Skills技能

Applies ACMG/AMP 2015 framework with ClinGen SVI specifications, Tavtigian 2018/2020 Bayesian point system, Abou Tayoun 2018 PVS1 decision tree, Pejaver 2022 and Bergquist 2025 calibrated PP3/BP4 thresholds for REVEL/BayesDel/AlphaMissense, Brnich 2020 PS3/BS3 OddsPath, Walker 2023 SpliceAI splicing framework, and AMP/ASCO/CAP 2017 tumor tiers. Use when classifying germline variants P / LP / VUS / LB / B, applying VCEP-specific CSpec rules, computing Whiffin BS1, or assigning cancer Tier I-IV per Li 2017.应用 ACMG/AMP 2015 框架及 ClinGen SVI 细则、Tavtigian 2018/2020 贝叶斯计分体系、Abou Tayoun 2018 PVS1 决策树、Pejaver 2022 与 Bergquist 2025 针对 REVEL/BayesDel/AlphaMissense 校准的 PP3/BP4 阈值、Brnich 2020 PS3/BS3 OddsPath、Walker 2023 SpliceAI 剪接框架，以及 AMP/ASCO/CAP 2017 肿瘤变异分级。适用于将胚系变异分类为 P / LP / VUS / LB / B、应用特定 VCEP 的 CSpec 规则、计算 Whiffin BS1，或按 Li 2017 划分肿瘤 Tier I-IV。

Provides Biopython workflows for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Supports batch processing, custom molecular-biology pipelines, BLAST automation, structure analysis, and motif analysis.提供 Biopython 工作流，用于序列处理、文件解析（FASTA/GenBank/PDB）、系统发育分析，以及以编程方式访问 NCBI/PubMed（Bio.Entrez）。支持批量处理、自定义分子生物学流程、BLAST 自动化、结构分析和 motif 分析。

Prepares bulk RNA-seq FASTQ, Salmon, STAR or featureCounts output for gene-level differential expression. Covers nf-core/rnaseq and standalone quantification, biological replication, strandedness, reference provenance, validated count assembly and a PyDESeq2 handoff. Use for FASTQ-to-counts analysis, nf-core/rnaseq configuration, STAR/Salmon quantification, or building a counts matrix for DESeq2. For single-cell data use scanpy; for statistical fitting alone use pydeseq2.将 bulk RNA-seq 的 FASTQ、Salmon、STAR 或 featureCounts 输出整理为可用于基因水平差异表达分析的数据。涵盖 nf-core/rnaseq 与独立定量、生物学重复、链特异性、参考基因组来源追溯、经校验的计数矩阵构建，以及向 PyDESeq2 的衔接。适用于从 FASTQ 到计数的分析、nf-core/rnaseq 配置、STAR/Salmon 定量，或为 DESeq2 构建计数矩阵。单细胞数据请使用 scanpy；仅做统计拟合请使用 pydeseq2。

Comprehensive citation management for academic research. Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.面向学术研究的全面引文管理。在 OpenAlex、PubMed 和 Google Scholar 中检索论文，提取准确的元数据，校验引文，并生成格式规范的 BibTeX 条目。适用于需要查找论文、核实引文信息、将 DOI 转换为 BibTeX，或确保科研写作中参考文献准确性的场景。

Prepares and validates research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. Supports aggregate or synthetic research documentation and traceability, excluding patient care and live clinical operation.准备并校验仅限研究用途的临床决策支持相关材料，包括评估、证据概况、队列、生存分析、生物标志物/模型、隐私及治理等文档。支持汇总数据或合成数据的研究文档编写与可追溯性，不适用于患者诊疗及实际临床运行。

Creates safety-bounded draft structures and runs local deterministic checks for clinical case, diagnostic, trial, safety, and aggregate research reports. Use only with synthetic, de-identified, or aggregate inputs and verified source-fact manifests; every output requires qualified review.为临床病例、诊断、试验、安全性及汇总研究报告生成有安全边界的草稿结构，并在本地运行确定性检查。仅可用于合成、已去标识化或汇总的输入数据及经核实的源事实清单；所有输出均须经具备资质的人员审核。

