無料GitHub で公開

scientific-skills

Comprehensive scientific research toolkit with 139 specialized skills for biology, chemistry, medicine, data science, and computational research. Transforms Claude into an AI research assistant with access to scientific databases, analysis tools, and domain-specific workflows.

oimiragieo/agent-studio

インストール方法を見る

含まれるファイル（200）

SKILL.md15.3 KB
commands/scientific-skills.md117 B
hooks/post-execute.cjs187 B
hooks/pre-execute.cjs293 B
README.md32.6 KB
references/research-requirements.md1.3 KB
rules/scientific-skills.md1.0 KB
schemas/input.schema.json591 B
schemas/output.schema.json432 B
scripts/main.cjs630 B
skills/adaptyv/commands/adaptyv.md96 B
skills/adaptyv/hooks/post-execute.cjs118 B
skills/adaptyv/hooks/pre-execute.cjs115 B
skills/adaptyv/reference/api_reference.md6.5 KB
skills/adaptyv/reference/examples.md22.6 KB
skills/adaptyv/reference/experiments.md9.7 KB
skills/adaptyv/reference/protein_optimization.md17.5 KB
skills/adaptyv/references/research-requirements.md120 B
skills/adaptyv/rules/adaptyv.md124 B
skills/adaptyv/schemas/input.schema.json279 B
skills/adaptyv/schemas/output.schema.json278 B
skills/adaptyv/scripts/main.cjs146 B
skills/adaptyv/SKILL.md4.6 KB
skills/adaptyv/templates/implementation-template.md71 B
skills/aeon/commands/aeon.md90 B
skills/aeon/hooks/post-execute.cjs118 B
skills/aeon/hooks/pre-execute.cjs115 B
skills/aeon/references/anomaly_detection.md4.8 KB
skills/aeon/references/classification.md5.3 KB
skills/aeon/references/clustering.md3.7 KB
skills/aeon/references/datasets_benchmarking.md8.7 KB
skills/aeon/references/distances.md6.4 KB
skills/aeon/references/forecasting.md3.8 KB
skills/aeon/references/networks.md7.7 KB
skills/aeon/references/regression.md3.9 KB
skills/aeon/references/research-requirements.md120 B
skills/aeon/references/segmentation.md4.8 KB
skills/aeon/references/similarity_search.md5.1 KB
skills/aeon/references/transformations.md7.6 KB
skills/aeon/rules/aeon.md121 B
skills/aeon/schemas/input.schema.json276 B
skills/aeon/schemas/output.schema.json275 B
skills/aeon/scripts/main.cjs143 B
skills/aeon/SKILL.md11.3 KB
skills/aeon/templates/implementation-template.md68 B
skills/alphafold-database/commands/alphafold-database.md118 B
skills/alphafold-database/hooks/post-execute.cjs118 B
skills/alphafold-database/hooks/pre-execute.cjs115 B
skills/alphafold-database/references/api_reference.md12.7 KB
skills/alphafold-database/references/research-requirements.md120 B
skills/alphafold-database/rules/alphafold-database.md135 B
skills/alphafold-database/schemas/input.schema.json290 B
skills/alphafold-database/schemas/output.schema.json289 B
skills/alphafold-database/scripts/main.cjs157 B
skills/alphafold-database/SKILL.md17.0 KB
skills/alphafold-database/templates/implementation-template.md82 B
skills/anndata/commands/anndata.md96 B
skills/anndata/hooks/post-execute.cjs118 B
skills/anndata/hooks/pre-execute.cjs115 B
skills/anndata/references/best_practices.md11.9 KB
skills/anndata/references/concatenation.md10.3 KB
skills/anndata/references/data_structure.md8.6 KB
skills/anndata/references/io_operations.md9.3 KB
skills/anndata/references/manipulation.md11.6 KB
skills/anndata/references/research-requirements.md120 B
skills/anndata/rules/anndata.md124 B
skills/anndata/schemas/input.schema.json279 B
skills/anndata/schemas/output.schema.json278 B
