A comprehensive collection of 140 ready-to-use scientific skills for Claude, created by K-Dense. Transform Claude into your AI research assistant capable of executing complex multi-step scientific workflows across biology, chemistry, medicine, and beyond. 由 K-Dense 开发的 140 项现成科学技能的综合合集。将 Claude 转变为您的 AI 研究助手，能够执行涵盖生物学、化学、医学等领域的复杂多步骤科学流程。
Looking for the full AI co-scientist experience? Try K-Dense Web for 200+ skills, cloud compute, and publication-ready outputs. 想体验完整的 AI 联合科学家吗？ 试试 K-Dense Web，提供 200+技能、云计算和发表准备成果。
Want 10x the power with zero setup? K-Dense Web is the complete AI co-scientist platform—everything in this repo, plus: 想要零设置功率 10 倍？K-Dense Web 是完整的人工智能共同科学家平台——包含本仓库中的所有内容，此外还有：
| Feature 特色 | This Repo 本回购 | K-Dense Web K-稠密网络 |
|---|---|---|
| Scientific Skills 科学技能 | 140 skills 140项技能 | 200+ skills (exclusive access) 200+ 技能 （独家访问） |
| Setup Required 需要设置 | Manual installation 手动安装 | Zero setup — works instantly 零设置 ——立刻生效 |
| Compute 计算 | Your machine 你的机器 | Cloud GPUs & HPC included 云 GPU 和高性能计算（HPC） 包含 |
| Workflows 工作流程 | Basic prompts 基本提示 | End-to-end research pipelines 端到端研究流程 |
| Outputs 输出 | Code & analysis 代码与分析 | Publication-ready figures, reports & papers 可发表的数据、报告与论文 |
| Integrations 集成 | Local tools 本地工具 | Lab systems, ELNs, cloud storage 实验室系统、学习环境网（ELN）、云存储 |
Researchers at Stanford, MIT, and leading pharma companies use K-Dense Web to accelerate discoveries. 斯坦福、麻省理工学院及领先制药公司的研究人员利用 K-Dense Web 加速发现。
Get $50 in free credits — no credit card required. 获得 50 美元的免费积分 ——无需信用卡。
Learn more at k-dense.ai | Read our detailed comparison → 了解更多请访问 k-dense.ai | 阅读我们的详细对比→
These skills enable Claude to seamlessly work with specialized scientific libraries, databases, and tools across multiple scientific domains: 这些技能使 Claude 能够无缝地与多个科学领域的专业科学库、数据库和工具合作：
- 🧬 Bioinformatics & Genomics - Sequence analysis, single-cell RNA-seq, gene regulatory networks, variant annotation, phylogenetic analysis 🧬 生物信息学与基因组学——序列分析、单细胞 RNA 测序、基因调控网络、变异注释、系统发育分析
- 🧪 Cheminformatics & Drug Discovery - Molecular property prediction, virtual screening, ADMET analysis, molecular docking, lead optimization 🧪 化学信息学与药物发现——分子性质预测、虚拟筛选、ADMET 分析、分子对接、导线优化
- 🔬 Proteomics & Mass Spectrometry - LC-MS/MS processing, peptide identification, spectral matching, protein quantification 🔬 蛋白质组学与质谱——LC-MS/MS 处理、肽鉴定、光谱匹配、蛋白质定量
- 🏥 Clinical Research & Precision Medicine - Clinical trials, pharmacogenomics, variant interpretation, drug safety, clinical decision support, treatment planning 🏥 临床研究与精准医疗——临床试验、药物基因组学、变异解读、药物安全、临床决策支持、治疗计划
- 🧠 Healthcare AI & Clinical ML - EHR analysis, physiological signal processing, medical imaging, clinical prediction models 🧠 医疗人工智能与临床机器学习——电子健康记录分析、生理信号处理、医学影像、临床预测模型
- 🖼️ Medical Imaging & Digital Pathology - DICOM processing, whole slide image analysis, computational pathology, radiology workflows 🖼️ 医学影像与数字病理学——DICOM 处理、整张幻灯片图像分析、计算病理学、放射学工作流程
- 🤖 Machine Learning & AI - Deep learning, reinforcement learning, time series analysis, model interpretability, Bayesian methods 🤖 机器学习与人工智能——深度学习、强化学习、时间序列分析、模型可解释性、贝叶斯方法
- 🔮 Materials Science & Chemistry - Crystal structure analysis, phase diagrams, metabolic modeling, computational chemistry 🔮 材料科学与化学——晶体结构分析、相图、代谢建模、计算化学
- 🌌 Physics & Astronomy - Astronomical data analysis, coordinate transformations, cosmological calculations, symbolic mathematics, physics computations 🌌 物理与天文学——天文数据分析、坐标变换、宇宙学计算、符号数学、物理计算
- ⚙️ Engineering & Simulation - Discrete-event simulation, multi-objective optimization, metabolic engineering, systems modeling, process optimization ⚙️ 工程与仿真——离散事件模拟、多目标优化、代谢工程、系统建模、过程优化
- 📊 Data Analysis & Visualization - Statistical analysis, network analysis, time series, publication-quality figures, large-scale data processing, EDA 📊 数据分析与可视化——统计分析、网络分析、时间序列、发表质量数据、大规模数据处理、EDA
- 🧪 Laboratory Automation - Liquid handling protocols, lab equipment control, workflow automation, LIMS integration 🧪 实验室自动化——液体处理协议、实验室设备控制、工作流程自动化、LIMS 集成
- 📚 Scientific Communication - Literature review, peer review, scientific writing, document processing, posters, slides, schematics, citation management 📚 科学传播——文献综述、同行评审、科学写作、文档处理、海报、幻灯片、示意图、引用管理
- 🔬 Multi-omics & Systems Biology - Multi-modal data integration, pathway analysis, network biology, systems-level insights 🔬 多组学与系统生物学——多模态数据集成、通路分析、网络生物学、系统层面洞察
- 🧬 Protein Engineering & Design - Protein language models, structure prediction, sequence design, function annotation 🧬 蛋白质工程与设计——蛋白质语言模型、结构预测、序列设计、函数注释