Queries ClinVar for variant pathogenicity classifications, ClinGen VCEP curations, and somatic-vs-germline interpretations via REST API, weekly VCF, or bulk XML. Use when determining clinical significance, triangulating conflicting interpretations, or aggregating evidence against the ACMG/AMP framework with ClinGen SVI specifications.通过 REST API、每周发布的 VCF 或批量 XML 查询 ClinVar 中的变异致病性分类、ClinGen VCEP 审编结果以及体细胞与胚系解读。适用于判定临床意义、对相互冲突的解读进行交叉核对，或依据 ACMG/AMP 框架及 ClinGen SVI 细则汇总证据。

Queries documented public database APIs with explicit endpoints, filters, pagination, and provenance. Used when a scientific, regulatory, financial, or other database-backed fact must be retrieved reproducibly from a named source rather than inferred from general knowledge.通过明确的端点、过滤条件、分页及来源追溯，查询有文档说明的公共数据库 API。适用于需要从指定来源可复现地获取科学、监管、金融或其他基于数据库的事实，而非凭一般知识推断的场景。

Extract clean Markdown from HTML pages with Defuddle CLI.使用 Defuddle CLI 从 HTML 页面中提取干净的 Markdown。

Retrieves and analyzes Cancer Dependency Map (DepMap) release data, including CRISPR Chronos gene effects, cancer model annotations, omics biomarkers, and PRISM drug sensitivity. Supports cancer-selective dependency, co-essentiality, and candidate synthetic-lethality analyses with release-aware identifiers and statistical checks.获取并分析癌症依赖性图谱（DepMap）发布数据，包括 CRISPR Chronos 基因效应、癌症模型注释、组学生物标志物及 PRISM 药物敏感性。支持癌症选择性依赖、共必需性以及候选合成致死分析，并使用与发布版本对应的标识符和统计检验。

Converts DOCX/PDF/PPTX and saved HTML/HTM to high-quality Markdown with automatic post-processing. Fixes pandoc grid tables, simple tables, image paths, CJK bold spacing, attribute noise, and code blocks; for PDFs also strips OCR garbage blocks, repeated headers/footers/watermarks, and absolute image paths from pymupdf4llm output. Benchmarked best-in-class (7.6/10) against Docling, MarkItDown, Pandoc raw, and Mammoth. Trigger on "convert document", "docx to markdown", "parse word", "doc to markdown", "解析word", "转换文档", "HTML to Markdown".将 DOCX/PDF/PPTX 及保存的 HTML/HTM 转换为高质量 Markdown，并自动进行后处理。修复 pandoc 网格表格、简单表格、图片路径、CJK 加粗间距、属性噪声和代码块；对于 PDF，还会清除 pymupdf4llm 输出中的 OCR 乱码块、重复的页眉/页脚/水印以及绝对图片路径。基准测试中与 Docling、MarkItDown、Pandoc 原始输出和 Mammoth 相比表现最佳（7.6/10）。当出现 "convert document"、"docx to markdown"、"parse word"、"doc to markdown"、"解析word"、"转换文档"、"HTML to Markdown" 等请求时使用。

Search NCBI databases using Biopython Bio.Entrez (ESearch, EInfo, EGQuery, ESpell). Use when finding records by keyword, building reproducible field-qualified queries, navigating the Entrez Query Translator, exploiting the history server for large result sets, handling retmax caps, or interpreting weekly index lag. Covers PubMed, Nucleotide, Protein, Gene, SRA, GEO, Assembly, Taxonomy, ClinVar, dbSNP.使用 Biopython 的 Bio.Entrez（ESearch、EInfo、EGQuery、ESpell）检索 NCBI 数据库。适用于按关键词查找记录、构建可复现的字段限定查询、使用 Entrez Query Translator、利用 history server 处理大型结果集、应对 retmax 上限，或理解每周索引延迟。涵盖 PubMed、Nucleotide、Protein、Gene、SRA、GEO、Assembly、Taxonomy、ClinVar、dbSNP。

Searches scientific and technical web content with Exa and extracts page or PDF text from URLs in batches. Supports scholarly discovery with the publication category and academic domain filters. Applies to requests to search the web, look up current research, fetch a page, or extract an article using Exa.使用 Exa 检索科学与技术类网络内容，并从 URL 批量提取网页或 PDF 文本。支持通过出版物类别和学术域名过滤进行学术文献发现。适用于使用 Exa 进行网络检索、查找最新研究、抓取网页或提取文章的请求。