skills/anndata/scripts/main.cjs146 B
skills/anndata/SKILL.md10.9 KB
skills/anndata/templates/implementation-template.md71 B
skills/arboreto/commands/arboreto.md98 B
skills/arboreto/hooks/post-execute.cjs118 B
skills/arboreto/hooks/pre-execute.cjs115 B
skills/arboreto/references/algorithms.md4.6 KB
skills/arboreto/references/basic_inference.md3.9 KB
skills/arboreto/references/distributed_computing.md6.6 KB
skills/arboreto/references/research-requirements.md120 B
skills/arboreto/rules/arboreto.md125 B
skills/arboreto/schemas/input.schema.json280 B
skills/arboreto/schemas/output.schema.json279 B
skills/arboreto/scripts/basic_grn_inference.py2.9 KB
skills/arboreto/scripts/main.cjs147 B
skills/arboreto/SKILL.md7.8 KB
skills/arboreto/templates/implementation-template.md72 B
skills/astropy/commands/astropy.md96 B
skills/astropy/hooks/post-execute.cjs118 B
skills/astropy/hooks/pre-execute.cjs115 B
skills/astropy/references/coordinates.md6.9 KB
skills/astropy/references/cosmology.md6.3 KB
skills/astropy/references/fits.md8.5 KB
skills/astropy/references/research-requirements.md120 B
skills/astropy/references/tables.md9.2 KB
skills/astropy/references/time.md8.9 KB
skills/astropy/references/units.md3.7 KB
skills/astropy/references/wcs_and_other_modules.md8.3 KB
skills/astropy/rules/astropy.md124 B
skills/astropy/schemas/input.schema.json279 B
skills/astropy/schemas/output.schema.json278 B
skills/astropy/scripts/main.cjs146 B
skills/astropy/SKILL.md12.2 KB
skills/astropy/templates/implementation-template.md71 B
skills/benchling-integration/commands/benchling-integration.md124 B
skills/benchling-integration/hooks/post-execute.cjs118 B
skills/benchling-integration/hooks/pre-execute.cjs115 B
skills/benchling-integration/references/api_endpoints.md13.9 KB
skills/benchling-integration/references/authentication.md9.9 KB
skills/benchling-integration/references/research-requirements.md120 B
skills/benchling-integration/references/sdk_reference.md17.2 KB
skills/benchling-integration/rules/benchling-integration.md138 B
skills/benchling-integration/schemas/input.schema.json293 B
skills/benchling-integration/schemas/output.schema.json292 B
skills/benchling-integration/scripts/main.cjs160 B
skills/benchling-integration/SKILL.md13.7 KB
skills/benchling-integration/templates/implementation-template.md85 B
skills/biopython/commands/biopython.md100 B
skills/biopython/hooks/post-execute.cjs118 B
skills/biopython/hooks/pre-execute.cjs115 B
skills/biopython/references/advanced.md13.7 KB
skills/biopython/references/alignment.md8.7 KB
skills/biopython/references/blast.md12.4 KB
skills/biopython/references/databases.md11.2 KB
skills/biopython/references/phylogenetics.md13.5 KB
skills/biopython/references/research-requirements.md120 B
skills/biopython/references/sequence_io.md7.1 KB
skills/biopython/references/structure.md12.7 KB
skills/biopython/rules/biopython.md126 B
skills/biopython/schemas/input.schema.json281 B
skills/biopython/schemas/output.schema.json280 B
skills/biopython/scripts/main.cjs148 B
skills/biopython/SKILL.md14.5 KB
skills/biopython/templates/implementation-template.md73 B
skills/biorxiv-database/commands/biorxiv-database.md114 B
skills/biorxiv-database/hooks/post-execute.cjs118 B
skills/biorxiv-database/hooks/pre-execute.cjs115 B
skills/biorxiv-database/references/api_reference.md6.9 KB
skills/biorxiv-database/references/research-requirements.md120 B