- 🎓 Research Methodology - Hypothesis generation, scientific brainstorming, critical thinking, grant writing, scholar evaluation 🎓 研究方法论——假设生成、科学头脑风暴、批判性思维、资助申请、学者评估
Transform Claude Code into an 'AI Scientist' on your desktop! 将 Claude Code 转变为您的桌面“人工智能科学家”！
⭐ If you find this repository useful, please consider giving it a star! It helps others discover these tools and encourages us to continue maintaining and expanding this collection. ⭐ 如果你觉得这个仓库有用 ，请考虑给它一个星！它帮助他人发现这些工具，并鼓励我们继续维护和扩展这个收藏。
This repository provides 140 scientific skills organized into the following categories: 该库提供 140 项科学技能 ，分为以下类别：
- 28+ Scientific Databases - Direct API access to OpenAlex, PubMed, bioRxiv, ChEMBL, UniProt, COSMIC, ClinicalTrials.gov, and more 28+ 科学数据库 ——直接访问 OpenAlex、PubMed、bioRxiv、ChEMBL、UniProt、COSMIC、ClinicalTrials.gov 等
- 55+ Python Packages - RDKit, Scanpy, PyTorch Lightning, scikit-learn, BioPython, BioServices, PennyLane, Qiskit, and others 55+ Python 包 - RDKit、Scanpy、PyTorch Lightning、scikit-learn、BioPython、BioServices、PennyLane、Qiskit 等
- 15+ Scientific Integrations - Benchling, DNAnexus, LatchBio, OMERO, Protocols.io, and more **15+ 科学整合——**Benchling、DNAnexus、LatchBio、OMERO、Protocols.io 等
- 30+ Analysis & Communication Tools - Literature review, scientific writing, peer review, document processing, posters, slides, schematics, and more 30+ 分析与交流工具 ——文献综述、科学写作、同行评审、文档处理、海报、幻灯片、示意图等
- 10+ Research & Clinical Tools - Hypothesis generation, grant writing, clinical decision support, treatment plans, regulatory compliance 10+ 研究与临床工具 ——假设生成、资助撰写、临床决策支持、治疗计划、法规合规
Each skill includes: 每个技能包括：
- ✅ Comprehensive documentation (
SKILL.md) ✅ 全面文档（SKILL.md） - ✅ Practical code examples ✅ 实用代码示例
- ✅ Use cases and best practices ✅ 用例与最佳实践
- ✅ Integration guides ✅ 集成指南
- ✅ Reference materials ✅ 参考资料
- What's Included 包含内容
- Why Use This? 为什么要用这个？
- Getting Started 入门指南
- Support Open Source 支持开源
- Prerequisites 前提条件
- Quick Examples 快速示例
- Use Cases 使用场景
- Available Skills 可用技能
- Contributing 贡献
- Troubleshooting 故障排除
- FAQ 常见问题
- Support 支持
- Join Our Community 加入我们的社区
- Citation 引用
- License 许可
- Save Days of Work - Skip API documentation research and integration setup 节省工作日—— 跳过 API 文档研究和集成设置
- Production-Ready Code - Tested, validated examples following scientific best practices 生产就绪代码 ——遵循科学最佳实践经过测试和验证的示例
- Multi-Step Workflows - Execute complex pipelines with a single prompt 多步工作流程 ——用一个提示执行复杂的管道
- 140 Skills - Extensive coverage across all major scientific domains 140 技能——涵盖所有主要科学领域的广泛内容
- 28+ Databases - Direct access to OpenAlex, PubMed, bioRxiv, ChEMBL, UniProt, COSMIC, and more 28+ 数据库 ——直接访问 OpenAlex、PubMed、bioRxiv、ChEMBL、UniProt、COSMIC 等
- 55+ Python Packages - RDKit, Scanpy, PyTorch Lightning, scikit-learn, BioServices, PennyLane, Qiskit, and others 55+ Python 包 - RDKit、Scanpy、PyTorch Lightning、scikit-learn、BioServices、PennyLane、Qiskit 等
- One-Click Setup - Install via Claude Code or MCP server 一键设置 - 通过 Claude Code 或 MCP 服务器安装
- Automatic Discovery - Claude automatically finds and uses relevant skills 自动发现 ——Claude 会自动查找并使用相关技能
- Well Documented - Each skill includes examples, use cases, and best practices 文档详尽——每项技能都包含示例、用例和最佳实践
- Regular Updates - Continuously maintained and expanded by K-Dense team 定期更新 ——由 K-Dense 团队持续维护和扩展
- Community Driven - Open source with active community contributions 社区驱动 ——开源，社区积极贡献
- Enterprise Ready - Commercial support available for advanced needs 企业级准备 ——为高级需求提供商业支持
Choose your preferred platform to get started: 选择您偏好的平台开始：
📚 New to Claude Code? Check out the Claude Code Quickstart Guide to get started. When using Claude Code please use the Skills as a plugin. Do not use the MCP server below. 📚 刚接触 Claude 代码吗？ 请查看 Claude 代码快速入门指南 ，开始使用。使用 Claude 代码时，请将技能作为插件使用。请勿使用下面的 MCP 服务器。
Step 1: Install Claude Code 步骤 1：安装 Claude 代码
macOS: macOS：
curl -fsSL https://claude.ai/install.sh | bash
Windows: Windows：
irm https://claude.ai/install.ps1 | iex
Step 2: Register the Marketplace 步骤2：注册市场
In Claude Code, run the following command: 在 Claude Code 中，执行以下命令：
/plugin marketplace add K-Dense-AI/claude-scientific-skills
Step 3: Install the Plugin 步骤3：安装插件
Option A: Direct Install (Fastest) 选项 A：直接安装（最快）
/plugin install scientific-skills@claude-scientific-skills
Option B: Interactive Install 选项 B：交互式安装
- Run
/pluginin Claude Code 在 Claude Code 中运行/plugin - Select Browse and install plugins 选择浏览并安装插件