Designs experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. Use whenever someone is planning a study, asks how to assign subjects/samples to groups, mentions randomization, blocking, stratification, controls, factorial or fractional-factorial designs, design of experiments (DOE), screening many factors, response-surface optimization, crossover or repeated-measures or split-plot designs, cluster/group randomization, Latin squares, plate layouts, batch/run-order effects, replication vs. pseudoreplication, or sequential/adaptive/group-sequential designs. Trigger even for informal phrasings like "how should I set up this experiment", "how do I avoid confounding", "what's the best way to test these 6 factors", or "assign these mice to conditions". For computing the sample size or power once the design is chosen, use statistical-power; for analyzing data already collected, use statistical-analysis.在数据收集之前设计实验和研究——选择设计方案、随机化、区组化及安排处理组合，使结果可被解释。适用于有人在规划研究、询问如何将受试者/样本分配到各组，或提及随机化、区组、分层、对照、析因或部分析因设计、实验设计（DOE）、多因素筛选、响应面优化、交叉设计、重复测量或裂区设计、整群/分组随机化、拉丁方、板布局、批次/运行顺序效应、真重复与伪重复，或序贯/适应性/成组序贯设计等情形。即使是非正式的表述也应触发，如 "how should I set up this experiment"、"how do I avoid confounding"、"what's the best way to test these 6 factors" 或 "assign these mice to conditions"。设计确定后计算样本量或检验效能请使用 statistical-power；分析已收集的数据请使用 statistical-analysis。

Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed.对明确支持的科学数据文件进行有边界的本地探索性分析。支持已脱敏的 CSV/TSV/JSON 概况分析；可选的 NumPy、HDF5、FASTA/FASTQ 及基础图像元数据检查；缺失值/数据泄漏审查；离群值与变换敏感性分析；以及严谨的 EDA 报告框架。其他领域格式仅供参考，未知格式一律拒绝处理（fail closed）。

Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.在本地分支的改动中查找缺陷、安全漏洞和代码质量问题。适用于被要求评审改动、查找缺陷、进行安全评审或审计当前分支代码时。

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work当实现已完成、所有测试均已通过，需要决定如何集成这些工作时使用。

Queries 20+ bioinformatics resources through CLI/Python. Supports quick lookups of gene info, BLAST/BLAT, viral sequence downloads, PDB/mmCIF structures, G2P residue annotations, enrichment analysis, OpenTargets, COSMIC, CELLxGENE, and 8cube mouse specificity/expression data. Best for interactive exploration and simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.通过 CLI/Python 查询 20 多个生物信息学资源。支持快速查询基因信息、BLAST/BLAT、病毒序列下载、PDB/mmCIF 结构、G2P 残基注释、富集分析、OpenTargets、COSMIC、CELLxGENE 以及 8cube 小鼠特异性/表达数据。最适合交互式探索和简单查询。批量处理或高级 BLAST 请使用 biopython；多数据库 Python 工作流请使用 bioservices。

Extracts and preprocesses whole-slide histology image tiles with Histolab. Use for WSI inspection, tissue masks, random/grid/score-based tile extraction, H&E stain normalization, and tile dataset preparation. For multiplexed imaging or deep learning inference pipelines, use pathml.使用 Histolab 提取并预处理全切片组织病理图像（WSI）的图块。适用于 WSI 检查、组织掩膜、随机/网格/基于评分的图块提取、H&E 染色标准化以及图块数据集准备。如需多重成像或深度学习推理流程，请使用 pathml。

Formulates evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Used when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.在证据边界内构建科学问题、候选假设、竞争性解释、因果或关联性论断、可区分的预测、测量方案，以及可用于预注册的分析计划。适用于将观察结果或初步发现转化为透明、可检验的研究计划，且不把假设当作事实。

Queries and downloads public cancer imaging data from NCI Imaging Data Commons. Supports IDC collection discovery, DICOM access, radiology (CT, MR, PET) and pathology AI datasets, metadata SQL, visualization, licensing, and citations. Uses public metadata and download routes without authentication; optional BigQuery and Google Healthcare routes require Google credentials.从 NCI Imaging Data Commons 查询并下载公开的癌症影像数据。支持 IDC 数据集合发现、DICOM 访问、放射学（CT、MR、PET）和病理学 AI 数据集、元数据 SQL 查询、可视化、许可信息及引用。使用公开的元数据和下载途径，无需身份验证；可选的 BigQuery 和 Google Healthcare 途径需要 Google 凭据。

Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities are spatial text boxes, Markdown, page raster output, and local parsing with optional custom HTTP OCR.本地文档与 PDF 解析，返回带边界框的空间文本。适用于从 PDF、DOCX、Office 文件和图像中提取文本；对扫描件进行 OCR；为 RAG 生成保留版面布局的 JSON；批量导入论文文件夹；或将页面渲染为 PNG 供多模态智能体使用。其特色能力包括空间文本框、Markdown 输出、页面栅格图输出，以及支持可选自定义 HTTP OCR 的本地解析。

Writes scientific Markdown documentation and Mermaid diagrams for workflows, relationships, timelines, and schemas. Provides syntax references, document templates, accessibility guidance, and version-aware rendering checks. Use when a user requests Markdown, Mermaid, or a text-based structural diagram; quantitative scientific figures require suitable plotting tools.为工作流、关系、时间线和数据结构（schema）编写科学 Markdown 文档和 Mermaid 图表。提供语法参考、文档模板、无障碍指导以及区分版本的渲染检查。当用户需要 Markdown、Mermaid 或基于文本的结构图时使用；定量科学图表则需使用合适的绘图工具。

Converts heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.使用 Microsoft MarkItDown 将各类文档及指定 URI 转换为 Markdown，用于文本分析、检索以及 LLM/RAG 数据导入。涵盖安全的本地转换、流式处理、Office/PDF/数据格式、批处理工作流、插件、视觉 OCR、Azure 提取以及官方 MCP 服务器。

Applies medicinal chemistry filters for compound triage, using drug-likeness rules (Lipinski, Veber, CNS), structural alert catalogs (PAINS, NIBR, ChEMBL), complexity metrics, and the medchem query language for library filtering.应用药物化学过滤规则进行化合物优先级筛选，涵盖类药性规则（Lipinski、Veber、CNS）、结构警示库（PAINS、NIBR、ChEMBL）、复杂度指标，以及用于化合物库过滤的 medchem 查询语言。

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, conducting literature reviews, finding related work, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, citation verification workflows, and paper discovery/evaluation criteria.为 NeurIPS、ICML、ICLR、ACL、AAAI、COLM 撰写可发表水准的 ML/AI 论文。适用于基于研究代码仓库起草论文、开展文献综述、查找相关工作、核实引用或准备最终版（camera-ready）投稿。包含 LaTeX 模板、引用核查工作流以及论文检索/评估标准。

Builds and audits reproducible NeuroKit2 research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment, variability, and complexity. Use when code imports neurokit2 or needs its current APIs, schemas, and method-aware validation—not for diagnosis or device validation.构建并审核可复现的 NeuroKit2 研究工作流，用于生理时间序列预处理、事件/区间分析、多模态对齐、变异性及复杂度分析。适用于代码导入 neurokit2 或需要使用其当前 API、数据结构及方法相关验证的场景——不适用于临床诊断或设备验证。

Builds, runs, and debugs Nextflow DSL2 pipelines and nf-core workflows. Use for Nextflow, nf-core, .nf files, nextflow.config, processes/channels/operators, samplesheets, nf-test, modules/subworkflows, container and executor configuration, HPC/SLURM or cloud deployment, and failed or resumed pipeline runs.构建、运行并调试 Nextflow DSL2 流程和 nf-core 工作流。适用于 Nextflow、nf-core、.nf 文件、nextflow.config、processes/channels/operators、samplesheet、nf-test、modules/subworkflows、容器与执行器配置、HPC/SLURM 或云端部署，以及失败或断点续跑（resume）的流程运行。

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.创建和编辑 Obsidian 风格的 Markdown，支持 wikilink、嵌入、callout、属性及其他 Obsidian 专有语法。适用于在 Obsidian 中处理 .md 文件，或当用户提到 wikilink、callout、frontmatter、标签、嵌入或 Obsidian 笔记时使用。

GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS, cuCIM, KvikIO, Warp, Newton, Numba-CUDA, or RAFT questions; and profiling, memory-transfer, kernel, or multi-GPU bottlenecks. Also use when large data-parallel Python code is slow and GPU acceleration is a plausible option, even if the user does not name CUDA.在 NVIDIA 硬件上对科学计算 Python 代码进行 GPU 加速，并验证结果正确且速度更快。适用于 CUDA/GPU 优化；受 CPU 限制的 NumPy、SciPy、pandas、scikit-learn、NetworkX、scikit-image、向量检索、图像处理、图计算、仿真或文件 I/O 负载；有关 CuPy、cuDF、cuML、cuGraph、cuVS、cuCIM、KvikIO、Warp、Newton、Numba-CUDA 或 RAFT 的问题；以及性能剖析、内存传输、内核或多 GPU 瓶颈。当大规模数据并行的 Python 代码运行缓慢且 GPU 加速可能可行时，即使用户未提及 CUDA，也可使用。

Searches 18 scholarly APIs for papers, preprints, citations, open-access full text, repository records, and journal OA status, and returns results with reproducible provenance. Covers PubMed, PMC, Europe PMC, bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall, OpenCitations, PubTator3, Zenodo, Figshare, ROR, BioStudies, and DOAJ. Use when searching for papers, citations, DOI/PMID/arXiv lookups, abstracts, full text, open-access PDFs, preprints, citation graphs, author publications, biomedical entity annotations, deposited records (Zenodo, Figshare, BioStudies), institution ROR IDs, or any scholarly literature query. Triggers on mentions of any supported database or requests like "find papers on X", "look up this DOI", "who cites this paper", or "get me the PDF".检索 18 个学术 API，获取论文、预印本、引用、开放获取全文、存储库记录及期刊 OA 状态，并返回带可复现来源信息的结果。覆盖 PubMed、PMC、Europe PMC、bioRxiv、medRxiv、arXiv、OpenAlex、Crossref、Semantic Scholar、CORE、Unpaywall、OpenCitations、PubTator3、Zenodo、Figshare、ROR、BioStudies 和 DOAJ。适用于检索论文和引用、按 DOI/PMID/arXiv 查找、获取摘要、全文、开放获取 PDF、预印本、引用网络、作者发表记录、生物医学实体注释、存储记录（Zenodo、Figshare、BioStudies）、机构 ROR ID，或任何学术文献查询。当提及任一受支持的数据库，或出现诸如 "find papers on X"、"look up this DOI"、"who cites this paper" 或 "get me the PDF" 之类的请求时触发。

Supports local computational pathology research with PathML: slide loading and tiling, preprocessing and QC, h5path storage, multiplex quantification, spatial graphs, and bounded model inference. Use for whole-slide H&E, CODEX, Vectra, Mesmer, HoVer-Net, and HACTNet workflows.使用 PathML 支持本地计算病理学研究：切片加载与切块、预处理与质控、h5path 存储、多重标记定量、空间图，以及限定范围的模型推理。适用于全切片 H&E、CODEX、Vectra、Mesmer、HoVer-Net 和 HACTNet 工作流。

Performs pathway and gene-set enrichment analysis on gene lists or ranked gene data and interprets the results. Used when the user has a set of genes (differentially expressed genes from PyDESeq2/Scanpy, CRISPR-screen hits, cluster marker genes, proteomics hits) and wants to know which biological pathways, GO terms, or gene sets are over-represented or enriched. Covers over-representation analysis (ORA / Enrichr / Fisher / hypergeometric), ranked Gene Set Enrichment Analysis (GSEA / preranked), single-sample scoring (ssGSEA/GSVA), and functional profiling via gseapy, g:Profiler, Enrichr libraries, MSigDB, GO, KEGG, Reactome, and WikiPathways — plus gene-ID mapping, choosing the right background universe, multiple-testing correction, redundancy reduction, dotplots/enrichment maps, and publication-ready tables. Use this for "pathway analysis", "enrichment analysis", "GO enrichment", "KEGG/Reactome pathways", "GSEA", "over-representation", "functional annotation", or "what pathways are my genes in".对基因列表或排序后的基因数据进行通路与基因集富集分析，并解读结果。适用于用户拥有一组基因（来自 PyDESeq2/Scanpy 的差异表达基因、CRISPR 筛选命中基因、聚类标志基因、蛋白质组学命中蛋白），并希望了解哪些生物学通路、GO 条目或基因集呈过度代表或富集的场景。涵盖过度代表分析（ORA / Enrichr / Fisher / 超几何检验）、基于排序的基因集富集分析（GSEA / preranked）、单样本评分（ssGSEA/GSVA），以及通过 gseapy、g:Profiler、Enrichr 库、MSigDB、GO、KEGG、Reactome 和 WikiPathways 进行功能注释——另含基因 ID 映射、选择合适的背景基因集、多重检验校正、冗余精简、点图/富集图谱以及可直接用于发表的表格。适用于 "pathway analysis"、"enrichment analysis"、"GO enrichment"、"KEGG/Reactome pathways"、"GSEA"、"over-representation"、"functional annotation" 或 "what pathways are my genes in" 等请求。

