mirror of
https://github.com/K-Dense-AI/claude-scientific-skills.git
synced 2026-03-27 07:09:27 +08:00
Added around 23 new skills contributed by the community!
This commit is contained in:
Timothy Kassis
76
README.md
76
README.md
@@ -1,12 +1,12 @@
|
||||
# Claude Scientific Skills
|
||||
|
||||
[](LICENSE.md)
|
||||
[](#whats-included)
|
||||
[](#whats-included)
|
||||
[](#whats-included)
|
||||
[](https://agentskills.io/)
|
||||
[](#getting-started)
|
||||
|
||||
A comprehensive collection of **148+ ready-to-use scientific and research skills** (now including financial/SEC research, U.S. Treasury fiscal data, OFR Hedge Fund Monitor, and Alpha Vantage market data) for any AI agent that supports the open [Agent Skills](https://agentskills.io/) standard, created by [K-Dense](https://k-dense.ai). Works with **Cursor, Claude Code, Codex, and more**. Transform your AI agent into a research assistant capable of executing complex multi-step scientific workflows across biology, chemistry, medicine, and beyond.
|
||||
A comprehensive collection of **170+ ready-to-use scientific and research skills** (now including cancer genomics, drug-target binding, molecular dynamics, RNA velocity, geospatial science, time series forecasting, FRED economic data, and more) for any AI agent that supports the open [Agent Skills](https://agentskills.io/) standard, created by [K-Dense](https://k-dense.ai). Works with **Cursor, Claude Code, Codex, and more**. Transform your AI agent into a research assistant capable of executing complex multi-step scientific workflows across biology, chemistry, medicine, and beyond.
|
||||
|
||||
<p align="center">
|
||||
<a href="https://k-dense.ai">
|
||||
@@ -46,12 +46,12 @@ These skills enable your AI agent to seamlessly work with specialized scientific
|
||||
|
||||
## 📦 What's Included
|
||||
|
||||
This repository provides **148 scientific and research skills** organized into the following categories:
|
||||
This repository provides **170 scientific and research skills** organized into the following categories:
|
||||
|
||||
- **250+ Scientific & Financial Databases** - Collectively, these skills provide access to over 250 databases and data sources. Dedicated skills cover PubMed, ChEMBL, UniProt, COSMIC, ClinicalTrials.gov, SEC EDGAR, Alpha Vantage, and more; multi-database packages like BioServices (~40 bioinformatics services + 30+ PSICQUIC interaction databases), BioPython (38 NCBI sub-databases via Entrez), and gget (20+ genomics databases) account for the rest
|
||||
- **55+ Optimized Python Package Skills** - Explicitly defined skills for RDKit, Scanpy, PyTorch Lightning, scikit-learn, BioPython, pyzotero, BioServices, PennyLane, Qiskit, and others — with curated documentation, examples, and best practices. Note: the agent can write code using *any* Python package, not just these; these skills simply provide stronger, more reliable performance for the packages listed
|
||||
- **60+ Optimized Python Package Skills** - Explicitly defined skills for RDKit, Scanpy, PyTorch Lightning, scikit-learn, BioPython, pyzotero, BioServices, PennyLane, Qiskit, OpenMM, MDAnalysis, scVelo, TimesFM, and others — with curated documentation, examples, and best practices. Note: the agent can write code using *any* Python package, not just these; these skills simply provide stronger, more reliable performance for the packages listed
|
||||
- **15+ Scientific Integration Skills** - Explicitly defined skills for Benchling, DNAnexus, LatchBio, OMERO, Protocols.io, and more. Again, the agent is not limited to these — any API or platform reachable from Python is fair game; these skills are the optimized, pre-documented paths
|
||||
- **30+ Analysis & Communication Tools** - Literature review, scientific writing, peer review, document processing, posters, slides, schematics, and more
|
||||
- **35+ Analysis & Communication Tools** - Literature review, scientific writing, peer review, document processing, posters, slides, schematics, infographics, Mermaid diagrams, and more
|
||||
- **10+ Research & Clinical Tools** - Hypothesis generation, grant writing, clinical decision support, treatment plans, regulatory compliance
|
||||
|
||||
Each skill includes:
|
||||
@@ -91,9 +91,9 @@ Each skill includes:
|
||||
- **Multi-Step Workflows** - Execute complex pipelines with a single prompt
|
||||
|
||||
### 🎯 **Comprehensive Coverage**
|
||||