- Choose claude-scientific-skills marketplace 选择 claude-scientific-skills 市场
- Select scientific-skills 选择科学技能
- Click Install now 点击立即安装
That's it! Claude will automatically use the appropriate skills when you describe your scientific tasks. 就是这样！ 当你描述科学任务时，Claude 会自动运用相应的技能。
Managing Your Plugin: 管理你的插件：
# Check installed plugins
/plugin → Manage Plugins
# Update the plugin to the latest version
/plugin update scientific-skills@claude-scientific-skills
# Enable/disable the plugin
/plugin enable scientific-skills@claude-scientific-skills
/plugin disable scientific-skills@claude-scientific-skills
# Uninstall if needed
/plugin uninstall scientific-skills@claude-scientific-skills
One-click installation via our hosted MCP server: 通过我们托管的 MCP 服务器一键安装：
Access all skills via our MCP server in any MCP-compatible client (ChatGPT, Google ADK, OpenAI Agent SDK, etc.): 通过我们的 MCP 服务器访问所有技能，支持任何兼容 MCP 的客户端（ChatGPT、Google ADK、OpenAI 代理 SDK 等）：
Option 1: Hosted MCP Server (Easiest) 选项 1：托管 MCP 服务器 （最简单）
https://mcp.k-dense.ai/claude-scientific-skills/mcp
Option 2: Self-Hosted (More Control) 🔗 claude-skills-mcp - Deploy your own MCP server 选项二：自托管 （更多控制）🔗 claude-skills-mcp - 部署您自己的 MCP 服务器
Claude Scientific Skills is powered by 50+ incredible open source projects maintained by dedicated developers and research communities worldwide. Projects like Biopython, Scanpy, RDKit, scikit-learn, PyTorch Lightning, and many others form the foundation of these skills. Claude Scientific Skills 由全球敬业的开发者和研究社区维护的 50+ 个令人难以置信的开源项目提供支持。像 Biopython、Scanpy、RDKit、scikit-learn、PyTorch Lightning 等项目构成了这些技能的基础。
If you find value in this repository, please consider supporting the projects that make it possible: 如果您觉得这个仓库有价值，请考虑支持那些使该项目成为可能的项目：
- ⭐ Star their repositories on GitHub ⭐ 在 GitHub 上给他们的仓库加星号
- 💰 Sponsor maintainers via GitHub Sponsors or NumFOCUS 💰 通过 GitHub 赞助商或 NumFOCUS 赞助维护者
- 📝 Cite projects in your publications 📝 引用您的出版物中的项目
- 💻 Contribute code, docs, or bug reports 💻 贡献代码、文档或错误报告
👉 View the full list of projects to support 👉 查看支持项目的完整列表
- Python: 3.9+ (3.12+ recommended for best compatibility) Python：3.9+（推荐 3.12+以获得最佳兼容性）
- uv: Python package manager (required for installing skill dependencies) uv：Python 包管理器（安装技能依赖必备）
- Client: Claude Code, Cursor, or any MCP-compatible client 客户端 ：Claude Code、Cursor 或任何兼容 MCP 的客户端
- System: macOS, Linux, or Windows with WSL2 系统 ：macOS、Linux 或 Windows WSL2
- Dependencies: Automatically handled by individual skills (check
SKILL.mdfiles for specific requirements) 依赖：由单个技能自动处理（ 具体需求请查看SKILL.md文件）
The skills use uv as the package manager for installing Python dependencies. Install it using the instructions for your operating system:
这些技能用 UV 作为安装 Python 依赖的包管理器。按照作系统说明安装：
macOS and Linux: macOS 和 Linux：
curl -LsSf https://astral.sh/uv/install.sh | sh
Windows: Windows：
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Alternative (via pip): 替代方案（通过 pip）：
pip install uv
After installation, verify it works by running: 安装后，请通过以下作验证：
uv --version
For more installation options and details, visit the official uv documentation. 更多安装选项和详情，请访问官方紫外线文档 。
Once you've installed the skills, you can ask Claude to execute complex multi-step scientific workflows. Here are some example prompts: 安装好技能后，你可以让 Claude 执行复杂的多步骤科学工作流程。以下是一些示例提示：
Goal: Find novel EGFR inhibitors for lung cancer treatment 目标 ：寻找用于肺癌治疗的新型 EGFR 抑制剂
Prompt: 提示：
Use available skills you have access to whenever possible. Query ChEMBL for EGFR inhibitors (IC50 < 50nM), analyze structure-activity relationships
with RDKit, generate improved analogs with datamol, perform virtual screening with DiffDock
against AlphaFold EGFR structure, search PubMed for resistance mechanisms, check COSMIC for
mutations, and create visualizations and a comprehensive report.
Skills Used: ChEMBL, RDKit, datamol, DiffDock, AlphaFold DB, PubMed, COSMIC, scientific visualization 使用技能 ：ChEMBL、RDKit、datamol、DiffDock、AlphaFold 数据库、PubMed、COSMIC、科学可视化
Goal: Comprehensive analysis of 10X Genomics data with public data integration 目标：全面分析 10X 基因组学数据并整合公开数据
Prompt: 提示：
Use available skills you have access to whenever possible. Load 10X dataset with Scanpy, perform QC and doublet removal, integrate with Cellxgene
Census data, identify cell types using NCBI Gene markers, run differential expression with
PyDESeq2, infer gene regulatory networks with Arboreto, enrich pathways via Reactome/KEGG,
and identify therapeutic targets with Open Targets.