skills/biorxiv-database/rules/biorxiv-database.md133 B
skills/biorxiv-database/schemas/input.schema.json288 B
skills/biorxiv-database/schemas/output.schema.json287 B
skills/biorxiv-database/scripts/biorxiv_search.py15.1 KB
skills/biorxiv-database/scripts/main.cjs155 B
skills/biorxiv-database/SKILL.md13.2 KB
skills/biorxiv-database/templates/implementation-template.md80 B
skills/bioservices/commands/bioservices.md104 B
skills/bioservices/hooks/post-execute.cjs118 B
skills/bioservices/hooks/pre-execute.cjs115 B
skills/bioservices/references/identifier_mapping.md18.2 KB
skills/bioservices/references/research-requirements.md120 B
skills/bioservices/references/services_reference.md12.3 KB
skills/bioservices/references/workflow_patterns.md19.7 KB
skills/bioservices/rules/bioservices.md128 B
skills/bioservices/schemas/input.schema.json283 B
skills/bioservices/schemas/output.schema.json282 B
skills/bioservices/scripts/batch_id_converter.py10.6 KB
skills/bioservices/scripts/compound_cross_reference.py11.0 KB
skills/bioservices/scripts/main.cjs150 B
skills/bioservices/scripts/pathway_analysis.py9.3 KB
skills/bioservices/scripts/protein_analysis_workflow.py12.2 KB
skills/bioservices/SKILL.md10.7 KB
skills/bioservices/templates/implementation-template.md75 B
skills/brenda-database/commands/brenda-database.md112 B
skills/brenda-database/hooks/post-execute.cjs118 B
skills/brenda-database/hooks/pre-execute.cjs115 B
skills/brenda-database/references/api_reference.md15.5 KB
skills/brenda-database/references/research-requirements.md120 B
skills/brenda-database/rules/brenda-database.md132 B
skills/brenda-database/schemas/input.schema.json287 B
skills/brenda-database/schemas/output.schema.json286 B
skills/brenda-database/scripts/brenda_queries.py30.2 KB
skills/brenda-database/scripts/brenda_visualization.py28.7 KB
skills/brenda-database/scripts/enzyme_pathway_builder.py43.8 KB
skills/brenda-database/scripts/main.cjs154 B
skills/brenda-database/SKILL.md22.6 KB
skills/brenda-database/templates/implementation-template.md79 B
skills/cellxgene-census/commands/cellxgene-census.md114 B
skills/cellxgene-census/hooks/post-execute.cjs118 B
skills/cellxgene-census/hooks/pre-execute.cjs115 B
skills/cellxgene-census/references/census_schema.md5.6 KB
skills/cellxgene-census/references/common_patterns.md9.7 KB
skills/cellxgene-census/references/research-requirements.md120 B
skills/cellxgene-census/rules/cellxgene-census.md133 B
skills/cellxgene-census/schemas/input.schema.json288 B
skills/cellxgene-census/schemas/output.schema.json287 B
skills/cellxgene-census/scripts/main.cjs155 B
skills/cellxgene-census/SKILL.md16.0 KB
skills/cellxgene-census/templates/implementation-template.md80 B
skills/chembl-database/commands/chembl-database.md112 B
skills/chembl-database/hooks/post-execute.cjs118 B
skills/chembl-database/hooks/pre-execute.cjs115 B
skills/chembl-database/references/api_reference.md6.7 KB
skills/chembl-database/references/research-requirements.md120 B
skills/chembl-database/rules/chembl-database.md132 B
skills/chembl-database/schemas/input.schema.json287 B
skills/chembl-database/schemas/output.schema.json286 B
skills/chembl-database/scripts/example_queries.py7.0 KB
skills/chembl-database/scripts/main.cjs154 B
skills/chembl-database/SKILL.md11.0 KB
skills/chembl-database/templates/implementation-template.md79 B
skills/cirq/commands/cirq.md90 B