Prepares evidence-bounded, constructive peer-review drafts and structured manuscript assessments. Supports authorized review of scientific manuscripts, protocols, preprints, or research proposals; reporting-guideline selection; claim–evidence checks; methods, statistics, reproducibility, ethics, figure/table, and citation critique; or revision-response planning.在证据边界内撰写建设性的同行评审意见草稿及结构化的稿件评估。支持对科学稿件、研究方案、预印本或研究提案进行经授权的评审；报告规范的选择；论断与证据一致性核查；对方法、统计、可复现性、伦理、图表及引用的评析；或修回答复的规划。

Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when analysing concentration-time data, deriving exposure metrics, fitting PK or PD models, or evaluating dosing regimens. Triggers include "pharmacokinetics", "pharmacodynamics", "PK/PD", "NCA", "non-compartmental", "AUC", "Cmax", "lambda z", "half-life", "clearance", "volume of distribution", "compartmental model", "population PK", "popPK", "NONMEM", "nlmixr2", "Pharmpy", "Monolix", "exposure-response", "Emax", "EC50", "indirect response", "effect compartment", "TMDD", "PBPK", "bioequivalence", "RSABE", "ABEL", "allometric scaling", "first-in-human", "MABEL", "drug-drug interaction", "DDI", "ICH M12", "concentration-QTc", "therapeutic drug monitoring", "MIPD", and "dosing regimen".药代动力学与药效动力学建模与模拟——非房室分析、房室模型与群体 PK、PK/PD 及暴露-效应分析、TMDD、PBPK 概览、生物等效性、异速放大与首次人体给药剂量、药物相互作用预测，以及贝叶斯治疗药物监测。适用于分析浓度-时间数据、推导暴露指标、拟合 PK 或 PD 模型或评估给药方案。触发词包括 "pharmacokinetics"、"pharmacodynamics"、"PK/PD"、"NCA"、"non-compartmental"、"AUC"、"Cmax"、"lambda z"、"half-life"、"clearance"、"volume of distribution"、"compartmental model"、"population PK"、"popPK"、"NONMEM"、"nlmixr2"、"Pharmpy"、"Monolix"、"exposure-response"、"Emax"、"EC50"、"indirect response"、"effect compartment"、"TMDD"、"PBPK"、"bioequivalence"、"RSABE"、"ABEL"、"allometric scaling"、"first-in-human"、"MABEL"、"drug-drug interaction"、"DDI"、"ICH M12"、"concentration-QTc"、"therapeutic drug monitoring"、"MIPD" 和 "dosing regimen"。

Search PubMed for scientific literature. Use when the user asks to find papers, search literature, look up research, find publications, or asks about recent studies. Triggers on "pubmed", "papers", "literature", "publications", "research on", "studies about".在 PubMed 中检索科学文献。当用户要求查找论文、检索文献、查阅研究、查找出版物或询问近期研究时使用。触发词包括 "pubmed"、"papers"、"literature"、"publications"、"research on"、"studies about"。

Performs bulk RNA-seq differential expression analysis with PyDESeq2, including count validation, formula designs, explicit contrasts, Wald tests, FDR correction, coefficient-matched LFC shrinkage, and result visualization. Use for PyDESeq2 or Python DESeq2 workflows with biological replicates.使用 PyDESeq2 进行 bulk RNA-seq 差异表达分析，包括计数数据校验、公式设计、显式对比、Wald 检验、FDR 校正、与系数匹配的 LFC 收缩以及结果可视化。适用于含生物学重复的 PyDESeq2 或 Python DESeq2 工作流。

Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.读取、检查、写入、转换并预检本地 DICOM 数据集及像素数据。适用于 DICOM 元数据、传输语法（transfer syntax）、压缩插件、多帧图像、私有元素、JSON，以及有限范围的去标识化审查。

Builds and validates PyHealth clinical machine-learning pipelines for EHR, signals, imaging, and medical codes. Use for PyHealth dataset loading, MIMIC-III/IV, eICU or OMOP prediction tasks, patient-level evaluation, mortality/readmission/length-of-stay modeling, medication recommendation, sleep staging, Trainer checkpoints, and ICD/ATC/NDC/RxNorm mapping.构建并验证基于 PyHealth 的临床机器学习流程，涵盖 EHR、生理信号、医学影像和医学编码。适用于 PyHealth 数据集加载、MIMIC-III/IV、eICU 或 OMOP 预测任务、患者层面的评估、死亡率/再入院/住院时长建模、用药推荐、睡眠分期、Trainer 检查点，以及 ICD/ATC/NDC/RxNorm 编码映射。

Manages Zotero reference libraries using the pyzotero Python client: retrieves, creates, updates, and deletes items, collections, tags, and attachments via the Zotero Web API v3 or local API. Applies when working with Zotero libraries programmatically, managing bibliographic references, exporting citations, searching library contents, uploading PDF attachments, or building research automation workflows that integrate with Zotero.使用 pyzotero Python 客户端管理 Zotero 文献库：通过 Zotero Web API v3 或本地 API 检索、创建、更新和删除条目、分类集合、标签与附件。适用于以编程方式操作 Zotero 文献库、管理参考文献、导出引文、搜索文献库内容、上传 PDF 附件，或构建与 Zotero 集成的科研自动化工作流。

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.用于精细分子操控的化学信息学工具包。支持 SMILES/SDF 解析、分子描述符（MW、LogP、TPSA）、分子指纹、子结构搜索、2D/3D 构象生成、相似性计算和化学反应。如需接口更简洁的标准工作流，请使用 datamol（RDKit 的封装库）；需要高级控制、自定义 sanitization 或专门算法时使用 rdkit。

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation在收到代码评审反馈、动手实施建议之前使用，尤其是当反馈含义不清或技术上存疑时。要求以技术严谨性加以核实，而非表面附和或盲目照改。

Supports research proposal preparation and review for NSF, NIH, DOE, DARPA, and Taiwan NSTC, including opportunity-specific requirements, aims, review criteria, budgets, broader impacts, forms, and resubmissions. Use for investigator-authored grant development, compliance matrices, and proposal critiques.支持面向 NSF、NIH、DOE、DARPA 及台湾 NSTC 的科研基金申请书撰写与评审，涵盖具体资助机会的要求、研究目标（aims）、评审标准、预算、更广泛影响（broader impacts）、申请表格及重新申请。适用于由研究者本人主导的基金申请撰写、合规对照表制作以及申请书评析。

Performs Scanpy single-cell RNA-seq QC, normalization, HVG selection, PCA/UMAP/t-SNE, clustering, exploratory marker ranking, pseudobulk preparation, visualization, and Seurat or SingleCellExperiment RDS conversion to h5ad. Applies to established exploratory scRNA-seq workflows with explicit count and expression provenance; complementary skills cover scvi-tools models and AnnData format details.使用 Scanpy 执行单细胞 RNA-seq 的质控、标准化、高变基因（HVG）筛选、PCA/UMAP/t-SNE、聚类、探索性 marker 基因排序、pseudobulk 准备、可视化，以及将 Seurat 或 SingleCellExperiment 的 RDS 文件转换为 h5ad。适用于计数与表达数据来源明确的成熟探索性 scRNA-seq 工作流；scvi-tools 模型和 AnnData 格式细节由配套技能负责。

Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs. Use for early-stage research brainstorming or prioritizing candidate directions; hand off empirical validation, study design, ethics or regulatory review, and clinical questions to appropriate experts or skills.引导基于证据的科学构思，包括独立产出想法、结构化讨论、明确假设、透明评估、对抗式审视和决策记录。适用于早期科研头脑风暴或候选研究方向的优先级排序；实证验证、研究设计、伦理或监管审查以及临床问题应转交相应的专家或技能处理。