Skills Used: Scanpy, Cellxgene Census, NCBI Gene, PyDESeq2, Arboreto, Reactome, KEGG, Open Targets 所用技能 ：扫描、细胞基因普查、NCBI 基因、PyDESeq2、树木、反应组、KEGG、开放靶点
Goal: Integrate RNA-seq, proteomics, and metabolomics to predict patient outcomes 目标 ：整合 RNA 测序、蛋白质组学和代谢组学，预测患者结局
Prompt: 提示：
Use available skills you have access to whenever possible. Analyze RNA-seq with PyDESeq2, process mass spec with pyOpenMS, integrate metabolites from
HMDB/Metabolomics Workbench, map proteins to pathways (UniProt/KEGG), find interactions via
STRING, correlate omics layers with statsmodels, build predictive model with scikit-learn,
and search ClinicalTrials.gov for relevant trials.
Skills Used: PyDESeq2, pyOpenMS, HMDB, Metabolomics Workbench, UniProt, KEGG, STRING, statsmodels, scikit-learn, ClinicalTrials.gov 使用技能 ：PyDESeq2、pyOpenMS、HMDB、Metabolomics Workbench、UniProt、KEGG、STRING、statsmodels、scikit-learn、ClinicalTrials.gov
Goal: Discover allosteric modulators for protein-protein interactions 目标 ：发现蛋白质间相互作用的变构调节剂
Prompt: 提示：
Use available skills you have access to whenever possible. Retrieve AlphaFold structures, identify interaction interface with BioPython, search ZINC
for allosteric candidates (MW 300-500, logP 2-4), filter with RDKit, dock with DiffDock,
rank with DeepChem, check PubChem suppliers, search USPTO patents, and optimize leads with
MedChem/molfeat.
Skills Used: AlphaFold DB, BioPython, ZINC, RDKit, DiffDock, DeepChem, PubChem, USPTO, MedChem, molfeat 使用技能 ：AlphaFold 数据库、BioPython、ZINC、RDKit、DiffDock、深化化学、PubChem、USPTO、MedChem、molfeat
Goal: Analyze VCF file for hereditary cancer risk assessment 目标 ：分析 VCF 文件以评估遗传性癌症风险
Prompt: 提示：
Use available skills you have access to whenever possible. Parse VCF with pysam, annotate variants with Ensembl VEP, query ClinVar for pathogenicity,
check COSMIC for cancer mutations, retrieve gene info from NCBI Gene, analyze protein impact
with UniProt, search PubMed for case reports, check ClinPGx for pharmacogenomics, generate
clinical report with ReportLab, and find matching trials on ClinicalTrials.gov.
Skills Used: pysam, Ensembl, ClinVar, COSMIC, NCBI Gene, UniProt, PubMed, ClinPGx, ReportLab, ClinicalTrials.gov 使用技能 ：pysam、Ensembl、ClinVar、COSMIC、NCBI Gene、UniProt、PubMed、ClinPGx、ReportLab、ClinicalTrials.gov
Goal: Analyze gene regulatory networks from RNA-seq data 目标 ：分析 RNA 测序数据中的基因调控网络
Prompt: 提示：
Use available skills you have access to whenever possible. Query NCBI Gene for annotations, retrieve sequences from UniProt, identify interactions via
STRING, map to Reactome/KEGG pathways, analyze topology with Torch Geometric, reconstruct
GRNs with Arboreto, assess druggability with Open Targets, model with PyMC, visualize
networks, and search GEO for similar patterns.
Skills Used: NCBI Gene, UniProt, STRING, Reactome, KEGG, Torch Geometric, Arboreto, Open Targets, PyMC, GEO 使用技能 ：NCBI 基因、单一蛋白、弦、反应组、KEGG、火炬几何、树木、开放目标、PyMC、地理
📖 Want more examples? Check out docs/examples.md for comprehensive workflow examples and detailed use cases across all scientific domains. 📖 想要更多例子吗？ 可以查看 docs/examples.md，获取涵盖所有科学领域的全面工作流程示例和详细用例。
- Virtual Screening: Screen millions of compounds from PubChem/ZINC against protein targets 虚拟筛选 ：从 PubChem/ZINC 筛查数百万化合物与蛋白质靶点
- Lead Optimization: Analyze structure-activity relationships with RDKit, generate analogs with datamol 潜在客户优化 ：用 RDKit 分析结构-活性关系，用 datamol 生成类比
- ADMET Prediction: Predict absorption, distribution, metabolism, excretion, and toxicity with DeepChem ADMET 预测 ：利用 DeepChem 预测吸收、分布、新陈代谢、排泄和毒性
- Molecular Docking: Predict binding poses and affinities with DiffDock 分子对接 ：预测结合姿态和与 DiffDock 的亲和力
- Bioactivity Mining: Query ChEMBL for known inhibitors and analyze SAR patterns 生物活性挖掘 ：查询 ChEMBL 中已知抑制剂并分析 SAR 模式
- Sequence Analysis: Process DNA/RNA/protein sequences with BioPython and pysam 序列分析 ：利用 BioPython 和 pysam 处理 DNA/RNA/蛋白质序列
- Single-Cell Analysis: Analyze 10X Genomics data with Scanpy, identify cell types, infer GRNs with Arboreto 单细胞分析 ：用 Scanpy 分析 10X 基因组数据，识别细胞类型，用 Arboreto 推断 GRNs。
- Variant Annotation: Annotate VCF files with Ensembl VEP, query ClinVar for pathogenicity 变体注释 ：用 Ensembl VEP 注释 VCF 文件，查询 ClinVar 的致病性
- Gene Discovery: Query NCBI Gene, UniProt, and Ensembl for comprehensive gene information 基因发现 ：查询 NCBI Gene、UniProt 和 Ensembl 以获取全面的基因信息
- Network Analysis: Identify protein-protein interactions via STRING, map to pathways (KEGG, Reactome) 网络分析 ：通过 STRING 识别蛋白质-蛋白质相互作用，映射到通路（KEGG，反应组）
