diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json index f62645c..d969712 100644 --- a/.claude-plugin/marketplace.json +++ b/.claude-plugin/marketplace.json @@ -6,7 +6,7 @@ }, "metadata": { "description": "Claude scientific skills from K-Dense Inc", - "version": "2.13.0" + "version": "2.15.0" }, "plugins": [ { diff --git a/docs/examples.md b/docs/examples.md index 8ef53e0..8486c09 100644 --- a/docs/examples.md +++ b/docs/examples.md @@ -26,6 +26,9 @@ This document provides comprehensive, practical examples demonstrating how to co 18. [Experimental Physics & Data Analysis](#experimental-physics--data-analysis) 19. [Chemical Engineering & Process Optimization](#chemical-engineering--process-optimization) 20. [Scientific Illustration & Visual Communication](#scientific-illustration--visual-communication) +21. [Quantum Computing for Chemistry](#quantum-computing-for-chemistry) +22. [Research Grant Writing](#research-grant-writing) +23. [Flow Cytometry & Immunophenotyping](#flow-cytometry--immunophenotyping) --- @@ -40,12 +43,16 @@ This document provides comprehensive, practical examples demonstrating how to co - `pubchem-database` - Search compound libraries - `rdkit` - Analyze molecular properties - `datamol` - Generate analogs +- `medchem` - Medicinal chemistry filters +- `molfeat` - Molecular featurization - `diffdock` - Molecular docking - `alphafold-database` - Retrieve protein structure - `pubmed-database` - Literature review - `cosmic-database` - Query mutations - `deepchem` - Property prediction +- `torchdrug` - Graph neural networks for molecules - `scientific-visualization` - Create figures +- `clinical-reports` - Generate PDF reports **Workflow**: @@ -135,7 +142,10 @@ Expected Output: - `clinicaltrials-database` - Check ongoing trials - `fda-database` - Drug approvals and safety - `networkx` - Network analysis +- `bioservices` - Biological database queries - `literature-review` - Systematic review +- `openalex-database` - Academic literature search +- `biorxiv-database` - Preprint search **Workflow**: @@ -213,15 +223,17 @@ Expected Output: **Skills Used**: - `pysam` - Parse VCF files - `ensembl-database` - Variant annotation +- `gget` - Unified gene/protein data retrieval - `clinvar-database` - Clinical significance - `cosmic-database` - Somatic mutations - `gene-database` - Gene information - `uniprot-database` - Protein impact +- `clinpgx-database` - Pharmacogenomics data - `drugbank-database` - Drug-gene associations - `clinicaltrials-database` - Matching trials - `opentargets-database` - Target validation - `pubmed-database` - Literature evidence -- `reportlab` - Generate clinical report +- `clinical-reports` - Generate clinical report PDF **Workflow**: @@ -297,7 +309,7 @@ Step 12: Generate clinical genomics report - Clinical trial options with eligibility information - Prognostic implications based on mutation profile - References to guidelines (NCCN, ESMO, AMP/ASCO/CAP) -- Generate professional PDF using ReportLab +- Generate professional PDF using clinical-reports skill Expected Output: - Annotated variant list with clinical significance @@ -318,11 +330,14 @@ Expected Output: - `scanpy` - Clustering and visualization - `scikit-learn` - Machine learning classification - `gene-database` - Gene annotation +- `gget` - Gene data retrieval - `reactome-database` - Pathway analysis - `opentargets-database` - Drug targets - `pubmed-database` - Literature validation - `matplotlib` - Visualization - `seaborn` - Heatmaps +- `plotly` - Interactive visualization +- `scikit-survival` - Survival analysis **Workflow**: @@ -412,11 +427,14 @@ Expected Output: - `scvi-tools` - Batch correction and integration - `cellxgene-census` - Reference data - `gene-database` - Cell type markers +- `gget` - Gene data retrieval - `anndata` - Data structure - `arboreto` - Gene regulatory networks - `pytorch-lightning` - Deep learning - `matplotlib` - Visualization +- `plotly` - Interactive visualization - `statistical-analysis` - Hypothesis testing +- `geniml` - Genomic ML embeddings **Workflow**: @@ -526,12 +544,14 @@ Expected Output: - `pdb-database` - Experimental structures - `uniprot-database` - Protein information - `biopython` - Structure analysis -- `pyrosetta` - Protein design (if available) +- `esm` - Protein language models and embeddings - `rdkit` - Chemical library generation +- `datamol` - Molecule manipulation - `diffdock` - Molecular docking - `zinc-database` - Screening library - `deepchem` - Property prediction -- `pymol` - Visualization (external) +- `scientific-visualization` - Structure visualization +- `medchem` - Medicinal chemistry filters **Workflow**: @@ -638,7 +658,9 @@ Expected Output: **Skills Used**: - `rdkit` - Molecular descriptors +- `medchem` - Toxicophore detection - `deepchem` - Toxicity prediction +- `pytdc` - Therapeutics data commons - `chembl-database` - Toxicity data - `pubchem-database` - Bioassay data - `drugbank-database` - Known drug toxicities @@ -646,6 +668,7 @@ Expected Output: - `hmdb-database` - Metabolite prediction - `scikit-learn` - Classification models - `shap` - Model interpretability +- `clinical-reports` - Safety assessment reports **Workflow**: @@ -769,12 +792,15 @@ Expected Output: - `clinicaltrials-database` - Trial registry - `fda-database` - Drug approvals - `pubmed-database` - Published results +- `openalex-database` - Academic literature - `drugbank-database` - Approved drugs - `opentargets-database` - Target validation - `polars` - Data manipulation - `matplotlib` - Visualization - `seaborn` - Statistical plots -- `reportlab` - Report generation +- `plotly` - Interactive plots +- `clinical-reports` - Report generation +- `market-research-reports` - Competitive intelligence **Workflow**: @@ -872,7 +898,7 @@ Step 12: Generate competitive intelligence report * Differentiation strategies * Partnership opportunities * Regulatory pathway considerations -- Export as professional PDF with citations and data tables +- Export as professional PDF with citations and data tables using clinical-reports skill Expected Output: - Comprehensive trial database for indication @@ -894,14 +920,17 @@ Expected Output: **Skills Used**: - `pydeseq2` - RNA-seq analysis - `pyopenms` - Mass spectrometry +- `matchms` - Mass spectra matching - `hmdb-database` - Metabolite identification - `metabolomics-workbench-database` - Public datasets - `kegg-database` - Pathway mapping - `reactome-database` - Pathway analysis - `string-database` - Protein interactions +- `cobrapy` - Constraint-based metabolic modeling - `statsmodels` - Multi-omics correlation - `networkx` - Network analysis - `pymc` - Bayesian modeling +- `plotly` - Interactive network visualization **Workflow**: @@ -1011,15 +1040,16 @@ Expected Output: **Objective**: Discover novel solid electrolyte materials for lithium-ion batteries using computational screening. **Skills Used**: -- `pymatgen` - Materials analysis -- `matminer` - Feature engineering +- `pymatgen` - Materials analysis and feature engineering - `scikit-learn` - Machine learning - `pymoo` - Multi-objective optimization -- `ase` - Atomic simulation - `sympy` - Symbolic math - `vaex` - Large dataset handling +- `dask` - Parallel computing - `matplotlib` - Visualization +- `plotly` - Interactive visualization - `scientific-writing` - Report generation +- `scientific-visualization` - Publication figures **Workflow**: @@ -1052,8 +1082,8 @@ Step 4: Calculate material properties with Pymatgen - Ionic radii and bond lengths - Coordination environments -Step 5: Feature engineering with matminer -- Calculate compositional features: +Step 5: Feature engineering with Pymatgen +- Calculate compositional features using Pymatgen's featurizers: * Elemental property statistics (electronegativity, ionic radius) * Valence electron concentrations * Stoichiometric attributes @@ -1095,7 +1125,7 @@ Step 9: Analyze Pareto optimal materials Step 10: Validate predictions with DFT calculations - Select top 10 candidates for detailed study -- Set up DFT calculations (VASP-like, if available via ASE) +- Set up DFT calculations using Pymatgen's interface - Calculate: * Accurate formation energies * Li⁺ migration barriers (NEB calculations) @@ -1142,13 +1172,14 @@ Expected Output: **Skills Used**: - `histolab` - Whole slide image processing - `pathml` - Computational pathology -- `pytorch-lightning` - Deep learning -- `torchvision` - Image models +- `pytorch-lightning` - Deep learning and image models - `scikit-learn` - Model evaluation - `pydicom` - DICOM handling - `omero-integration` - Image management - `matplotlib` - Visualization +- `plotly` - Interactive visualization - `shap` - Model interpretability +- `clinical-reports` - Clinical validation reports **Workflow**: @@ -1264,11 +1295,14 @@ Expected Output: - `pylabrobot` - Lab automation - `opentrons-integration` - Opentrons protocol - `benchling-integration` - Sample tracking +- `labarchive-integration` - Electronic lab notebook - `protocolsio-integration` - Protocol documentation - `simpy` - Process simulation - `polars` - Data processing - `matplotlib` - Plate visualization -- `reportlab` - Report generation +- `plotly` - Interactive plate heatmaps +- `rdkit` - PAINS filtering for hits +- `clinical-reports` - Screening report generation **Workflow**: @@ -1406,11 +1440,14 @@ Expected Output: - `gwas-database` - Public GWAS data - `ensembl-database` - Plant genomics - `gene-database` - Gene annotation -- `scanpy` - Population structure (adapted for genetic data) +- `gget` - Gene data retrieval +- `scanpy` - Population structure analysis - `scikit-learn` - PCA and clustering - `statsmodels` - Association testing +- `statistical-analysis` - Hypothesis testing - `matplotlib` - Manhattan plots - `seaborn` - Visualization +- `plotly` - Interactive visualizations **Workflow**: @@ -1535,14 +1572,16 @@ Expected Output: **Skills Used**: - `neurokit2` - Neurophysiological signal processing -- `nilearn` (external) - Neuroimaging analysis +- `neuropixels-analysis` - Neural data analysis - `scikit-learn` - Classification and clustering - `networkx` - Graph theory analysis - `statsmodels` - Statistical testing +- `statistical-analysis` - Hypothesis testing - `torch_geometric` - Graph neural networks - `pymc` - Bayesian modeling - `matplotlib` - Brain visualization - `seaborn` - Connectivity matrices +- `plotly` - Interactive brain networks **Workflow**: @@ -1675,13 +1714,16 @@ Expected Output: - `biopython` - Sequence processing - `pysam` - BAM file handling - `ena-database` - Sequence data +- `geo-database` - Public datasets - `uniprot-database` - Protein annotation - `kegg-database` - Pathway analysis - `etetoolkit` - Phylogenetic trees - `scikit-bio` - Microbial ecology - `networkx` - Co-occurrence networks - `statsmodels` - Diversity statistics +- `statistical-analysis` - Hypothesis testing - `matplotlib` - Visualization +- `plotly` - Interactive plots **Workflow**: @@ -1826,7 +1868,10 @@ Expected Output: - `scikit-learn` - Resistance prediction - `networkx` - Transmission networks - `statsmodels` - Trend analysis +- `statistical-analysis` - Hypothesis testing - `matplotlib` - Epidemiological plots +- `plotly` - Interactive dashboards +- `clinical-reports` - Surveillance reports **Workflow**: @@ -1969,6 +2014,7 @@ Expected Output: - `pydeseq2` - RNA-seq DE analysis - `pysam` - Variant calling - `ensembl-database` - Gene annotation +- `gget` - Gene data retrieval - `cosmic-database` - Cancer mutations - `string-database` - Protein interactions - `reactome-database` - Pathway analysis @@ -1976,8 +2022,11 @@ Expected Output: - `scikit-learn` - Clustering and classification - `torch_geometric` - Graph neural networks - `umap-learn` - Dimensionality reduction -- `statsmodels` - Survival analysis +- `scikit-survival` - Survival analysis +- `statsmodels` - Statistical modeling - `pymoo` - Multi-objective optimization +- `pyhealth` - Healthcare ML models +- `clinical-reports` - Integrative genomics report **Workflow**: @@ -2147,7 +2196,7 @@ Expected Output: **Skills Used**: - `astropy` - Units and constants - `sympy` - Symbolic mathematics -- `scipy` - Statistical analysis +- `statistical-analysis` - Statistical analysis - `scikit-learn` - Classification - `stable-baselines3` - Reinforcement learning for optimization - `matplotlib` - Visualization @@ -2155,6 +2204,7 @@ Expected Output: - `statsmodels` - Hypothesis testing - `dask` - Large-scale data processing - `vaex` - Out-of-core dataframes +- `plotly` - Interactive visualization **Workflow**: @@ -2296,14 +2346,17 @@ Expected Output: **Skills Used**: - `sympy` - Symbolic equations and reaction kinetics -- `scipy` - Numerical integration and optimization +- `statistical-analysis` - Numerical analysis - `pymoo` - Multi-objective optimization - `simpy` - Process simulation - `pymc` - Bayesian parameter estimation - `scikit-learn` - Process modeling - `stable-baselines3` - Real-time control optimization - `matplotlib` - Process diagrams -- `reportlab` - Engineering reports +- `plotly` - Interactive process visualization +- `fluidsim` - Fluid dynamics simulation +- `scientific-writing` - Engineering reports +- `document-skills` - Technical documentation **Workflow**: @@ -2500,9 +2553,14 @@ Expected Output: **Skills Used**: - `generate-image` - AI image generation and editing - `matplotlib` - Data visualization +- `plotly` - Interactive visualization - `scientific-visualization` - Best practices +- `scientific-schematics` - Scientific diagrams - `scientific-writing` - Figure caption creation -- `reportlab` - PDF report generation +- `scientific-slides` - Presentation materials +- `latex-posters` - Conference posters +- `pptx-posters` - PowerPoint posters +- `document-skills` - PDF report generation **Workflow**: @@ -2618,7 +2676,7 @@ Step 12: Assemble final publication package - Organize all figures in publication order - Create high-resolution exports (300+ DPI for print) - Generate both RGB (web) and CMYK (print) versions -- Compile into PDF using ReportLab: +- Compile into PDF using document-skills: * Title page with graphical abstract * All figures with captions * Supplementary figures section @@ -2637,6 +2695,332 @@ Expected Output: --- +## Quantum Computing for Chemistry + +### Example 21: Variational Quantum Eigensolver for Molecular Ground States + +**Objective**: Use quantum computing to calculate molecular electronic structure and ground state energies for drug design applications. + +**Skills Used**: +- `qiskit` - IBM quantum computing framework +- `pennylane` - Quantum machine learning +- `cirq` - Google quantum circuits +- `qutip` - Quantum dynamics simulation +- `rdkit` - Molecular structure input +- `sympy` - Symbolic Hamiltonian construction +- `matplotlib` - Energy landscape visualization +- `scientific-visualization` - Publication figures +- `scientific-writing` - Quantum chemistry reports + +**Workflow**: + +```bash +Step 1: Define molecular system +- Load molecular structure with RDKit (small drug molecule) +- Extract atomic coordinates and nuclear charges +- Define basis set (STO-3G, 6-31G for small molecules) +- Calculate number of qubits needed (2 qubits per orbital) + +Step 2: Construct molecular Hamiltonian +- Use Qiskit Nature to generate fermionic Hamiltonian +- Apply Jordan-Wigner transformation to qubit Hamiltonian +- Use SymPy to symbolically verify Hamiltonian terms +- Calculate number of Pauli terms + +Step 3: Design variational ansatz with Qiskit +- Choose ansatz type: UCCSD, hardware-efficient, or custom +- Define circuit depth and entanglement structure +- Calculate circuit parameters (variational angles) +- Estimate circuit resources (gates, depth) + +Step 4: Implement VQE algorithm +- Initialize variational parameters randomly +- Define cost function: <ψ(θ)|H|ψ(θ)> +- Choose classical optimizer (COBYLA, SPSA, L-BFGS-B) +- Set convergence criteria + +Step 5: Run quantum simulation with PennyLane +- Configure quantum device (simulator or real hardware) +- Execute variational circuits +- Measure expectation values of Hamiltonian terms +- Update parameters iteratively + +Step 6: Error mitigation +- Implement readout error mitigation +- Apply zero-noise extrapolation +- Use measurement error correction +- Estimate uncertainty in energy values + +Step 7: Quantum dynamics with QuTiP +- Simulate molecular dynamics on quantum computer +- Calculate time evolution of molecular system +- Study non-adiabatic transitions +- Visualize wavefunction dynamics + +Step 8: Compare with classical methods +- Run classical HF and DFT calculations for reference +- Compare VQE results with CCSD(T) (gold standard) +- Analyze quantum advantage for this system +- Quantify accuracy vs computational cost + +Step 9: Scale to larger molecules +- Design circuits for larger drug candidates +- Estimate resources for pharmaceutical applications +- Identify molecules where quantum advantage is expected +- Plan for near-term quantum hardware capabilities + +Step 10: Generate quantum chemistry report +- Energy convergence plots +- Circuit diagrams and ansatz visualizations +- Comparison with classical methods +- Resource estimates for target molecules +- Discussion of quantum advantage timeline +- Publication-quality figures +- Export comprehensive report + +Expected Output: +- Molecular ground state energies from VQE +- Optimized variational circuits +- Comparison with classical chemistry methods +- Resource estimates for drug molecules +- Quantum chemistry analysis report +``` + +--- + +## Research Grant Writing + +### Example 22: NIH R01 Grant Proposal Development + +**Objective**: Develop a comprehensive research grant proposal with literature review, specific aims, and budget justification. + +**Skills Used**: +- `research-grants` - Grant writing templates and guidelines +- `literature-review` - Systematic literature analysis +- `pubmed-database` - Literature search +- `openalex-database` - Citation analysis +- `clinicaltrials-database` - Preliminary data context +- `hypothesis-generation` - Scientific hypothesis development +- `scientific-writing` - Technical writing +- `scientific-critical-thinking` - Research design +- `citation-management` - Reference formatting +- `document-skills` - PDF generation + +**Workflow**: + +```bash +Step 1: Define research question and significance +- Use hypothesis-generation skill to refine research questions +- Identify knowledge gaps in the field +- Articulate significance and innovation +- Define measurable outcomes + +Step 2: Comprehensive literature review +- Search PubMed for relevant publications (last 10 years) +- Query OpenAlex for citation networks +- Identify key papers and review articles +- Use literature-review skill to synthesize findings +- Identify gaps that proposal will address + +Step 3: Develop specific aims +- Aim 1: Mechanistic studies (hypothesis-driven) +- Aim 2: Translational applications +- Aim 3: Validation and clinical relevance +- Ensure aims are interdependent but not contingent +- Define success criteria for each aim + +Step 4: Design research approach +- Use scientific-critical-thinking for experimental design +- Define methods for each specific aim +- Include positive and negative controls +- Plan statistical analysis approach +- Identify potential pitfalls and alternatives + +Step 5: Preliminary data compilation +- Gather existing data supporting hypothesis +- Search ClinicalTrials.gov for relevant prior work +- Create figures showing preliminary results +- Quantify feasibility evidence + +Step 6: Innovation and significance sections +- Articulate what is novel about approach +- Compare to existing methods/knowledge +- Explain expected impact on field +- Address NIH mission alignment + +Step 7: Timeline and milestones +- Create Gantt chart for 5-year project +- Define quarterly milestones +- Identify go/no-go decision points +- Plan for personnel and resource allocation + +Step 8: Budget development +- Calculate personnel costs (PI, postdocs, students) +- Equipment and supplies estimates +- Core facility usage costs +- Travel and publication costs +- Indirect cost calculation + +Step 9: Rigor and reproducibility +- Address biological variables (sex, age, strain) +- Statistical power calculations +- Data management and sharing plan +- Authentication of key resources + +Step 10: Format and compile +- Use research-grants templates for NIH format +- Apply citation-management for references +- Create biosketch and facilities sections +- Generate PDF with proper formatting +- Check page limits and formatting requirements + +Step 11: Review and revision +- Use peer-review skill principles for self-assessment +- Check for logical flow and clarity +- Verify alignment with FOA requirements +- Ensure responsive to review criteria + +Step 12: Final deliverables +- Specific Aims page (1 page) +- Research Strategy (12 pages) +- Bibliography +- Budget and justification +- Biosketches +- Letters of support +- Data management plan +- Human subjects/vertebrate animals sections (if applicable) + +Expected Output: +- Complete NIH R01 grant proposal +- Literature review summary +- Budget spreadsheet with justification +- Timeline and milestone chart +- All required supplementary documents +- Properly formatted PDF ready for submission +``` + +--- + +## Flow Cytometry & Immunophenotyping + +### Example 23: Multi-Parameter Flow Cytometry Analysis Pipeline + +**Objective**: Analyze high-dimensional flow cytometry data to characterize immune cell populations in clinical samples. + +**Skills Used**: +- `flowio` - FCS file parsing +- `scanpy` - High-dimensional analysis +- `scikit-learn` - Clustering and classification +- `umap-learn` - Dimensionality reduction +- `statistical-analysis` - Population statistics +- `matplotlib` - Flow cytometry plots +- `plotly` - Interactive gating +- `clinical-reports` - Clinical flow reports +- `exploratory-data-analysis` - Data exploration + +**Workflow**: + +```bash +Step 1: Load and parse FCS files +- Use flowio to read FCS 3.0/3.1 files +- Extract channel names and metadata +- Load compensation matrix from file +- Parse keywords (patient ID, tube, date) + +Step 2: Quality control +- Check for acquisition anomalies (time vs events) +- Identify clogging or fluidics issues +- Remove doublets (FSC-A vs FSC-H) +- Gate viable cells (exclude debris) +- Document QC metrics per sample + +Step 3: Compensation and transformation +- Apply compensation matrix +- Transform data (biexponential/logicle) +- Verify compensation with single-stain controls +- Visualize spillover reduction + +Step 4: Traditional gating strategy +- Sequential manual gating approach: + * Lymphocytes (FSC vs SSC) + * Single cells (FSC-A vs FSC-H) + * Live cells (viability dye negative) + * CD3+ T cells, CD19+ B cells, etc. +- Calculate population frequencies +- Export gated populations + +Step 5: High-dimensional analysis with Scanpy +- Convert flow data to AnnData format +- Apply variance-stabilizing transformation +- Calculate highly variable markers +- Build neighbor graph + +Step 6: Dimensionality reduction +- Run UMAP with umap-learn for visualization +- Optimize UMAP parameters (n_neighbors, min_dist) +- Create 2D embeddings colored by: + * Marker expression + * Sample/patient + * Clinical group + +Step 7: Automated clustering +- Apply Leiden or FlowSOM clustering +- Determine optimal cluster resolution +- Assign cell type labels based on marker profiles +- Validate clusters against manual gating + +Step 8: Differential abundance analysis +- Compare population frequencies between groups +- Use statistical-analysis for hypothesis testing +- Calculate fold changes and p-values +- Apply multiple testing correction +- Identify significantly altered populations + +Step 9: Biomarker discovery +- Train classifiers to predict clinical outcome +- Use scikit-learn Random Forest or SVM +- Calculate feature importance (which populations matter) +- Cross-validate prediction accuracy +- Identify candidate biomarkers + +Step 10: Quality metrics and batch effects +- Calculate CV for control samples +- Detect batch effects across acquisition dates +- Apply batch correction if needed +- Generate Levey-Jennings plots for QC + +Step 11: Visualization suite +- Traditional flow plots: + * Bivariate dot plots with quadrant gates + * Histogram overlays + * Contour plots +- High-dimensional plots: + * UMAP colored by population + * Heatmaps of marker expression + * Violin plots for marker distributions +- Interactive plots with Plotly + +Step 12: Generate clinical flow cytometry report +- Sample information and QC summary +- Gating strategy diagrams +- Population frequency tables +- Reference range comparisons +- Statistical comparisons between groups +- Interpretation and clinical significance +- Export as PDF for clinical review + +Expected Output: +- Parsed and compensated flow cytometry data +- Traditional and automated gating results +- High-dimensional clustering and UMAP +- Differential abundance statistics +- Biomarker candidates for clinical outcome +- Publication-quality flow plots +- Clinical flow cytometry report +``` + +--- + ## Summary These examples demonstrate: @@ -2647,6 +3031,44 @@ These examples demonstrate: 4. **End-to-end workflows**: From data acquisition to publication-ready reports 5. **Best practices**: QC, statistical rigor, visualization, interpretation, and documentation +### Skills Coverage Summary + +The examples in this document cover the following skill categories: + +**Databases & Data Sources:** +- Biological: `chembl-database`, `pubchem-database`, `drugbank-database`, `uniprot-database`, `gene-database`, `ensembl-database`, `clinvar-database`, `cosmic-database`, `string-database`, `kegg-database`, `reactome-database`, `hmdb-database`, `pdb-database`, `alphafold-database`, `zinc-database`, `gwas-database`, `geo-database`, `ena-database`, `cellxgene-census`, `metabolomics-workbench-database`, `brenda-database`, `clinpgx-database` +- Clinical: `clinicaltrials-database`, `fda-database` +- Literature: `pubmed-database`, `openalex-database`, `biorxiv-database` + +**Analysis Packages:** +- Chemistry: `rdkit`, `datamol`, `medchem`, `molfeat`, `deepchem`, `torchdrug`, `pytdc`, `diffdock`, `pyopenms`, `matchms`, `cobrapy` +- Genomics: `biopython`, `pysam`, `pydeseq2`, `scanpy`, `scvi-tools`, `anndata`, `gget`, `geniml`, `deeptools`, `etetoolkit`, `scikit-bio` +- Proteins: `esm`, `bioservices` +- Machine Learning: `scikit-learn`, `pytorch-lightning`, `torch_geometric`, `transformers`, `stable-baselines3`, `shap` +- Statistics: `statsmodels`, `statistical-analysis`, `pymc`, `scikit-survival` +- Visualization: `matplotlib`, `seaborn`, `plotly`, `scientific-visualization` +- Data Processing: `polars`, `dask`, `vaex`, `networkx` +- Materials: `pymatgen` +- Physics: `astropy`, `sympy`, `fluidsim` +- Quantum: `qiskit`, `pennylane`, `cirq`, `qutip` +- Neuroscience: `neurokit2`, `neuropixels-analysis` +- Pathology: `histolab`, `pathml`, `pydicom` +- Flow Cytometry: `flowio` +- Dimensionality Reduction: `umap-learn`, `arboreto` +- Lab Automation: `pylabrobot`, `opentrons-integration`, `benchling-integration`, `labarchive-integration`, `protocolsio-integration` +- Simulation: `simpy`, `pymoo` + +**Writing & Reporting:** +- `scientific-writing`, `scientific-visualization`, `scientific-schematics`, `scientific-slides` +- `clinical-reports`, `clinical-decision-support` +- `literature-review`, `hypothesis-generation`, `scientific-critical-thinking` +- `research-grants`, `peer-review` +- `document-skills`, `latex-posters`, `pptx-posters` +- `citation-management`, `market-research-reports` + +**Image & Media:** +- `generate-image`, `omero-integration` + ### How to Use These Examples 1. **Adapt to your needs**: Modify parameters, datasets, and objectives for your specific research question diff --git a/scientific-skills/alphafold-database/SKILL.md b/scientific-skills/alphafold-database/SKILL.md index 4d55596..cfac90d 100644 --- a/scientific-skills/alphafold-database/SKILL.md +++ b/scientific-skills/alphafold-database/SKILL.md @@ -1,6 +1,6 @@ --- name: alphafold-database -description: "Access AlphaFold's 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology." +description: Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/anndata/SKILL.md b/scientific-skills/anndata/SKILL.md index 0afa26c..28e0986 100644 --- a/scientific-skills/anndata/SKILL.md +++ b/scientific-skills/anndata/SKILL.md @@ -1,6 +1,6 @@ --- name: anndata -description: This skill should be used when working with annotated data matrices in Python, particularly for single-cell genomics analysis, managing experimental measurements with metadata, or handling large-scale biological datasets. Use when tasks involve AnnData objects, h5ad files, single-cell RNA-seq data, or integration with scanpy/scverse tools. +description: Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census. license: BSD-3-Clause license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/benchling-integration/SKILL.md b/scientific-skills/benchling-integration/SKILL.md index 03e3547..13603ed 100644 --- a/scientific-skills/benchling-integration/SKILL.md +++ b/scientific-skills/benchling-integration/SKILL.md @@ -1,6 +1,6 @@ --- name: benchling-integration -description: "Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation." +description: Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation. license: Unknown compatibility: Requires a Benchling account and API key metadata: diff --git a/scientific-skills/biopython/SKILL.md b/scientific-skills/biopython/SKILL.md index a24e816..04325c4 100644 --- a/scientific-skills/biopython/SKILL.md +++ b/scientific-skills/biopython/SKILL.md @@ -1,6 +1,6 @@ --- name: biopython -description: "Primary Python toolkit for molecular biology. Preferred for Python-based PubMed/NCBI queries (Bio.Entrez), sequence manipulation, file parsing (FASTA, GenBank, FASTQ, PDB), advanced BLAST workflows, structures, phylogenetics. For quick BLAST, use gget. For direct REST API, use pubmed-database." +description: Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/bioservices/SKILL.md b/scientific-skills/bioservices/SKILL.md index 4a81d60..dcf2f4a 100644 --- a/scientific-skills/bioservices/SKILL.md +++ b/scientific-skills/bioservices/SKILL.md @@ -1,6 +1,6 @@ --- name: bioservices -description: "Primary Python tool for 40+ bioinformatics services. Preferred for multi-database workflows: UniProt, KEGG, ChEMBL, PubChem, Reactome, QuickGO. Unified API for queries, ID mapping, pathway analysis. For direct REST control, use individual database skills (uniprot-database, kegg-database)." +description: Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython. license: GPLv3 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/brenda-database/SKILL.md b/scientific-skills/brenda-database/SKILL.md index e29d4f9..2b5e137 100644 --- a/scientific-skills/brenda-database/SKILL.md +++ b/scientific-skills/brenda-database/SKILL.md @@ -1,6 +1,6 @@ --- name: brenda-database -description: "Access BRENDA enzyme database via SOAP API. Retrieve kinetic parameters (Km, kcat), reaction equations, organism data, and substrate-specific enzyme information for biochemical research and metabolic pathway analysis." +description: Access BRENDA enzyme database via SOAP API. Retrieve kinetic parameters (Km, kcat), reaction equations, organism data, and substrate-specific enzyme information for biochemical research and metabolic pathway analysis. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/cellxgene-census/SKILL.md b/scientific-skills/cellxgene-census/SKILL.md index 37bc6a3..a16d0c0 100644 --- a/scientific-skills/cellxgene-census/SKILL.md +++ b/scientific-skills/cellxgene-census/SKILL.md @@ -1,6 +1,6 @@ --- name: cellxgene-census -description: "Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, integrate with scanpy/PyTorch, for population-scale single-cell analysis." +description: Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/chembl-database/SKILL.md b/scientific-skills/chembl-database/SKILL.md index a294537..c4a8807 100644 --- a/scientific-skills/chembl-database/SKILL.md +++ b/scientific-skills/chembl-database/SKILL.md @@ -1,6 +1,6 @@ --- name: chembl-database -description: "Query ChEMBL's bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry." +description: Query ChEMBL bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/cirq/SKILL.md b/scientific-skills/cirq/SKILL.md index 3ef9804..0fa39b0 100644 --- a/scientific-skills/cirq/SKILL.md +++ b/scientific-skills/cirq/SKILL.md @@ -1,6 +1,6 @@ --- name: cirq -description: Quantum computing framework for building, simulating, optimizing, and executing quantum circuits. Use this skill when working with quantum algorithms, quantum circuit design, quantum simulation (noiseless or noisy), running on quantum hardware (Google, IonQ, AQT, Pasqal), circuit optimization and compilation, noise modeling and characterization, or quantum experiments and benchmarking (VQE, QAOA, QPE, randomized benchmarking). +description: Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip. license: Apache-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/clinical-decision-support/SKILL.md b/scientific-skills/clinical-decision-support/SKILL.md index 1021d5f..f17538f 100644 --- a/scientific-skills/clinical-decision-support/SKILL.md +++ b/scientific-skills/clinical-decision-support/SKILL.md @@ -1,6 +1,6 @@ --- name: clinical-decision-support -description: "Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis." +description: Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis. allowed-tools: [Read, Write, Edit, Bash] license: MIT License metadata: diff --git a/scientific-skills/clinical-reports/SKILL.md b/scientific-skills/clinical-reports/SKILL.md index 993067e..8c95bd6 100644 --- a/scientific-skills/clinical-reports/SKILL.md +++ b/scientific-skills/clinical-reports/SKILL.md @@ -1,6 +1,6 @@ --- name: clinical-reports -description: "Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools." +description: Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools. allowed-tools: [Read, Write, Edit, Bash] license: MIT License metadata: diff --git a/scientific-skills/clinicaltrials-database/SKILL.md b/scientific-skills/clinicaltrials-database/SKILL.md index 40594ad..707121b 100644 --- a/scientific-skills/clinicaltrials-database/SKILL.md +++ b/scientific-skills/clinicaltrials-database/SKILL.md @@ -1,6 +1,6 @@ --- name: clinicaltrials-database -description: "Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching." +description: Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/clinpgx-database/SKILL.md b/scientific-skills/clinpgx-database/SKILL.md index 5aec967..5e49a3e 100644 --- a/scientific-skills/clinpgx-database/SKILL.md +++ b/scientific-skills/clinpgx-database/SKILL.md @@ -1,6 +1,6 @@ --- name: clinpgx-database -description: "Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions." +description: Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/clinvar-database/SKILL.md b/scientific-skills/clinvar-database/SKILL.md index 06b0512..0adfabd 100644 --- a/scientific-skills/clinvar-database/SKILL.md +++ b/scientific-skills/clinvar-database/SKILL.md @@ -1,6 +1,6 @@ --- name: clinvar-database -description: "Query NCBI ClinVar for variant clinical significance. Search by gene/position, interpret pathogenicity classifications, access via E-utilities API or FTP, annotate VCFs, for genomic medicine." +description: Query NCBI ClinVar for variant clinical significance. Search by gene/position, interpret pathogenicity classifications, access via E-utilities API or FTP, annotate VCFs, for genomic medicine. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/cobrapy/SKILL.md b/scientific-skills/cobrapy/SKILL.md index fec1174..586bd97 100644 --- a/scientific-skills/cobrapy/SKILL.md +++ b/scientific-skills/cobrapy/SKILL.md @@ -1,6 +1,6 @@ --- name: cobrapy -description: "Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis." +description: Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis. license: GPL-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/cosmic-database/SKILL.md b/scientific-skills/cosmic-database/SKILL.md index 5d2a2a3..cd32dfa 100644 --- a/scientific-skills/cosmic-database/SKILL.md +++ b/scientific-skills/cosmic-database/SKILL.md @@ -1,6 +1,6 @@ --- name: cosmic-database -description: "Access COSMIC cancer mutation database. Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions, for cancer research and precision oncology. Requires authentication." +description: Access COSMIC cancer mutation database. Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions, for cancer research and precision oncology. Requires authentication. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/dask/SKILL.md b/scientific-skills/dask/SKILL.md index bb83650..ca4b62c 100644 --- a/scientific-skills/dask/SKILL.md +++ b/scientific-skills/dask/SKILL.md @@ -1,6 +1,6 @@ --- name: dask -description: "Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows." +description: Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars. license: BSD-3-Clause license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/datamol/SKILL.md b/scientific-skills/datamol/SKILL.md index 9358366..139e950 100644 --- a/scientific-skills/datamol/SKILL.md +++ b/scientific-skills/datamol/SKILL.md @@ -1,6 +1,6 @@ --- name: datamol -description: "Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery: SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly." +description: Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly. license: Apache-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/deepchem/SKILL.md b/scientific-skills/deepchem/SKILL.md index 2024794..ef85fdb 100644 --- a/scientific-skills/deepchem/SKILL.md +++ b/scientific-skills/deepchem/SKILL.md @@ -1,6 +1,6 @@ --- name: deepchem -description: "Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug discovery ML." +description: Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/deeptools/SKILL.md b/scientific-skills/deeptools/SKILL.md index f2f3ad5..7266b90 100644 --- a/scientific-skills/deeptools/SKILL.md +++ b/scientific-skills/deeptools/SKILL.md @@ -1,6 +1,6 @@ --- name: deeptools -description: "NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization." +description: NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization. license: BSD license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/diffdock/SKILL.md b/scientific-skills/diffdock/SKILL.md index 64523eb..c789e54 100644 --- a/scientific-skills/diffdock/SKILL.md +++ b/scientific-skills/diffdock/SKILL.md @@ -1,6 +1,6 @@ --- name: diffdock -description: "Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction." +description: Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/dnanexus-integration/SKILL.md b/scientific-skills/dnanexus-integration/SKILL.md index 77cdbc2..f9ec4ae 100644 --- a/scientific-skills/dnanexus-integration/SKILL.md +++ b/scientific-skills/dnanexus-integration/SKILL.md @@ -1,6 +1,6 @@ --- name: dnanexus-integration -description: "DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution." +description: DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution. license: Unknown compatibility: Requires a DNAnexus account metadata: diff --git a/scientific-skills/document-skills/docx/SKILL.md b/scientific-skills/document-skills/docx/SKILL.md index cc3ceb9..59b9326 100644 --- a/scientific-skills/document-skills/docx/SKILL.md +++ b/scientific-skills/document-skills/docx/SKILL.md @@ -1,6 +1,6 @@ --- name: docx -description: "Document toolkit (.docx). Create/edit documents, tracked changes, comments, formatting preservation, text extraction, for professional document processing." +description: Document toolkit (.docx). Create/edit documents, tracked changes, comments, formatting preservation, text extraction, for professional document processing. license: Proprietary. LICENSE.txt has complete terms --- diff --git a/scientific-skills/document-skills/pdf/SKILL.md b/scientific-skills/document-skills/pdf/SKILL.md index 8ff8801..00f623c 100644 --- a/scientific-skills/document-skills/pdf/SKILL.md +++ b/scientific-skills/document-skills/pdf/SKILL.md @@ -1,6 +1,6 @@ --- name: pdf -description: "PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis." +description: PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis. license: Proprietary. LICENSE.txt has complete terms --- diff --git a/scientific-skills/document-skills/pptx/SKILL.md b/scientific-skills/document-skills/pptx/SKILL.md index 134b3b6..3f6d4c2 100644 --- a/scientific-skills/document-skills/pptx/SKILL.md +++ b/scientific-skills/document-skills/pptx/SKILL.md @@ -1,6 +1,6 @@ --- name: pptx -description: "Presentation toolkit (.pptx). Create/edit slides, layouts, content, speaker notes, comments, for programmatic presentation creation and modification." +description: Presentation toolkit (.pptx). Create/edit slides, layouts, content, speaker notes, comments, for programmatic presentation creation and modification. license: Proprietary. LICENSE.txt has complete terms --- diff --git a/scientific-skills/document-skills/xlsx/SKILL.md b/scientific-skills/document-skills/xlsx/SKILL.md index 3e12c94..4705e63 100644 --- a/scientific-skills/document-skills/xlsx/SKILL.md +++ b/scientific-skills/document-skills/xlsx/SKILL.md @@ -1,6 +1,6 @@ --- name: xlsx -description: "Spreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze data, visualization, recalculate formulas, for spreadsheet processing and analysis." +description: Spreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze data, visualization, recalculate formulas, for spreadsheet processing and analysis. license: Proprietary. LICENSE.txt has complete terms --- diff --git a/scientific-skills/ena-database/SKILL.md b/scientific-skills/ena-database/SKILL.md index 28c611f..16b5eba 100644 --- a/scientific-skills/ena-database/SKILL.md +++ b/scientific-skills/ena-database/SKILL.md @@ -1,6 +1,6 @@ --- name: ena-database -description: "Access European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines. Supports multiple formats." +description: Access European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines. Supports multiple formats. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/ensembl-database/SKILL.md b/scientific-skills/ensembl-database/SKILL.md index aa609ba..424671c 100644 --- a/scientific-skills/ensembl-database/SKILL.md +++ b/scientific-skills/ensembl-database/SKILL.md @@ -1,6 +1,6 @@ --- name: ensembl-database -description: "Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research." +description: Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/etetoolkit/SKILL.md b/scientific-skills/etetoolkit/SKILL.md index b67e186..838542c 100644 --- a/scientific-skills/etetoolkit/SKILL.md +++ b/scientific-skills/etetoolkit/SKILL.md @@ -1,6 +1,6 @@ --- name: etetoolkit -description: "Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics." +description: Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics. license: GPL-3.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/fda-database/SKILL.md b/scientific-skills/fda-database/SKILL.md index 58523d7..ac9f620 100644 --- a/scientific-skills/fda-database/SKILL.md +++ b/scientific-skills/fda-database/SKILL.md @@ -1,6 +1,6 @@ --- name: fda-database -description: "Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research." +description: Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/flowio/SKILL.md b/scientific-skills/flowio/SKILL.md index 2be4386..10c1610 100644 --- a/scientific-skills/flowio/SKILL.md +++ b/scientific-skills/flowio/SKILL.md @@ -1,6 +1,6 @@ --- name: flowio -description: "Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing." +description: Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing. license: BSD-3-Clause license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/gene-database/SKILL.md b/scientific-skills/gene-database/SKILL.md index 68def0c..4bbd9e8 100644 --- a/scientific-skills/gene-database/SKILL.md +++ b/scientific-skills/gene-database/SKILL.md @@ -1,6 +1,6 @@ --- name: gene-database -description: "Query NCBI Gene via E-utilities/Datasets API. Search by symbol/ID, retrieve gene info (RefSeqs, GO, locations, phenotypes), batch lookups, for gene annotation and functional analysis." +description: Query NCBI Gene via E-utilities/Datasets API. Search by symbol/ID, retrieve gene info (RefSeqs, GO, locations, phenotypes), batch lookups, for gene annotation and functional analysis. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/generate-image/SKILL.md b/scientific-skills/generate-image/SKILL.md index 460f301..25f6aaf 100644 --- a/scientific-skills/generate-image/SKILL.md +++ b/scientific-skills/generate-image/SKILL.md @@ -1,6 +1,6 @@ --- name: generate-image -description: Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that isn't a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead. +description: Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead. license: MIT license compatibility: Requires an OpenRouter API key metadata: diff --git a/scientific-skills/geo-database/SKILL.md b/scientific-skills/geo-database/SKILL.md index fe8a52d..9ddf30b 100644 --- a/scientific-skills/geo-database/SKILL.md +++ b/scientific-skills/geo-database/SKILL.md @@ -1,6 +1,6 @@ --- name: geo-database -description: "Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis." +description: Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/gget/SKILL.md b/scientific-skills/gget/SKILL.md index 1cd2c6d..745a2ac 100644 --- a/scientific-skills/gget/SKILL.md +++ b/scientific-skills/gget/SKILL.md @@ -1,6 +1,6 @@ --- name: gget -description: "CLI/Python toolkit for rapid bioinformatics queries. Preferred for quick BLAST searches. Access to 20+ databases: gene info (Ensembl/UniProt), AlphaFold, ARCHS4, Enrichr, OpenTargets, COSMIC, genome downloads. For advanced BLAST/batch processing, use biopython. For multi-database integration, use bioservices." +descriptipn: Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices. license: BSD-2-Clause license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/gwas-database/SKILL.md b/scientific-skills/gwas-database/SKILL.md index 086ab80..4248516 100644 --- a/scientific-skills/gwas-database/SKILL.md +++ b/scientific-skills/gwas-database/SKILL.md @@ -1,6 +1,6 @@ --- name: gwas-database -description: "Query NHGRI-EBI GWAS Catalog for SNP-trait associations. Search variants by rs ID, disease/trait, gene, retrieve p-values and summary statistics, for genetic epidemiology and polygenic risk scores." +description: Query NHGRI-EBI GWAS Catalog for SNP-trait associations. Search variants by rs ID, disease/trait, gene, retrieve p-values and summary statistics, for genetic epidemiology and polygenic risk scores. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/histolab/SKILL.md b/scientific-skills/histolab/SKILL.md index f04ae1f..0bd4d02 100644 --- a/scientific-skills/histolab/SKILL.md +++ b/scientific-skills/histolab/SKILL.md @@ -1,6 +1,6 @@ --- name: histolab -description: Digital pathology image processing toolkit for whole slide images (WSI). Use this skill when working with histopathology slides, processing H&E or IHC stained tissue images, extracting tiles from gigapixel pathology images, detecting tissue regions, segmenting tissue masks, or preparing datasets for computational pathology deep learning pipelines. Applies to WSI formats (SVS, TIFF, NDPI), tile-based analysis, and histological image preprocessing workflows. +description: Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml. license: Apache-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/hmdb-database/SKILL.md b/scientific-skills/hmdb-database/SKILL.md index 05a8e9a..4fd5cc6 100644 --- a/scientific-skills/hmdb-database/SKILL.md +++ b/scientific-skills/hmdb-database/SKILL.md @@ -1,6 +1,6 @@ --- name: hmdb-database -description: "Access Human Metabolome Database (220K+ metabolites). Search by name/ID/structure, retrieve chemical properties, biomarker data, NMR/MS spectra, pathways, for metabolomics and identification." +description: Access Human Metabolome Database (220K+ metabolites). Search by name/ID/structure, retrieve chemical properties, biomarker data, NMR/MS spectra, pathways, for metabolomics and identification. license: HMDB is offered to the public as a freely available resource. Use and re-distribution of the data, in whole or in part, for commercial purposes requires explicit permission of the authors and explicit acknowledgment of the source material (HMDB) and the original publication (see the HMDB citing page). We ask that users who download significant portions of the database cite the HMDB paper in any resulting publications. metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/hypogenic/SKILL.md b/scientific-skills/hypogenic/SKILL.md index f6a5e71..6f6106a 100644 --- a/scientific-skills/hypogenic/SKILL.md +++ b/scientific-skills/hypogenic/SKILL.md @@ -1,6 +1,6 @@ --- name: hypogenic -description: Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data, testing hypotheses against observational data, or conducting systematic hypothesis exploration for research discovery in domains like deception detection, AI content detection, mental health analysis, or other empirical research tasks. +description: Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/hypothesis-generation/SKILL.md b/scientific-skills/hypothesis-generation/SKILL.md index 6a63df1..fb03078 100644 --- a/scientific-skills/hypothesis-generation/SKILL.md +++ b/scientific-skills/hypothesis-generation/SKILL.md @@ -1,6 +1,6 @@ --- name: hypothesis-generation -description: "Generate testable hypotheses. Formulate from observations, design experiments, explore competing explanations, develop predictions, propose mechanisms, for scientific inquiry across domains." +description: Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/kegg-database/SKILL.md b/scientific-skills/kegg-database/SKILL.md index b6bb058..83a3e4f 100644 --- a/scientific-skills/kegg-database/SKILL.md +++ b/scientific-skills/kegg-database/SKILL.md @@ -1,6 +1,6 @@ --- name: kegg-database -description: "Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP/REST work or KEGG-specific control." +description: Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP/REST work or KEGG-specific control. license: Non-academic use of KEGG requires a commercial license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/labarchive-integration/SKILL.md b/scientific-skills/labarchive-integration/SKILL.md index e3874a2..4bf0bcb 100644 --- a/scientific-skills/labarchive-integration/SKILL.md +++ b/scientific-skills/labarchive-integration/SKILL.md @@ -1,6 +1,6 @@ --- name: labarchive-integration -description: "Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows." +description: Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/latchbio-integration/SKILL.md b/scientific-skills/latchbio-integration/SKILL.md index 728f94b..6b8c90a 100644 --- a/scientific-skills/latchbio-integration/SKILL.md +++ b/scientific-skills/latchbio-integration/SKILL.md @@ -1,6 +1,6 @@ --- name: latchbio-integration -description: "Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration." +description: Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/latex-posters/SKILL.md b/scientific-skills/latex-posters/SKILL.md index 1fb6bec..130299e 100644 --- a/scientific-skills/latex-posters/SKILL.md +++ b/scientific-skills/latex-posters/SKILL.md @@ -1,6 +1,6 @@ --- name: latex-posters -description: "Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication." +description: Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/market-research-reports/SKILL.md b/scientific-skills/market-research-reports/SKILL.md index fdf93ad..d3991ed 100644 --- a/scientific-skills/market-research-reports/SKILL.md +++ b/scientific-skills/market-research-reports/SKILL.md @@ -1,6 +1,6 @@ --- name: market-research-reports -description: "Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix." +description: Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/markitdown/SKILL.md b/scientific-skills/markitdown/SKILL.md index 964e097..fb42f29 100644 --- a/scientific-skills/markitdown/SKILL.md +++ b/scientific-skills/markitdown/SKILL.md @@ -1,6 +1,6 @@ --- name: markitdown -description: "Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more." +description: Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/matchms/SKILL.md b/scientific-skills/matchms/SKILL.md index 0f217bb..f9ea1f7 100644 --- a/scientific-skills/matchms/SKILL.md +++ b/scientific-skills/matchms/SKILL.md @@ -1,6 +1,6 @@ --- name: matchms -description: "Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization, compound ID, for metabolomics and MS data processing." +description: Spectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity scores (cosine, modified cosine), and identifying unknown compounds from spectral libraries. Best for metabolite identification, spectral matching, library searching. For full LC-MS/MS proteomics pipelines use pyopenms. license: Apache-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/matplotlib/SKILL.md b/scientific-skills/matplotlib/SKILL.md index 88aaa79..6652c15 100644 --- a/scientific-skills/matplotlib/SKILL.md +++ b/scientific-skills/matplotlib/SKILL.md @@ -1,6 +1,6 @@ --- name: matplotlib -description: "Foundational plotting library. Create line plots, scatter, bar, histograms, heatmaps, 3D, subplots, export PNG/PDF/SVG, for scientific visualization and publication figures." +description: Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization. license: https://github.com/matplotlib/matplotlib/tree/main/LICENSE metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/medchem/SKILL.md