Scrum, sprint analysis, backlog refinement, sc…
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNe…
Design and implementation of comprehensive simulation studies
Export systematic review as manuscript, data package, PRISMA checklist, or archive. Assembles all review data into publication-ready outputs. Use when the user types `revman export`.
Generate PRISMA 2020 flow diagrams for systematic reviews. Renders the study selection flowchart from screening numbers. Use when the user types `revman prisma`.
Writing scientific/research code at senior engineer level. Covers project structure, module organization, function design, type hints, naming, error handling, separation of concerns, idiomatic Python/…
Build or revise scientific talks, posters, and Beamer slide decks from papers, codebases, figures, or LaTeX templates. Use when Codex needs to turn technical research into a clear presentation, preser…
Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.
Senior-level code review specifically for scientific/research code in bioinformatics, medical imaging, ML/DL pipelines, and statistical software. Covers correctness (numerical stability, data leakage,…
Create a timestamped research-session progress log that records completed work, evidence, decisions, and next steps. Use when closing or checkpointing substantive project work that needs a durable chr…
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or opti…
Generate forest plots for meta-analysis. Renders publication-quality forest plots from synthesis data. Use when the user types `revman forest`.
Study-centric data management for systematic reviews. Add, edit, view, import, and remove studies with arm-level and outcome-level data. Use when the user types `revman studio`.
Senior-level debugging specifically for scientific code failure modes. Covers CUDA out-of-memory errors, numerical instability (NaN/Inf propagation), reproducibility failures, multiprocessing/GIL issu…
Simplify scientific code, LaTeX, and technical prose while preserving exact behavior, results, and meaning. Use when Codex needs to remove duplication, reduce unnecessary abstraction, clean up AI-gene…
Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitt…
Sensitivity analysis frameworks and assumption-testing methods
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for…
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM inte…