- Clinical Trials: Search ClinicalTrials.gov for relevant studies, analyze eligibility criteria 临床试验 ：ClinicalTrials.gov 搜索相关研究，分析资格标准
- Variant Interpretation: Annotate variants with ClinVar, COSMIC, and ClinPGx for pharmacogenomics 变异解读 ：用 ClinVar、COSMIC 和 ClinPGx 注释变异，用于药物基因组学
- Drug Safety: Query FDA databases for adverse events, drug interactions, and recalls 药品安全 ：查询 FDA 数据库中的不良事件、药物相互作用和召回信息
- Precision Therapeutics: Match patient variants to targeted therapies and clinical trials 精准治疗 ：将患者变异与靶向疗法和临床试验匹配
- Multi-Omics Integration: Combine RNA-seq, proteomics, and metabolomics data 多组学整合 ：结合 RNA 测序、蛋白质组学和代谢组学数据
- Pathway Analysis: Enrich differentially expressed genes in KEGG/Reactome pathways 途径分析 ：富集 KEGG/反应组途径中差异表达的基因
- Network Biology: Reconstruct gene regulatory networks, identify hub genes 网络生物学 ：重建基因调控网络，识别枢纽基因
- Biomarker Discovery: Integrate multi-omics layers to predict patient outcomes 生物标志物发现 ：整合多组学层次以预测患者结局
- Statistical Analysis: Perform hypothesis testing, power analysis, and experimental design 统计分析 ：进行假设检验、检验力分析和实验设计
- Publication Figures: Create publication-quality visualizations with matplotlib and seaborn 出版图表 ：使用 matplotlib 和 seaborn 创建发表级可视化
- Network Visualization: Visualize biological networks with NetworkX 网络可视化 ：使用 NetworkX 可视化生物网络
- Report Generation: Generate comprehensive PDF reports with ReportLab 报告生成 ：使用 ReportLab 生成全面的 PDF 报告
- Protocol Design: Create Opentrons protocols for automated liquid handling 协议设计 ：创建用于自动液体处理的 Opentron 协议
- LIMS Integration: Integrate with Benchling and LabArchives for data management LIMS 集成 ：与 Benchling 和 LabArchives 集成以实现数据管理
- Workflow Automation: Automate multi-step laboratory workflows 工作流程自动化 ：自动化多步骤实验室工作流程
This repository contains 140 scientific skills organized across multiple domains. Each skill provides comprehensive documentation, code examples, and best practices for working with scientific libraries, databases, and tools. 该仓库包含 140 项跨领域科学技能。每项技能都提供全面的文档、代码示例以及科学库、数据库和工具的最佳实践。
- Sequence analysis: BioPython, pysam, scikit-bio, BioServices 序列分析：BioPython、pysam、scikit-bio、BioServices
- Single-cell analysis: Scanpy, AnnData, scvi-tools, Arboreto, Cellxgene Census 单细胞分析：Scanpy、AnnData、scvi-tools、Arboreto、Cellxgene Census
- Genomic tools: gget, geniml, gtars, deepTools, FlowIO, Zarr Genomic tools： gget， geniml， gtars， deepTools， FlowIO， Zarr
- Phylogenetics: ETE Toolkit 系统发生学：ETE 工具包
- Molecular manipulation: RDKit, Datamol, Molfeat 分子作：RDKit、Datamol、Molfeat
- Deep learning: DeepChem, TorchDrug 深度学习：DeepChem，TorchDrug
- Docking & screening: DiffDock 对接与筛选：DiffDock
- Cloud quantum chemistry: Rowan (pKa, docking, cofolding) 云量子化学：Rowan（pKa，对接，共折叠）
- Drug-likeness: MedChem 药物类比：MedChem
- Benchmarks: PyTDC 基准测试：PyTDC
- Spectral processing: matchms, pyOpenMS 频谱处理：matchms，pyOpenMS
- Clinical databases: ClinicalTrials.gov, ClinVar, ClinPGx, COSMIC, FDA Databases 临床数据库：ClinicalTrials.gov、ClinVar、ClinPGx、COSMIC、FDA 数据库
- Healthcare AI: PyHealth, NeuroKit2, Clinical Decision Support 医疗人工智能：PyHealth、NeuroKit2、临床决策支持
- Clinical documentation: Clinical Reports, Treatment Plans 临床文档：临床报告、治疗计划
- Variant analysis: Ensembl, NCBI Gene 变异分析：Ensembl，NCBI 基因
- DICOM processing: pydicom DICOM 处理：pydicom
- Whole slide imaging: histolab, PathML 全片影像：histolab，PathML
- Neural recordings: Neuropixels-Analysis (extracellular spikes, silicon probes, spike sorting) 神经记录：神经像素分析（细胞外尖峰、硅探针、尖峰分类）
- Deep learning: PyTorch Lightning, Transformers, Stable Baselines3, PufferLib 深度学习：PyTorch Lightning、Transformers、Stable Baselines3、PufferLib
- Classical ML: scikit-learn, scikit-survival, SHAP 经典机器学习：scikit-learn、scikit-survival、SHAP
- Time series: aeon 时间序列：aeon
- Bayesian methods: PyMC 贝叶斯方法：PyMC
- Optimization: PyMOO 优化：PyMOO
- Graph ML: Torch Geometric 图 ML：火炬几何
- Dimensionality reduction: UMAP-learn 降维：UMAP-learn
- Statistical modeling: statsmodels 统计建模：statsmodels
- Materials: Pymatgen 材料：Pymatgen
- Metabolic modeling: COBRApy 代谢建模：COBRApy
- Astronomy: Astropy 天文学：天文观测
- Quantum computing: Cirq, PennyLane, Qiskit, QuTiP 量子计算：Cirq、PennyLane、Qiskit、QuTiP
- Numerical computing: MATLAB/Octave 数值计算：MATLAB/八度
- Computational fluid dynamics: FluidSim 计算流体力学：流体模拟
- Discrete-event simulation: SimPy 离散事件仿真：SimPy
- Data processing: Dask, Polars, Vaex 数据处理：Dask、Polars、Vaex
- Visualization: Matplotlib, Seaborn, Plotly, Scientific Visualization 可视化：Matplotlib、Seaborn、Plotly、科学可视化