b/scientific-skills/medchem/SKILL.md index 06ebae5..23a2a39 100644 --- a/scientific-skills/medchem/SKILL.md +++ b/scientific-skills/medchem/SKILL.md @@ -1,6 +1,6 @@ --- name: medchem -description: "Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering." +description: Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering. license: Apache-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/metabolomics-workbench-database/SKILL.md b/scientific-skills/metabolomics-workbench-database/SKILL.md index 526f76b..4bf2a9c 100644 --- a/scientific-skills/metabolomics-workbench-database/SKILL.md +++ b/scientific-skills/metabolomics-workbench-database/SKILL.md @@ -1,6 +1,6 @@ --- name: metabolomics-workbench-database -description: "Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery." +description: Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/molfeat/SKILL.md b/scientific-skills/molfeat/SKILL.md index 10e36b3..789d65b 100644 --- a/scientific-skills/molfeat/SKILL.md +++ b/scientific-skills/molfeat/SKILL.md @@ -1,6 +1,6 @@ --- name: molfeat -description: "Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML." +description: Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML. license: Apache-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/neuropixels-analysis/SKILL.md b/scientific-skills/neuropixels-analysis/SKILL.md index 278721b..15a7b2f 100644 --- a/scientific-skills/neuropixels-analysis/SKILL.md +++ b/scientific-skills/neuropixels-analysis/SKILL.md @@ -1,6 +1,6 @@ --- name: neuropixels-analysis -description: "Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation." +description: Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/omero-integration/SKILL.md b/scientific-skills/omero-integration/SKILL.md index 917ced3..82d8b6a 100644 --- a/scientific-skills/omero-integration/SKILL.md +++ b/scientific-skills/omero-integration/SKILL.md @@ -1,6 +1,6 @@ --- name: omero-integration -description: "Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows." +description: Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/opentargets-database/SKILL.md b/scientific-skills/opentargets-database/SKILL.md index 538a553..faa61c8 100644 --- a/scientific-skills/opentargets-database/SKILL.md +++ b/scientific-skills/opentargets-database/SKILL.md @@ -1,6 +1,6 @@ --- name: opentargets-database -description: "Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification." +description: Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/opentrons-integration/SKILL.md b/scientific-skills/opentrons-integration/SKILL.md index c5605b6..e37d781 100644 --- a/scientific-skills/opentrons-integration/SKILL.md +++ b/scientific-skills/opentrons-integration/SKILL.md @@ -1,6 +1,6 @@ --- name: opentrons-integration -description: "Lab automation platform for Flex/OT-2 robots. Write Protocol API v2 protocols, liquid handling, hardware modules (heater-shaker, thermocycler), labware management, for automated pipetting workflows." +description: Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pathml/SKILL.md b/scientific-skills/pathml/SKILL.md index dd57ba4..172cbad 100644 --- a/scientific-skills/pathml/SKILL.md +++ b/scientific-skills/pathml/SKILL.md @@ -1,6 +1,6 @@ --- name: pathml -description: Computational pathology toolkit for analyzing whole-slide images (WSI) and multiparametric imaging data. Use this skill when working with histopathology slides, H&E stained images, multiplex immunofluorescence (CODEX, Vectra), spatial proteomics, nucleus detection/segmentation, tissue graph construction, or training ML models on pathology data. Supports 160+ slide formats including Aperio SVS, NDPI, DICOM, OME-TIFF for digital pathology workflows. +description: Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler. license: GPL-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pdb-database/SKILL.md b/scientific-skills/pdb-database/SKILL.md index b86741e..377ec7f 100644 --- a/scientific-skills/pdb-database/SKILL.md +++ b/scientific-skills/pdb-database/SKILL.md @@ -1,6 +1,6 @@ --- name: pdb-database -description: "Access RCSB PDB for 3D protein/nucleic acid structures. Search by text/sequence/structure, download coordinates (PDB/mmCIF), retrieve metadata, for structural biology and drug discovery." +description: Access RCSB PDB for 3D protein/nucleic acid structures. Search by text/sequence/structure, download coordinates (PDB/mmCIF), retrieve metadata, for structural biology and drug discovery. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/peer-review/SKILL.md b/scientific-skills/peer-review/SKILL.md index 9f1a1d5..fbc0ca3 100644 --- a/scientific-skills/peer-review/SKILL.md +++ b/scientific-skills/peer-review/SKILL.md @@ -1,6 +1,6 @@ --- name: peer-review -description: "Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines." +description: Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/pennylane/SKILL.md b/scientific-skills/pennylane/SKILL.md index 5a41246..8cedc21 100644 --- a/scientific-skills/pennylane/SKILL.md +++ b/scientific-skills/pennylane/SKILL.md @@ -1,6 +1,6 @@ --- name: pennylane -description: Cross-platform Python library for quantum computing, quantum machine learning, and quantum chemistry. Enables building and training quantum circuits with automatic differentiation, seamless integration with PyTorch/JAX/TensorFlow, and device-independent execution across simulators and quantum hardware (IBM, Amazon Braket, Google, Rigetti, IonQ, etc.). Use when working with quantum circuits, variational quantum algorithms (VQE, QAOA), quantum neural networks, hybrid quantum-classical models, molecular simulations, quantum chemistry calculations, or any quantum computing tasks requiring gradient-based optimization, hardware-agnostic programming, or quantum machine learning workflows. +description: Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip. license: Apache-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/perplexity-search/SKILL.md b/scientific-skills/perplexity-search/SKILL.md index dba2403..cf491d8 100644 --- a/scientific-skills/perplexity-search/SKILL.md +++ b/scientific-skills/perplexity-search/SKILL.md @@ -1,6 +1,6 @@ --- name: perplexity-search -description: Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model's knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key. +description: Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key. license: MIT license compatibility: An OpenRouter API key is required to use Perplexity search metadata: diff --git a/scientific-skills/plotly/SKILL.md b/scientific-skills/plotly/SKILL.md index 78c20cf..ad4524a 100644 --- a/scientific-skills/plotly/SKILL.md +++ b/scientific-skills/plotly/SKILL.md @@ -1,6 +1,6 @@ --- name: plotly -description: Interactive scientific and statistical data visualization library for Python. Use when creating charts, plots, or visualizations including scatter plots, line charts, bar charts, heatmaps, 3D plots, geographic maps, statistical distributions, financial charts, and dashboards. Supports both quick visualizations (Plotly Express) and fine-grained customization (graph objects). Outputs interactive HTML or static images (PNG, PDF, SVG). +description: Interactive visualization library. Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards, exploratory analysis, and presentations. For static publication figures use matplotlib or scientific-visualization. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/polars/SKILL.md b/scientific-skills/polars/SKILL.md index 0a01b19..65e5329 100644 --- a/scientific-skills/polars/SKILL.md +++ b/scientific-skills/polars/SKILL.md @@ -1,6 +1,6 @@ --- name: polars -description: "Fast DataFrame library (Apache Arrow). Select, filter, group_by, joins, lazy evaluation, CSV/Parquet I/O, expression API, for high-performance data analysis workflows." +description: Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex. license: https://github.com/pola-rs/polars/blob/main/LICENSE metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pptx-posters/SKILL.md b/scientific-skills/pptx-posters/SKILL.md index 1dd40bc..4df7ca2 100644 --- a/scientific-skills/pptx-posters/SKILL.md +++ b/scientific-skills/pptx-posters/SKILL.md @@ -1,6 +1,6 @@ --- name: pptx-posters -description: "Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual integration." +description: Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual integration. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/pubchem-database/SKILL.md b/scientific-skills/pubchem-database/SKILL.md index 7e68ac2..e76bb3a 100644 --- a/scientific-skills/pubchem-database/SKILL.md +++ b/scientific-skills/pubchem-database/SKILL.md @@ -1,6 +1,6 @@ --- name: pubchem-database -description: "Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics." +description: Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pubmed-database/SKILL.md b/scientific-skills/pubmed-database/SKILL.md index 86267d4..933cde6 100644 --- a/scientific-skills/pubmed-database/SKILL.md +++ b/scientific-skills/pubmed-database/SKILL.md @@ -1,6 +1,6 @@ --- name: pubmed-database -description: "Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use this for direct HTTP/REST work or custom API implementations." +description: Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use this for direct HTTP/REST work or custom API implementations. