scientific-skills

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Claude Scientific Skills

Claude 科研技能集合

Overview

概述

A comprehensive collection of 139 ready-to-use scientific skills that transform Claude into an AI research assistant capable of executing complex multi-step scientific workflows across biology, chemistry, medicine, and related fields.

这是一个包含139项即用型科研技能的综合集合，可将Claude转变为AI科研助手，能够在生物学、化学、医学及相关领域执行复杂的多步骤科研工作流。

When to Use

适用场景

Invoke this skill when:

Working on scientific research tasks
Need access to specialized databases (PubMed, ChEMBL, UniProt, etc.)
Performing bioinformatics or cheminformatics analysis
Creating literature reviews or scientific documents
Analyzing single-cell RNA-seq, proteomics, or multi-omics data
Drug discovery and molecular analysis workflows
Statistical analysis and machine learning on scientific data

在以下场景中调用本技能：

开展科研任务时
需要访问专业数据库（PubMed、ChEMBL、UniProt等）时
进行生物信息学或化学信息学分析时
撰写文献综述或科研文档时
分析单细胞RNA测序、蛋白质组学或多组学数据时
进行药物发现和分子分析工作流时
对科研数据进行统计分析和机器学习时

Quick Start

快速开始

javascript

// Invoke the main skill catalog
Skill({ skill: 'scientific-skills' });

// Or invoke specific sub-skills directly
Skill({ skill: 'scientific-skills/rdkit' }); // Cheminformatics
Skill({ skill: 'scientific-skills/scanpy' }); // Single-cell analysis
Skill({ skill: 'scientific-skills/biopython' }); // Bioinformatics
Skill({ skill: 'scientific-skills/literature-review' }); // Literature review

javascript

// 调用主技能目录
Skill({ skill: 'scientific-skills' });

// 或直接调用特定子技能
Skill({ skill: 'scientific-skills/rdkit' }); // 化学信息学
Skill({ skill: 'scientific-skills/scanpy' }); // 单细胞分析
Skill({ skill: 'scientific-skills/biopython' }); // 生物信息学
Skill({ skill: 'scientific-skills/literature-review' }); // 文献综述

Skill Categories

技能分类

Scientific Databases (28+)

科学数据库（28+项）

Skill	Description
`pubchem`	Chemical compound database
`chembl-database`	Bioactivity database for drug discovery
`uniprot-database`	Protein sequence and function database
`pdb`	Protein Data Bank structures
`drugbank-database`	Drug and drug target information
`kegg`	Pathway and genome database
`clinvar-database`	Clinical variant interpretations
`cosmic-database`	Cancer mutation database
`ensembl-database`	Genome browser and annotations
`geo-database`	Gene expression data
`gwas-database`	Genome-wide association studies
`reactome-database`	Biological pathways
`string-database`	Protein-protein interactions
`alphafold-database`	Protein structure predictions
`biorxiv-database`	Preprint server for biology
`clinicaltrials-database`	Clinical trial registry
`ena-database`	European Nucleotide Archive
`fda-database`	FDA drug approvals and labels
`gene-database`	Gene information from NCBI
`zinc-database`	Commercially available compounds
`brenda-database`	Enzyme database
`clinpgx-database`	Pharmacogenomics annotations
`uspto-database`	Patent database

技能名称	描述说明
`pubchem`	化合物数据库
`chembl-database`	药物发现用生物活性数据库
`uniprot-database`	蛋白质序列与功能数据库
`pdb`	蛋白质数据库（PDB）结构
`drugbank-database`	药物及药物靶点信息库
`kegg`	通路与基因组数据库
`clinvar-database`	临床变异解读数据库
`cosmic-database`	癌症突变数据库
`ensembl-database`	基因组浏览器与注释库
`geo-database`	基因表达数据库
`gwas-database`	全基因组关联研究数据库
`reactome-database`	生物学通路数据库
`string-database`	蛋白质-蛋白质相互作用数据库
`alphafold-database`	蛋白质结构预测数据库
`biorxiv-database`	生物学预印本服务器
`clinicaltrials-database`	临床试验注册库
`ena-database`	欧洲核苷酸档案库
`fda-database`	FDA药物审批与标签库
`gene-database`	NCBI基因信息库
`zinc-database`	商用化合物数据库
`brenda-database`	酶数据库
`clinpgx-database`	药物基因组学注释库
`uspto-database`	专利数据库