- Geospatial analysis: GeoPandas 地理空间分析：GeoPandas
- Network analysis: NetworkX 网络分析：NetworkX
- Symbolic math: SymPy 符号数学：SymPy
- PDF generation: ReportLab PDF 生成：ReportLab
- Data access: Data Commons 数据访问：Data Commons
- Exploratory data analysis: EDA workflows 探索性数据分析：EDA 工作流程
- Statistical analysis: Statistical Analysis workflows 统计分析：统计分析工作流程
- Liquid handling: PyLabRobot 液体处理：PyLabRobot
- Protocol management: Protocols.io 协议管理：Protocols.io
- LIMS integration: Benchling, LabArchives LIMS 集成：Benchling，LabArchives
- Pathway analysis: KEGG, Reactome, STRING 通路分析：KEGG、反应组、STRING
- Multi-omics: BIOMNI, Denario, HypoGeniC 多组学：BIOMNI、Denario、HypoGeniC
- Data management: LaminDB 数据管理：LaminDB
- Protein language models: ESM 蛋白质语言模型：ESM
- Cloud laboratory platform: Adaptyv (automated protein testing and validation) 云实验室平台：Adaptyv（自动蛋白质检测与验证）
- Literature: OpenAlex, PubMed, bioRxiv, Literature Review 文献：OpenAlex、PubMed、bioRxiv、文献综述
- Web search: Perplexity Search (AI-powered search with real-time information) 网页搜索：复杂性搜索（AI 驱动的实时信息搜索）
- Writing: Scientific Writing, Peer Review 写作：科学写作，同行评审
- Document processing: XLSX, MarkItDown, Document Skills 文档处理：XLSX、MarkItDown、文档技能
- Publishing: Paper-2-Web, Venue Templates 出版：Paper-2-Web，场地模板
- Presentations: Scientific Slides, LaTeX Posters, PPTX Posters 演示：科学幻灯片、LaTeX 海报、PPTX 海报
- Diagrams: Scientific Schematics 图表：科学示意图
- Citations: Citation Management 引用：引用管理
- Illustration: Generate Image (AI image generation with FLUX.2 Pro and Gemini 3 Pro (Nano Banana Pro)) 插图：生成图像（使用 FLUX.2 Pro 和 Gemini 3 Pro（Nano Banana Pro）进行的 AI 图像生成）
- Protein: UniProt, PDB, AlphaFold DB 蛋白质：UniProt、PDB、AlphaFold DB
- Chemical: PubChem, ChEMBL, DrugBank, ZINC, HMDB 化学：PubChem、ChEMBL、DrugBank、ZINC、HMDB
- Genomic: Ensembl, NCBI Gene, GEO, ENA, GWAS Catalog 基因组学：Ensembl、NCBI Gene、GEO、ENA、GWAS 目录
- Literature: bioRxiv (preprints) 文献：bioRxiv（预印本）
- Clinical: ClinVar, COSMIC, ClinicalTrials.gov, ClinPGx, FDA Databases 临床：ClinVar、COSMIC、ClinicalTrials.gov、ClinPGx、FDA 数据库
- Pathways: KEGG, Reactome, STRING 通路：KEGG、反应组、弦
- Targets: Open Targets 目标：开放目标
- Metabolomics: Metabolomics Workbench 代谢组学：代谢组学工作台
- Enzymes: BRENDA 酶类：BRENDA
- Patents: USPTO 专利：美国专利商标局
- Cloud compute: Modal 云计算：模态
- Genomics platforms: DNAnexus, LatchBio 基因组学平台：DNAnexus，LatchBio
- Microscopy: OMERO 显微镜：OMERO
- Automation: Opentrons 自动化：Opentrons
- Tool discovery: ToolUniverse, Get Available Resources 工具发现：ToolUniverse，获取可用资源
- Ideation: Scientific Brainstorming, Hypothesis Generation 构思：科学头脑风暴，假设生成
- Critical analysis: Scientific Critical Thinking, Scholar Evaluation 批判性分析：科学批判性思维，学者评价
- Funding: Research Grants 资金来源：研究资助
- Discovery: Research Lookup 发现：研究查询
- Market analysis: Market Research Reports 市场分析：市场调研报告
- Medical device standards: ISO 13485 Certification 医疗器械标准：ISO 13485 认证
📖 For complete details on all skills, see docs/scientific-skills.md 📖 关于所有技能的完整详情 ，请参见 docs/scientific-skills.md
💡 Looking for practical examples? Check out docs/examples.md for comprehensive workflow examples across all scientific domains. 💡 想找实用的例子吗？ 可以查看 docs/examples.md，获取涵盖所有科学领域的全面工作流程示例。
We welcome contributions to expand and improve this scientific skills repository! 我们欢迎大家贡献，以扩展和完善这个科学技能库！
✨ Add New Skills ✨ 新增技能
- Create skills for additional scientific packages or databases 为额外的科学软件包或数据库创建技能
- Add integrations for scientific platforms and tools 为科学平台和工具添加集成
📚 Improve Existing Skills 📚 提升现有技能
- Enhance documentation with more examples and use cases 用更多示例和用例来丰富文档
- Add new workflows and reference materials 添加新的工作流程和参考材料
- Improve code examples and scripts 改进代码示例和脚本
- Fix bugs or update outdated information 修复漏洞或更新过时信息
🐛 Report Issues 🐛 报告问题
- Submit bug reports with detailed reproduction steps 提交带有详细复刻步骤的错误报告
- Suggest improvements or new features 建议改进或新功能
- Fork the repository 分支仓库
- Create a feature branch (
git checkout -b feature/amazing-skill) 创建功能分支 （git checkout -b feature/amazing-skill） - Follow the existing directory structure and documentation patterns 遵循现有的目录结构和文档模式
- Ensure all new skills include comprehensive
SKILL.mdfiles 确保所有新技能都包含全面的SKILL.md文件 - Test your examples and workflows thoroughly 彻底测试你的示例和工作流程
- Commit your changes (
git commit -m 'Add amazing skill') 提交你的修改（git commit -m 'Add amazing skill'） - Push to your branch (
git push origin feature/amazing-skill) 推到你的分支 （git push origin feature/amazing-skill） - Submit a pull request with a clear description of your changes 提交一个拉取请求，明确描述你的更改