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Claude Scientific Skills

Overview

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.

When to Use

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

Quick Start

// 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

Skill Categories

Scientific Databases (28+)

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

Python Analysis Libraries (55+)

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

Bioinformatics & Genomics

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

Cheminformatics & Drug Discovery

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

Scientific Communication

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

Clinical & Medical

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

Laboratory & Integration

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

Core Workflows

Literature Review Workflow

# 7-phase systematic literature review
# 1. Planning with PICO framework
# 2. Multi-database search execution
# 3. Screening with PRISMA flow
# 4. Data extraction and quality assessment
# 5. Thematic synthesis
# 6. Citation verification
# 7. PDF generation

Drug Discovery Workflow

# Using RDKit + ChEMBL + datamol
from rdkit import Chem
from rdkit.Chem import Descriptors, AllChem

# 1. Query ChEMBL for bioactivity data
# 2. Calculate molecular properties
# 3. Filter by drug-likeness (Lipinski)
# 4. Similarity screening
# 5. Substructure analysis

Single-Cell Analysis Workflow

# Using scanpy + anndata
import scanpy as sc

# 1. Load and QC data
# 2. Normalization and feature selection
# 3. Dimensionality reduction (PCA, UMAP)
# 4. Clustering (Leiden algorithm)
# 5. Marker gene identification
# 6. Cell type annotation

Hypothesis Generation Workflow

# 8-step systematic process
# 1. Understand phenomenon
# 2. Literature search
# 3. Synthesize evidence
# 4. Generate competing hypotheses
# 5. Evaluate quality
# 6. Design experiments
# 7. Formulate predictions
# 8. Generate report

Sub-Skill Structure

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)

Invoking Sub-Skills

Direct Invocation

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

Chained Workflows

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

Prerequisites

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

Best Practices

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

Integration with Agent Framework

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

Example Agent Spawn

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.

## Task
Analyze the molecular dataset for drug-likeness properties.

## Skills to Invoke
1. Skill({ skill: "scientific-skills/rdkit" })
2. Skill({ skill: "scientific-skills/datamol" })

## Workflow
1. Load molecular data
2. Calculate descriptors
3. Apply Lipinski filters
4. Generate visualization
5. Report findings
`,
});

Resources

Bundled Documentation

skills/*/SKILL.md - Individual skill documentation
skills/*/references/ - API references and patterns
skills/*/scripts/ - Example scripts and templates

External Resources

Iron Laws

ALWAYS query scientific databases (PubMed, ChEMBL, UniProt) before performing any analysis — raw analysis without literature and database context produces uninformed conclusions that duplicate prior work.
NEVER perform analysis without documenting all steps (data sources, parameters, library versions, transformations) — undocumented research is irreproducible and cannot be peer-reviewed or extended.
ALWAYS chain multiple domain-specific skills for complex workflows — single-tool analysis misses interdependencies across biology, chemistry, and clinical domains.
NEVER report findings without statistical validation — scientific claims require appropriately sized samples, validated methods, and quantified uncertainty.
ALWAYS visualize intermediate results after each major processing step — data errors and outliers surface in visualizations before propagating silently to final conclusions.

Anti-Patterns

Anti-Pattern	Why It Fails	Correct Approach
Performing analysis without querying databases first	Missing context from existing literature duplicates known work and misses prior art	Query PubMed/ChEMBL/UniProt before analysis to ground work in existing scientific knowledge
Using a single tool for complex multi-domain analysis	Single-tool analysis misses domain boundary interdependencies	Chain multiple domain-specific skills (rdkit for chemistry, scanpy for single-cell, biopython for genomics)
Skipping intermediate visualization during data processing	Errors and outliers propagate silently from preprocessing to final results	Visualize data distribution and quality metrics after each major transformation step
Generating hypotheses without reviewing existing literature	Reinvents known solutions and ignores contradictory prior findings	Always invoke literature-review skill first; only generate hypotheses after reviewing existing evidence
Reporting findings without documenting analysis provenance	Research cannot be reproduced, verified, or extended by other researchers	Log all data sources, version numbers, parameters, and transformation steps in the research report

Memory Protocol (MANDATORY)

Before starting: Read .claude/context/memory/learnings.md

After completing:

New pattern → .claude/context/memory/learnings.md
Issue found → .claude/context/memory/issues.md
Decision made → .claude/context/memory/decisions.md

ASSUME INTERRUPTION: If it's not in memory, it didn't happen.

Version History

v2.17.0 - Current version with 139 skills
Integrated from K-Dense-AI/claude-scientific-skills repository

License

MIT License - Open source and freely available for research and commercial use.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

ログインしてレビューを書く

同じリポジトリのスキル

概要と使いどころ

accessibility

無料

Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.

日本語の概要は準備中です。原文の説明を表示しています。