Python Analysis Libraries (55+)

Python分析库（55+项）

Skill	Description
`rdkit`	Cheminformatics toolkit
`scanpy`	Single-cell RNA-seq analysis
`anndata`	Annotated data matrices
`biopython`	Computational biology tools
`pytorch-lightning`	Deep learning framework
`scikit-learn`	Machine learning library
`transformers`	NLP and deep learning models
`pandas` / `polars` / `vaex`	Data manipulation
`matplotlib` / `seaborn` / `plotly`	Visualization
`deepchem`	Deep learning for chemistry
`esm`	Evolutionary Scale Modeling
`datamol`	Molecular data processing
`pymatgen`	Materials science
`qiskit`	Quantum computing
`pymoo`	Multi-objective optimization
`statsmodels`	Statistical modeling
`sympy`	Symbolic mathematics
`networkx`	Network analysis
`geopandas`	Geospatial analysis
`shap`	Model explainability

技能名称	描述说明
`rdkit`	化学信息学工具包
`scanpy`	单细胞RNA测序分析工具
`anndata`	带注释的数据矩阵工具
`biopython`	计算生物学工具集
`pytorch-lightning`	深度学习框架
`scikit-learn`	机器学习库
`transformers`	自然语言处理与深度学习模型
`pandas` / `polars` / `vaex`	数据处理工具
`matplotlib` / `seaborn` / `plotly`	数据可视化工具
`deepchem`	化学领域深度学习工具
`esm`	进化尺度建模工具
`datamol`	分子数据处理工具
`pymatgen`	材料科学工具包
`qiskit`	量子计算工具包
`pymoo`	多目标优化工具
`statsmodels`	统计建模库
`sympy`	符号数学库
`networkx`	网络分析库
`geopandas`	地理空间分析工具
`shap`	模型可解释性工具

Bioinformatics & Genomics

生物信息学与基因组学

Skill	Description
`gget`	Gene and transcript information
`pysam`	SAM/BAM file manipulation
`deeptools`	NGS data analysis
`pydeseq2`	Differential expression
`scvi-tools`	Deep learning for single-cell
`etetoolkit`	Phylogenetic analysis
`scikit-bio`	Bioinformatics algorithms
`bioservices`	Web services for biology
`cellxgene-census`	Cell atlas exploration

技能名称	描述说明
`gget`	基因与转录本信息获取工具
`pysam`	SAM/BAM文件处理工具
`deeptools`	下一代测序（NGS）数据分析工具
`pydeseq2`	差异表达分析工具
`scvi-tools`	单细胞深度学习工具
`etetoolkit`	系统发育分析工具
`scikit-bio`	生物信息学算法库
`bioservices`	生物学Web服务工具
`cellxgene-census`	细胞图谱探索工具

Cheminformatics & Drug Discovery

化学信息学与药物发现

Skill	Description
`rdkit`	Molecular manipulation
`datamol`	Molecular data handling
`molfeat`	Molecular featurization
`diffdock`	Molecular docking
`torchdrug`	Drug discovery ML
`pytdc`	Therapeutics data commons
`cobrapy`	Metabolic modeling

技能名称	描述说明
`rdkit`	分子操作工具包
`datamol`	分子数据处理工具
`molfeat`	分子特征提取工具
`diffdock`	分子对接工具
`torchdrug`	药物发现机器学习工具
`pytdc`	治疗学数据公共库
`cobrapy`	代谢建模工具

Scientific Communication

科研成果传播

Skill	Description
`literature-review`	Systematic literature reviews
`scientific-writing`	Academic writing assistance
`scientific-schematics`	AI-generated figures
`scientific-slides`	Presentation generation
`hypothesis-generation`	Hypothesis development
`venue-templates`	Journal-specific formatting
`citation-management`	Reference management