✅ Adhere to the Agent Skills Specification — Every skill must follow the official spec (valid SKILL.md frontmatter, naming conventions, directory structure)
✅ 遵守代理技能规范 ——每个技能必须遵循官方规范（有效 SKILL.md 前言、命名规范、目录结构）
✅ Maintain consistency with existing skill documentation format
✅ 保持与现有技能文档格式的一致性
✅ Ensure all code examples are tested and functional
✅ 确保所有代码示例都经过测试并可正常运行
✅ Follow scientific best practices in examples and workflows
✅ 遵循科学的最佳实践，在示例和工作流程中保持一致
✅ Update relevant documentation when adding new capabilities
✅ 添加新功能时更新相关文档
✅ Provide clear comments and docstrings in code
✅ 在代码中提供清晰的注释和文档字符串
✅ Include references to official documentation
✅ 附带官方文件参考
Contributors are recognized in our community and may be featured in: 贡献者在我们的社区中受到认可，可能会出现在：
- Repository contributors list 仓库贡献者列表
- Special mentions in release notes 特别提及于发行说明中
- K-Dense community highlights K-Dense 社区亮点
Your contributions help make scientific computing more accessible and enable researchers to leverage AI tools more effectively! 您的贡献帮助科学计算更加易及，使研究人员能够更有效地利用人工智能工具！
This project builds on 50+ amazing open source projects. If you find value in these skills, please consider supporting the projects we depend on. 这个项目建立在 50+个令人惊叹的开源项目之上。如果您觉得这些技能有价值，请考虑支持我们依赖的项目 。
Problem: Skills not loading in Claude Code 问题：Claude 代码中技能无法加载
- Solution: Ensure you've installed the latest version of Claude Code 解决方案：确保你安装的是最新版本的 Claude 代码
- Verify the plugin is installed:
/plugin → Manage Plugins确认插件已安装：/plugin → 管理插件 - Try reinstalling:
/plugin uninstall scientific-skills@claude-scientific-skillsthen/plugin install scientific-skills@claude-scientific-skills试着重新安装：/plugin uninstall scientific-skills@claude-scientific-skills然后/plugin install scientific-skills@claude-scientific-skills - Re-add the marketplace if needed:
/plugin marketplace add K-Dense-AI/claude-scientific-skills如有需要，请重新添加市场：/plugin marketplace add K-Dense-AI/claude-scientific-skills
Problem: Missing Python dependencies 问题：缺少 Python 依赖
- Solution: Check the specific
SKILL.mdfile for required packages 解决方案：查看具体SKILL.md文件中的所需包裹 - Install dependencies:
uv pip install package-nameInstall dependencies：uv pip install package-name
Problem: API rate limits 问题：API 速率限制
- Solution: Many databases have rate limits. Review the specific database documentation 解决方案：许多数据库有速率限制。请查看具体的数据库文档
- Consider implementing caching or batch requests 考虑实现缓存或批处理请求
Problem: Authentication errors 问题：认证错误
- Solution: Some services require API keys. Check the
SKILL.mdfor authentication setup 解决方案：有些服务需要 API 密钥。查看SKILL.md中的身份验证设置 - Verify your credentials and permissions 验证你的凭证和权限
Problem: Outdated examples 问题：过时的示例
- Solution: Report the issue via GitHub Issues 解决方案：通过 GitHub Issues 举报问题
- Check the official package documentation for updated syntax 请查看官方包文档以获取最新的语法
Q: Is this free to use?
问：这是免费使用的吗？
A: Yes! This repository is MIT licensed. However, each individual skill has its own license specified in the license metadata field within its SKILL.md file—be sure to review and comply with those terms.
答：是的！该仓库获得了麻省理工学院（MIT）许可。不过，每个技能在其 SKILL.md 文件中的许可证元数据字段中都有自己的许可证——请务必审查并遵守这些条款。
Q: Why are all skills grouped into one plugin instead of separate plugins? 问：为什么所有技能都集中在一个插件里，而不是分开的插件？ A: We believe good science in the age of AI is inherently interdisciplinary. Bundling all skills into a single plugin makes it trivial for you (and Claude) to bridge across fields—e.g., combining genomics, cheminformatics, clinical data, and machine learning in one workflow—without worrying about which individual skills to install or wire together. 答：我们相信，在人工智能时代，优质科学本质上是跨学科的。将所有技能打包到一个插件中，让你（和 Claude）轻松跨领域跨领域交流——例如将基因组学、化学信息学、临床数据和机器学习整合到一个工作流程中——而无需担心安装或连接哪些技能。
Q: Can I use this for commercial projects?
问：我可以用它做商业项目吗？
A: The repository itself is MIT licensed, which allows commercial use. However, individual skills may have different licenses—check the license field in each skill's SKILL.md file to ensure compliance with your intended use.
答：该仓库本身是 MIT 许可的，允许商业使用。不过，每个技能可能有不同的许可证——请检查每个技能 SKILL.md 档中的许可证字段，以确保符合你的预期用途。
Q: Do all skills have the same license?
问：所有技能的许可证都一样吗？
A: No. Each skill has its own license specified in the license metadata field within its SKILL.md file. These licenses may differ from the repository's MIT License. Users are responsible for reviewing and adhering to the license terms of each individual skill they use.