- **148 Skills** - Extensive coverage across all major scientific domains
|
||||
- **170 Skills** - Extensive coverage across all major scientific domains
|
||||
- **250+ Databases** - Collective access to 250+ databases and data sources spanning genomics, chemistry, clinical, financial, and more — through dedicated database skills and multi-database packages like BioServices, BioPython, and gget
|
||||
- **55+ Optimized Python Package Skills** - RDKit, Scanpy, PyTorch Lightning, scikit-learn, BioServices, PennyLane, Qiskit, and others (the agent can use any Python package; these are the pre-documented, higher-performing paths)
|
||||
- **60+ Optimized Python Package Skills** - RDKit, Scanpy, PyTorch Lightning, scikit-learn, BioServices, PennyLane, Qiskit, OpenMM, scVelo, TimesFM, and others (the agent can use any Python package; these are the pre-documented, higher-performing paths)
|
||||
|
||||
### 🔧 **Easy Integration**
|
||||
- **Simple Setup** - Copy skills to your skills directory and start working
|
||||
@@ -331,7 +331,7 @@ If so, **[K-Dense Web](https://k-dense.ai)** was built for you. It is the full A
|
||||
|
||||
| Feature | This Repo | K-Dense Web |
|
||||
|---------|-----------|-------------|
|
||||
| Scientific Skills | 148 skills | **200+ skills** (exclusive access) |
|
||||
| Scientific Skills | 170 skills | **200+ skills** (exclusive access) |
|
||||
| Setup | Manual installation | **Zero setup, works instantly** |
|
||||
| Compute | Your machine | **Cloud GPUs and HPC included** |
|
||||
| Workflows | Prompt and code | **End-to-end research pipelines** |
|
||||
@@ -394,31 +394,36 @@ If so, **[K-Dense Web](https://k-dense.ai)** was built for you. It is the full A
|
||||
|
||||
## 📚 Available Skills
|
||||
|
||||
This repository contains **148 scientific and research skills** organized across multiple domains. Each skill provides comprehensive documentation, code examples, and best practices for working with scientific libraries, databases, and tools.
|
||||
This repository contains **170 scientific and research skills** organized across multiple domains. Each skill provides comprehensive documentation, code examples, and best practices for working with scientific libraries, databases, and tools.
|
||||
|
||||
### Skill Categories
|
||||
|
||||
> **Note:** The Python package and integration skills listed below are *explicitly defined* skills — curated with documentation, examples, and best practices for stronger, more reliable performance. They are not a ceiling: the agent can install and use *any* Python package or call *any* API, even without a dedicated skill. The skills listed simply make common workflows faster and more dependable.
|
||||
|
||||
#### 🧬 **Bioinformatics & Genomics** (16+ skills)
|
||||
#### 🧬 **Bioinformatics & Genomics** (20+ skills)
|
||||
- Sequence analysis: BioPython, pysam, scikit-bio, BioServices
|
||||
- Single-cell analysis: Scanpy, AnnData, scvi-tools, Arboreto, Cellxgene Census
|
||||
- Single-cell analysis: Scanpy, AnnData, scvi-tools, scVelo (RNA velocity), Arboreto, Cellxgene Census
|
||||
- Genomic tools: gget, geniml, gtars, deepTools, FlowIO, Zarr, TileDB-VCF
|
||||
- Phylogenetics: ETE Toolkit
|
||||
- Phylogenetics: ETE Toolkit, Phylogenetics (MAFFT, IQ-TREE 2, FastTree)
|
||||
|
||||
#### 🧪 **Cheminformatics & Drug Discovery** (11+ skills)
|
||||
#### 🧪 **Cheminformatics & Drug Discovery** (13+ skills)
|
||||
- Molecular manipulation: RDKit, Datamol, Molfeat
|
||||
- Deep learning: DeepChem, TorchDrug
|
||||
- Docking & screening: DiffDock
|
||||
- Molecular dynamics: OpenMM + MDAnalysis (MD simulation & trajectory analysis)
|
||||
- Cloud quantum chemistry: Rowan (pKa, docking, cofolding)
|
||||
- Drug-likeness: MedChem
|
||||
- Binding affinities: BindingDB (Ki, Kd, IC50, EC50 for drug-target pairs)
|
||||
- Benchmarks: PyTDC
|
||||
|
||||
#### 🔬 **Proteomics & Mass Spectrometry** (2 skills)
|
||||
- Spectral processing: matchms, pyOpenMS
|
||||
|
||||
#### 🏥 **Clinical Research & Precision Medicine** (12+ skills)
|
||||
#### 🏥 **Clinical Research & Precision Medicine** (16+ skills)
|
||||
- Clinical databases: ClinicalTrials.gov, ClinVar, ClinPGx, COSMIC, FDA Databases
|
||||
- Cancer genomics: cBioPortal (somatic mutations, CNAs, expression, survival across 400+ studies), DepMap (cancer dependency scores, drug sensitivity)
|
||||
- Disease-gene associations: Monarch Initiative (OMIM, ORPHANET, HPO, ClinVar, model organism data)