Evaluates scientific claims and evidence quality. Applies to experimental design validity, biases and confounders, statistical interpretation, evidence grading frameworks (GRADE, Cochrane Risk of Bias), and teaching critical analysis. Supports evidence appraisal and identifying flaws; formal peer review writing belongs to peer-review.评估科学论断及证据质量。适用于实验设计有效性、偏倚与混杂因素、统计结果解读、证据分级框架（GRADE、Cochrane Risk of Bias）以及批判性分析教学。支持证据评价和缺陷识别；正式的同行评审意见撰写请使用 peer-review。

Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.为学术报告制作幻灯片和演示文稿。适用于制作 PowerPoint 幻灯片、会议报告、研讨会讲座、科研汇报、论文答辩幻灯片或任何科学报告。提供幻灯片结构、设计模板、时间把控建议和视觉校验。支持 PowerPoint 和 LaTeX Beamer。

Security code review for vulnerabilities. Use when asked to "security review", "find vulnerabilities", "check for security issues", "audit security", "OWASP review", or review code for injection, XSS, authentication, authorization, cryptography issues. Provides systematic review with confidence-based reporting.针对安全漏洞的代码安全评审。当被要求进行 "security review"、"find vulnerabilities"、"check for security issues"、"audit security"、"OWASP review"，或评审代码中的注入、XSS、认证、授权、密码学问题时使用。提供系统化评审，并按置信度报告结果。

Calculates sample sizes and statistical power for study planning. Applies when someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers closed-form power for t-tests, ANOVA, proportions, correlations, chi-square, and regression, plus simulation-based (Monte Carlo) power for complex designs — logistic/Poisson regression, mixed models, cluster-randomized trials, survival, and interactions. Also handles requests that only mention an effect size, alpha, or "80% power" without saying "power analysis" explicitly. For laying out the study (randomization, blocking, factorial/DOE, crossover, sequential designs) use experimental-design; for analyzing data already collected and reporting it use statistical-analysis.为研究规划计算样本量和统计功效。适用于有人询问 "how many subjects/samples/replicates do I need"、需要事前（a priori）功效分析、最小可检测效应（MDE）、功效曲线，或需要为基金申请、IRB 方案或预注册论证样本量的情形。涵盖 t 检验、ANOVA、比例、相关、卡方检验和回归的解析式功效计算，以及针对复杂设计的基于模拟（Monte Carlo）的功效分析——包括 logistic/Poisson 回归、混合模型、整群随机试验、生存分析和交互作用。即使请求只提到效应量、alpha 或 "80% power" 而未明确说 "power analysis"，也可处理。如需规划研究设计（随机化、区组、析因/DOE、交叉设计、序贯设计），请使用 experimental-design；如需分析已收集的数据并报告结果，请使用 statistical-analysis。

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes在遇到任何 bug、测试失败或异常行为时，于提出修复方案之前使用。

Formats and structurally validates local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and release gates—not for clinical decision-making.在临床决策已由有资质的执业专业人员提供并核实之后，对本地治疗计划文档进行格式整理和结构性校验。适用于来源可追溯性、临床医生撰写的干预记录、目标与检查节点、共同决策记录、核对交接以及发布把关——不用于临床决策。

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback在开始需要与当前工作区隔离的功能开发时，或在执行实施计划之前使用——通过原生工具或回退到 git worktree，确保存在一个隔离的工作区。

Master the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.掌握 uv 包管理器，实现快速的 Python 依赖管理、虚拟环境管理和现代化 Python 项目工作流。适用于搭建 Python 项目、管理依赖，或使用 uv 优化 Python 开发工作流。

Prepares journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Supports selecting an official template, checking current page or anonymity rules, adapting academic writing to a venue, or inspecting a submission PDF.借助针对具体期刊/会议的格式指南和内置 LaTeX 模板框架，准备期刊稿件、会议论文、学术海报和基金申请文件。支持选择官方模板、核对当前页数或匿名要求、按目标期刊/会议调整学术写作，以及检查投稿 PDF。

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always在即将宣称工作已完成、已修复或已通过，以及提交 commit 或创建 PR 之前使用——要求先运行验证命令并确认输出，再做出任何成功声明；始终先有证据，再下结论。

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.使用 Playwright 与本地 Web 应用交互并进行测试的工具包。支持验证前端功能、调试 UI 行为、截取浏览器截图以及查看浏览器日志。