技能名称	描述说明
`literature-review`	系统性文献综述工具
`scientific-writing`	学术写作辅助工具
`scientific-schematics`	AI生成科研图表工具
`scientific-slides`	科研演示文稿生成工具
`hypothesis-generation`	科研假设构建工具
`venue-templates`	期刊特定格式模板
`citation-management`	参考文献管理工具

Clinical & Medical

临床与医学

Skill	Description
`clinical-decision-support`	Clinical reasoning
`clinical-reports`	Medical report generation
`treatment-plans`	Treatment planning
`pyhealth`	Healthcare ML
`pydicom`	Medical imaging

技能名称	描述说明
`clinical-decision-support`	临床决策支持工具
`clinical-reports`	医学报告生成工具
`treatment-plans`	治疗方案制定工具
`pyhealth`	医疗领域机器学习工具
`pydicom`	医学影像处理工具

Laboratory & Integration

实验室与集成工具

Skill	Description
`benchling-integration`	Lab informatics platform
`dnanexus-integration`	Genomics cloud platform
`pylabrobot`	Laboratory automation
`flowio`	Flow cytometry data
`omero-integration`	Bioimaging platform

技能名称	描述说明
`benchling-integration`	实验室信息学平台集成工具
`dnanexus-integration`	基因组学云平台集成工具
`pylabrobot`	实验室自动化工具
`flowio`	流式细胞术数据处理工具
`omero-integration`	生物成像平台集成工具

Core Workflows

核心工作流

Literature Review Workflow

文献综述工作流

python

undefined

python

undefined

7-phase systematic literature review

七阶段系统性文献综述

1. Planning with PICO framework

1. 基于PICO框架规划

2. Multi-database search execution

2. 多数据库检索执行

3. Screening with PRISMA flow

3. 按PRISMA流程筛选

4. Data extraction and quality assessment

4. 数据提取与质量评估

5. Thematic synthesis

5. 主题综合分析

6. Citation verification

6. 引用验证

7. PDF generation

7. 生成PDF报告

undefined

undefined

Drug Discovery Workflow

药物发现工作流

python

undefined

python

undefined

Using RDKit + ChEMBL + datamol

使用RDKit + ChEMBL + datamol

from rdkit import Chem from rdkit.Chem import Descriptors, AllChem

1. Query ChEMBL for bioactivity data

1. 检索ChEMBL生物活性数据

2. Calculate molecular properties

2. 计算分子属性

3. Filter by drug-likeness (Lipinski)

3. 应用类药规则（Lipinski）过滤

4. Similarity screening

4. 相似性筛选

5. Substructure analysis

5. 子结构分析

undefined

undefined

Single-Cell Analysis Workflow

单细胞分析工作流

python

undefined

python

undefined

Using scanpy + anndata

使用scanpy + anndata

import scanpy as sc

1. Load and QC data

1. 加载与质量控制数据

2. Normalization and feature selection

2. 归一化与特征选择

3. Dimensionality reduction (PCA, UMAP)

3. 降维分析（PCA、UMAP）

4. Clustering (Leiden algorithm)

4. 聚类分析（Leiden算法）

5. Marker gene identification

5. 标记基因识别

6. Cell type annotation

6. 细胞类型注释

undefined

undefined

Hypothesis Generation Workflow

科研假设构建工作流

python

undefined

python

undefined

8-step systematic process

八阶段系统性流程

1. Understand phenomenon

1. 理解研究现象

2. Literature search

2. 文献检索

3. Synthesize evidence

3. 证据综合

4. Generate competing hypotheses

4. 生成竞争性假设

5. Evaluate quality

5. 假设质量评估

6. Design experiments

6. 实验设计

7. Formulate predictions

7. 预测制定

8. Generate report

8. 生成报告

undefined

undefined

Sub-Skill Structure

子技能结构

Each sub-skill follows a consistent structure:

scientific-skills/
├── SKILL.md                    # This file (catalog/index)
├── skills/                     # Individual skill directories
│   ├── rdkit/
│   │   ├── SKILL.md           # Skill documentation
│   │   ├── references/        # API references, patterns
│   │   └── scripts/           # Example scripts
│   ├── scanpy/
│   ├── biopython/
│   └── ... (139 total)