|
||||
- Cancer imaging: NCI Imaging Data Commons (radiology & pathology datasets via idc-index)
|
||||
- Healthcare AI: PyHealth, NeuroKit2, Clinical Decision Support
|
||||
- Clinical documentation: Clinical Reports, Treatment Plans
|
||||
- Variant analysis: Ensembl, NCBI Gene
|
||||
@@ -430,10 +435,10 @@ This repository contains **148 scientific and research skills** organized across
|
||||
#### 🧠 **Neuroscience & Electrophysiology** (1 skill)
|
||||
- Neural recordings: Neuropixels-Analysis (extracellular spikes, silicon probes, spike sorting)
|
||||
|
||||
#### 🤖 **Machine Learning & AI** (15+ skills)
|
||||
#### 🤖 **Machine Learning & AI** (16+ skills)
|
||||
- Deep learning: PyTorch Lightning, Transformers, Stable Baselines3, PufferLib
|
||||
- Classical ML: scikit-learn, scikit-survival, SHAP
|
||||
- Time series: aeon
|
||||
- Time series: aeon, TimesFM (Google's zero-shot foundation model for univariate forecasting)
|
||||
- Bayesian methods: PyMC
|
||||
- Optimization: PyMOO
|
||||
- Graph ML: Torch Geometric
|
||||
@@ -452,12 +457,14 @@ This repository contains **148 scientific and research skills** organized across
|
||||
- Discrete-event simulation: SimPy
|
||||
- Data processing: Dask, Polars, Vaex
|
||||
|
||||
#### 📊 **Data Analysis & Visualization** (14+ skills)
|
||||
#### 📊 **Data Analysis & Visualization** (17+ skills)
|
||||
- Visualization: Matplotlib, Seaborn, Plotly, Scientific Visualization
|
||||
- Geospatial analysis: GeoPandas
|
||||
- Geospatial analysis: GeoPandas, GeoMaster (remote sensing, GIS, satellite imagery, spatial ML, 500+ examples)
|
||||
- Network analysis: NetworkX
|
||||
- Symbolic math: SymPy
|
||||
- Document processing: Document Skills (PDF, DOCX, PPTX, XLSX)
|
||||
- Infographics: Infographics (AI-powered professional infographic creation)
|
||||
- Diagrams: Markdown & Mermaid Writing (text-based diagrams as default documentation standard)
|
||||
- Data access: Data Commons
|
||||
- Exploratory data analysis: EDA workflows
|
||||
- Statistical analysis: Statistical Analysis workflows
|
||||
@@ -473,28 +480,33 @@ This repository contains **148 scientific and research skills** organized across
|
||||
- Multi-omics: Denario, HypoGeniC
|
||||
- Data management: LaminDB
|
||||
|
||||
#### 🧬 **Protein Engineering & Design** (2 skills)
|
||||
#### 🧬 **Protein Engineering & Design** (3 skills)
|
||||
- Protein language models: ESM
|
||||
- Glycoengineering: Glycoengineering (N/O-glycosylation prediction, therapeutic antibody optimization)
|
||||
- Cloud laboratory platform: Adaptyv (automated protein testing and validation)
|
||||
|
||||
#### 📚 **Scientific Communication** (20+ skills)
|
||||
#### 📚 **Scientific Communication** (24+ skills)
|
||||
- Literature: OpenAlex, PubMed, bioRxiv, Literature Review
|
||||
- Web search: Perplexity Search (AI-powered search with real-time information)
|
||||
- Advanced paper search: BGPT Paper Search (25+ structured fields per paper — methods, results, sample sizes, quality scores — from full text, not just abstracts)
|
||||
- Web search: Perplexity Search (AI-powered search with real-time information), Parallel Web (synthesized summaries with citations)
|
||||
- Research notebooks: Open Notebook (self-hosted NotebookLM alternative — PDFs, videos, audio, web pages; 16+ AI providers; multi-speaker podcast generation)
|
||||
- Writing: Scientific Writing, Peer Review
|
||||
- Document processing: XLSX, MarkItDown, Document Skills
|
||||
- Publishing: Paper-2-Web, Venue Templates
|
||||
- Presentations: Scientific Slides, LaTeX Posters, PPTX Posters
|
||||
- Diagrams: Scientific Schematics
|
||||
- Diagrams: Scientific Schematics, Markdown & Mermaid Writing
|
||||
- Infographics: Infographics (10 types, 8 styles, colorblind-safe palettes)
|
||||
- Citations: Citation Management
|
||||
- Illustration: Generate Image (AI image generation with FLUX.2 Pro and Gemini 3 Pro (Nano Banana Pro))
|
||||
|
||||
#### 🔬 **Scientific Databases** (28+ dedicated skills → 250+ databases total)
|
||||
> These 28+ skills each provide direct, optimized access to a named database. Collectively, however, these skills unlock **250+ databases and data sources** — multi-database packages like BioServices (~40 bioinformatics services + 30+ PSICQUIC interaction databases), BioPython (38 NCBI sub-databases via Entrez), and gget (20+ genomics databases) add far more coverage beyond what's listed here.