答：没有。每个技能在其 SKILL.md 文件中的许可证元数据字段中都有自己的许可证。这些许可证可能与仓库的 MIT 许可证不同。用户需负责审查并遵守他们所使用的每项技能的许可条款。
Q: How often is this updated? 问：更新频率如何？ A: We regularly update skills to reflect the latest versions of packages and APIs. Major updates are announced in release notes. 答：我们会定期更新技能，以反映最新版本的包和 API。重大更新会在发布说明中公布。
Q: Can I use this with other AI models? 问：我可以把这个功能用在其他 AI 模型上吗？ A: The skills are optimized for Claude but can be adapted for other models with MCP support. The MCP server works with any MCP-compatible client. 答：这些技能针对 Claude 进行了优化，但也可以适配到支持 MCP 的其他模型。MCP 服务器可与任何兼容 MCP 的客户端兼容。
Q: Do I need all the Python packages installed?
问：我需要安装所有 Python 包吗？
A: No! Only install the packages you need. Each skill specifies its requirements in its SKILL.md file.
答：不！只安装你需要的软件包。每个技能在其 SKILL.md 文件中明确要求。
Q: What if a skill doesn't work? 问：如果某个技能不起作用怎么办？ A: First check the Troubleshooting section. If the issue persists, file an issue on GitHub with detailed reproduction steps. 答：首先查看故障排除部分。如果问题依旧，请在 GitHub 提交详细复刻步骤的问题。
Q: Do the skills work offline? 问：这些技能离线有效吗？ A: Database skills require internet access to query APIs. Package skills work offline once Python dependencies are installed. 答：数据库技能需要通过互联网访问查询 API。安装了 Python 依赖后，软件包技能可以离线使用。
Q: Can I contribute my own skills? 问：我可以贡献自己的技能吗？ A: Absolutely! We welcome contributions. See the Contributing section for guidelines and best practices. 答：绝对可以！我们欢迎大家的贡献。请参阅贡献部分，了解指南和最佳实践。
Q: How do I report bugs or suggest features? 问：我如何报告错误或建议功能？ A: Open an issue on GitHub with a clear description. For bugs, include reproduction steps and expected vs actual behavior. 答：在 GitHub 上开一个带有明确描述的问题。对于漏洞，包含复制步骤以及预期与实际行为。
Need help? Here's how to get support: 需要帮助吗？以下是获得支持的方法：
- 📖 Documentation: Check the relevant
SKILL.mdandreferences/folders 📖 文档 ：请核对相关SKILL.md和参考文献/文件夹 - 🐛 Bug Reports: Open an issue 🐛 错误报告 ： 开启问题
- 💡 Feature Requests: Submit a feature request 💡 功能请求 ： 提交功能请求
- 💼 Enterprise Support: Contact K-Dense for commercial support 💼 企业支持 ：如需商业支持 请联系 K-Dense
- 🌐 MCP Support: Visit the claude-skills-mcp repository or use our hosted MCP server 🌐 MCP 支持 ：访问 claude-skills-mcp 仓库或使用我们托管的 MCP 服务器
We'd love to have you join us! 🚀 **我们非常欢迎你加入我们！**🚀
Connect with other scientists, researchers, and AI enthusiasts using Claude for scientific computing. Share your discoveries, ask questions, get help with your projects, and collaborate with the community! 与其他使用 Claude 进行科学计算的科学家、研究人员和人工智能爱好者交流。分享你的发现，提问，获得项目帮助，并与社区合作！
🌟 Join our Slack Community 🌟 🌟 **加入我们的 Slack 社区 **🌟
Whether you're just getting started or you're a power user, our community is here to support you. We share tips, troubleshoot issues together, showcase cool projects, and discuss the latest developments in AI-powered scientific research. 无论你是刚起步还是高级用户，我们的社区都在这里支持你。我们分享技巧，一起排查问题，展示酷炫项目，并讨论人工智能驱动科学研究的最新进展。
See you there! 💬 **到时候见！**💬
If you use Claude Scientific Skills in your research or project, please cite it as: 如果您在研究或项目中使用 Claude Scientific Skills，请注明：
@software{claude_scientific_skills_2025,
author = {{K-Dense Inc.}},
title = {Claude Scientific Skills: A Comprehensive Collection of Scientific Tools for Claude AI},
year = {2025},
url = {https://github.com/K-Dense-AI/claude-scientific-skills},
note = {skills covering databases, packages, integrations, and analysis tools}
}
K-Dense Inc. (2025). Claude Scientific Skills: A comprehensive collection of scientific tools for Claude AI [Computer software]. https://github.com/K-Dense-AI/claude-scientific-skills
K-Dense Inc. Claude Scientific Skills: A Comprehensive Collection of Scientific Tools for Claude AI. 2025, github.com/K-Dense-AI/claude-scientific-skills.
Claude Scientific Skills by K-Dense Inc. (2025)
Available at: https://github.com/K-Dense-AI/claude-scientific-skills
We appreciate acknowledgment in publications, presentations, or projects that benefit from these skills! 我们非常感谢在出版物、演讲或项目中认可这些技能！
This project is licensed under the MIT License. 该项目采用 MIT 许可证授权。
Copyright © 2025 K-Dense Inc. (k-dense.ai) 版权所有 © 2025 K-Dense Inc.（k-dense.ai）
- ✅ Free for any use (commercial and noncommercial) ✅ 免费用于任何用途 （商业和非商业）
- ✅ Open source - modify, distribute, and use freely ✅ 开源 ——自由修改、分发和使用
- ✅ Permissive - minimal restrictions on reuse ✅ 宽容 ——对重复使用限制极少
⚠️ No warranty - provided "as is" without warranty of any kind⚠️ 无保修 ——仅提供“现状”，不提供任何形式的保修
See LICENSE.md for full terms. 完整期限请参见 LICENSE.md。
⚠️ Important: Each skill has its own license specified in thelicensemetadata field within itsSKILL.mdfile. These licenses may differ from the repository's MIT License and may include additional terms or restrictions. Users are responsible for reviewing and adhering to the license terms of each individual skill they use.⚠️ 重要提示 ：每个技能在其SKILL.md文件中的许可证元数据字段中都有自己的许可证。这些许可证可能与仓库的 MIT 许可证不同，并可能包含额外的条款或限制。 用户需负责审查并遵守他们所使用的每项技能的许可条款。