每个子技能遵循统一结构：

scientific-skills/
├── SKILL.md                    # 本文件（目录索引）
├── skills/                     # 各子技能目录
│   ├── rdkit/
│   │   ├── SKILL.md           # 子技能文档
│   │   ├── references/        # API参考与模式
│   │   └── scripts/           # 示例脚本
│   ├── scanpy/
│   ├── biopython/
│   └── ...（共139项）

Invoking Sub-Skills

调用子技能

Direct Invocation

直接调用

javascript

// Invoke specific skill
Skill({ skill: 'scientific-skills/rdkit' });
Skill({ skill: 'scientific-skills/scanpy' });

javascript

// 调用特定技能
Skill({ skill: 'scientific-skills/rdkit' });
Skill({ skill: 'scientific-skills/scanpy' });

Chained Workflows

链式工作流调用

javascript

// Multi-skill workflow
Skill({ skill: 'scientific-skills/literature-review' });
Skill({ skill: 'scientific-skills/hypothesis-generation' });
Skill({ skill: 'scientific-skills/scientific-schematics' });

javascript

// 多技能工作流
Skill({ skill: 'scientific-skills/literature-review' });
Skill({ skill: 'scientific-skills/hypothesis-generation' });
Skill({ skill: 'scientific-skills/scientific-schematics' });

Prerequisites

前置要求

Python 3.9+ (3.12+ recommended)
uv package manager (recommended)
Platform: macOS, Linux, or Windows with WSL2

Python 3.9+（推荐3.12+）
uv包管理器（推荐）
平台：macOS、Linux或带WSL2的Windows

Best Practices

最佳实践

Start with the right skill: Use the category tables above to find appropriate skills
Chain skills for complex workflows: Literature review → Hypothesis → Experiment design
Use database skills for data access: Query databases before analysis
Visualize results: Use matplotlib/seaborn/plotly skills for publication-quality figures
Document findings: Use scientific-writing skill for formal documentation

选择合适的技能起步：使用上方分类表找到适配的技能
链式调用技能完成复杂工作流：文献综述 → 假设构建 → 实验设计
先用数据库技能获取数据：分析前先调用数据库技能检索数据
可视化结果：使用matplotlib/seaborn/plotly技能生成可用于发表的图表
记录研究发现：使用科研写作技能进行正式文档记录

Integration with Agent Framework

与Agent框架的集成

Recommended Agent Pairings

Agent	Scientific Skills
`data-engineer`	polars, dask, vaex, zarr-python
`python-pro`	All Python-based skills
`database-architect`	Database skills for schema design
`technical-writer`	literature-review, scientific-writing

Agent类型	适配的科研技能
`data-engineer`	polars、dask、vaex、zarr-python
`python-pro`	所有基于Python的技能
`database-architect`	数据库技能（用于 schema 设计）
`technical-writer`	literature-review、scientific-writing

Example Agent Spawn

Agent调用示例

javascript

Task({
  task_id: 'task-1',
  subagent_type: 'python-pro',
  description: 'Analyze molecular dataset with RDKit',
  prompt: `You are the PYTHON-PRO agent with scientific research expertise.

javascript

Task({
  task_id: 'task-1',
  subagent_type: 'python-pro',
  description: '使用RDKit分析分子数据集',
  prompt: `你是具备科研专业知识的PYTHON-PRO Agent。

Task

任务

Analyze the molecular dataset for drug-likeness properties.

分析分子数据集的类药属性。

Skills to Invoke

需调用的技能

Skill({ skill: "scientific-skills/rdkit" })
Skill({ skill: "scientific-skills/datamol" })

Skill({ skill: "scientific-skills/rdkit" })
Skill({ skill: "scientific-skills/datamol" })

Workflow

工作流

Load molecular data
Calculate descriptors
Apply Lipinski filters
Generate visualization
Report findings `, });

undefined

加载分子数据
计算分子描述符
应用Lipinski过滤规则
生成可视化图表
提交研究结果报告 `, });

undefined