|
||||
- Protein: UniProt, PDB, AlphaFold DB
|
||||
- Chemical: PubChem, ChEMBL, DrugBank, ZINC, HMDB
|
||||
- Genomic: Ensembl, NCBI Gene, GEO, ENA, GWAS Catalog
|
||||
#### 🔬 **Scientific Databases** (37+ dedicated skills → 250+ databases total)
|
||||
> These 37+ skills each provide direct, optimized access to a named database. Collectively, however, these skills unlock **250+ databases and data sources** — multi-database packages like BioServices (~40 bioinformatics services + 30+ PSICQUIC interaction databases), BioPython (38 NCBI sub-databases via Entrez), and gget (20+ genomics databases) add far more coverage beyond what's listed here.
|
||||
- Protein: UniProt, PDB, AlphaFold DB, InterPro (protein families, domains, Pfam, PANTHER, SMART + 11 others)
|
||||
- Chemical: PubChem, ChEMBL, DrugBank, ZINC, HMDB, BindingDB (drug-target binding affinities)
|
||||
- Genomic: Ensembl, NCBI Gene, GEO, ENA, GWAS Catalog, gnomAD (population allele frequencies, pLI/LOEUF), GTEx (tissue-specific expression, eQTLs), JASPAR (transcription factor binding site profiles)
|
||||
- Literature: bioRxiv (preprints)
|
||||
- Clinical: ClinVar, COSMIC, ClinicalTrials.gov, ClinPGx, FDA Databases
|
||||
- Clinical: ClinVar, COSMIC, ClinicalTrials.gov, ClinPGx, FDA Databases, cBioPortal (cancer genomics), DepMap (cancer cell line dependencies), Monarch Initiative (rare disease, HPO, cross-species)
|
||||
- Imaging: NCI Imaging Data Commons (radiology & pathology datasets)
|
||||
- Pathways: KEGG, Reactome, STRING
|
||||
- Targets: Open Targets
|
||||
- Metabolomics: Metabolomics Workbench
|
||||
@@ -508,9 +520,12 @@ This repository contains **148 scientific and research skills** organized across
|
||||
- Automation: Opentrons
|
||||
- Resource detection: Get Available Resources
|
||||
|
||||
#### 🎓 **Research Methodology & Planning** (8+ skills)
|
||||
#### 🎓 **Research Methodology & Planning** (11+ skills)
|
||||
- Ideation: Scientific Brainstorming, Hypothesis Generation
|
||||
- Critical analysis: Scientific Critical Thinking, Scholar Evaluation
|
||||
- Scenario analysis: What-If Oracle (multi-branch possibility exploration, risk analysis, strategic options)
|
||||
- Multi-perspective deliberation: Consciousness Council (diverse expert viewpoints, devil's advocate analysis)
|
||||
- Cognitive profiling: DHDNA Profiler (extract thinking patterns and cognitive signatures from any text)
|
||||
- Funding: Research Grants
|
||||
- Discovery: Research Lookup
|
||||
- Market analysis: Market Research Reports
|
||||
@@ -518,9 +533,10 @@ This repository contains **148 scientific and research skills** organized across
|
||||
#### ⚖️ **Regulatory & Standards** (1 skill)
|
||||
- Medical device standards: ISO 13485 Certification
|
||||
|
||||
#### 💹 **Financial & SEC Research** (4 skills)
|
||||
#### 💹 **Financial & SEC Research** (5 skills)
|
||||
- SEC filings & financial data: edgartools (10-K, 10-Q, 8-K, 13F, Form 4, XBRL, insider trading, institutional holdings)
|
||||
- U.S. federal fiscal data: usfiscaldata (national debt, Daily/Monthly Treasury Statements, Treasury auctions, interest rates, exchange rates, savings bonds)
|
||||
- Macroeconomic data: FRED (800,000+ economic time series from 100+ sources — GDP, unemployment, inflation, housing, regional data via Federal Reserve Economic Data API)
|
||||
- Hedge fund systemic risk: hedgefundmonitor (OFR Hedge Fund Monitor API — Form PF aggregated stats, CFTC futures positioning, FICC sponsored repo, SCOOS dealer financing)
|
||||
- Global market data: alpha-vantage (real-time & historical stocks, options, forex, crypto, commodities, economic indicators, 50+ technical indicators via Alpha Vantage API)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user