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pufferlib/SKILL.md b/scientific-skills/pufferlib/SKILL.md index 75e5112..45a78e4 100644 --- a/scientific-skills/pufferlib/SKILL.md +++ b/scientific-skills/pufferlib/SKILL.md @@ -1,6 +1,6 @@ --- name: pufferlib -description: This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs. +description: High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pydeseq2/SKILL.md b/scientific-skills/pydeseq2/SKILL.md index d5c3fe7..6417caa 100644 --- a/scientific-skills/pydeseq2/SKILL.md +++ b/scientific-skills/pydeseq2/SKILL.md @@ -1,6 +1,6 @@ --- name: pydeseq2 -description: "Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis." +description: Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pylabrobot/SKILL.md b/scientific-skills/pylabrobot/SKILL.md index 86f957c..a6f4a4e 100644 --- a/scientific-skills/pylabrobot/SKILL.md +++ b/scientific-skills/pylabrobot/SKILL.md @@ -1,6 +1,6 @@ --- name: pylabrobot -description: Laboratory automation toolkit for controlling liquid handlers, plate readers, pumps, heater shakers, incubators, centrifuges, and analytical equipment. Use this skill when automating laboratory workflows, programming liquid handling robots (Hamilton STAR, Opentrons OT-2, Tecan EVO), integrating lab equipment, managing deck layouts and resources (plates, tips, containers), reading plates, or creating reproducible laboratory protocols. Applicable for both simulated protocols and physical hardware control. +description: Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API, opentrons-integration may be simpler. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pymatgen/SKILL.md b/scientific-skills/pymatgen/SKILL.md index 6f94192..e037d23 100644 --- a/scientific-skills/pymatgen/SKILL.md +++ b/scientific-skills/pymatgen/SKILL.md @@ -1,6 +1,6 @@ --- name: pymatgen -description: "Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science." +description: Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pymc/SKILL.md b/scientific-skills/pymc/SKILL.md index 84beb83..0283d56 100644 --- a/scientific-skills/pymc/SKILL.md +++ b/scientific-skills/pymc/SKILL.md @@ -1,6 +1,6 @@ --- name: pymc-bayesian-modeling -description: "Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference." +description: Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference. license: Apache License, Version 2.0 metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pymoo/SKILL.md b/scientific-skills/pymoo/SKILL.md index aef8929..5267319 100644 --- a/scientific-skills/pymoo/SKILL.md +++ b/scientific-skills/pymoo/SKILL.md @@ -1,6 +1,6 @@ --- name: pymoo -description: "Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems." +description: Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems. license: Apache-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pyopenms/SKILL.md b/scientific-skills/pyopenms/SKILL.md index c4c953e..fec2472 100644 --- a/scientific-skills/pyopenms/SKILL.md +++ b/scientific-skills/pyopenms/SKILL.md @@ -1,6 +1,6 @@ --- name: pyopenms -description: Python interface to OpenMS for mass spectrometry data analysis. Use for LC-MS/MS proteomics and metabolomics workflows including file handling (mzML, mzXML, mzTab, FASTA, pepXML, protXML, mzIdentML), signal processing, feature detection, peptide identification, and quantitative analysis. Apply when working with mass spectrometry data, analyzing proteomics experiments, or processing metabolomics datasets. +description: Complete mass spectrometry analysis platform. Use for proteomics workflows feature detection, peptide identification, protein quantification, and complex LC-MS/MS pipelines. Supports extensive file formats and algorithms. Best for proteomics, comprehensive MS data processing. For simple spectral comparison and metabolite ID use matchms. license: 3 clause BSD license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pysam/SKILL.md b/scientific-skills/pysam/SKILL.md index eb38330..5511384 100644 --- a/scientific-skills/pysam/SKILL.md +++ b/scientific-skills/pysam/SKILL.md @@ -1,6 +1,6 @@ --- name: pysam -description: "Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines." +description: Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pytdc/SKILL.md b/scientific-skills/pytdc/SKILL.md index 0bdfdfd..04cf3b0 100644 --- a/scientific-skills/pytdc/SKILL.md +++ b/scientific-skills/pytdc/SKILL.md @@ -1,6 +1,6 @@ --- name: pytdc -description: "Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction." +description: Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/pytorch-lightning/SKILL.md b/scientific-skills/pytorch-lightning/SKILL.md index d456f6e..832a713 100644 --- a/scientific-skills/pytorch-lightning/SKILL.md +++ b/scientific-skills/pytorch-lightning/SKILL.md @@ -1,6 +1,6 @@ --- name: pytorch-lightning -description: "Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training." +description: Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training. license: Apache-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/qiskit/SKILL.md b/scientific-skills/qiskit/SKILL.md index 5433a06..52f7dd2 100644 --- a/scientific-skills/qiskit/SKILL.md +++ b/scientific-skills/qiskit/SKILL.md @@ -1,6 +1,6 @@ --- name: qiskit -description: Comprehensive quantum computing toolkit for building, optimizing, and executing quantum circuits. Use when working with quantum algorithms, simulations, or quantum hardware including (1) Building quantum circuits with gates and measurements, (2) Running quantum algorithms (VQE, QAOA, Grover), (3) Transpiling/optimizing circuits for hardware, (4) Executing on IBM Quantum or other providers, (5) Quantum chemistry and materials science, (6) Quantum machine learning, (7) Visualizing circuits and results, or (8) Any quantum computing development task. +description: IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use pennylane; for open quantum system simulations use qutip. license: Apache-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/qutip/SKILL.md b/scientific-skills/qutip/SKILL.md index fad711b..26c1da8 100644 --- a/scientific-skills/qutip/SKILL.md +++ b/scientific-skills/qutip/SKILL.md @@ -1,6 +1,6 @@ --- name: qutip -description: "Quantum mechanics simulations and analysis using QuTiP (Quantum Toolbox in Python). Use when working with quantum systems including: (1) quantum states (kets, bras, density matrices), (2) quantum operators and gates, (3) time evolution and dynamics (Schrödinger, master equations, Monte Carlo), (4) open quantum systems with dissipation, (5) quantum measurements and entanglement, (6) visualization (Bloch sphere, Wigner functions), (7) steady states and correlation functions, or (8) advanced methods (Floquet theory, HEOM, stochastic solvers). Handles both closed and open quantum systems across various domains including quantum optics, quantum computing, and condensed matter physics." +description: Quantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence, quantum optics, or cavity QED. Best for physics research, open system dynamics, and educational simulations. NOT for circuit-based quantum computing—use qiskit, cirq, or pennylane for quantum algorithms and hardware execution. license: BSD-3-Clause license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/rdkit/SKILL.md b/scientific-skills/rdkit/SKILL.md index 0a07c70..c3e6a0e 100644 --- a/scientific-skills/rdkit/SKILL.md +++ b/scientific-skills/rdkit/SKILL.md @@ -1,6 +1,6 @@ --- name: rdkit -description: "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." +description: 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. license: BSD-3-Clause license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/reactome-database/SKILL.md b/scientific-skills/reactome-database/SKILL.md index aecbfc7..968e1b2 100644 --- a/scientific-skills/reactome-database/SKILL.md +++ b/scientific-skills/reactome-database/SKILL.md @@ -1,6 +1,6 @@ --- name: reactome-database -description: "Query Reactome REST API for pathway analysis, enrichment, gene-pathway mapping, disease pathways, molecular interactions, expression analysis, for systems biology studies." +description: Query Reactome REST API for pathway analysis, enrichment, gene-pathway mapping, disease pathways, molecular interactions, expression analysis, for systems biology studies. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/research-grants/SKILL.md b/scientific-skills/research-grants/SKILL.md index 6fdec65..979c779 100644 --- a/scientific-skills/research-grants/SKILL.md +++ b/scientific-skills/research-grants/SKILL.md @@ -1,6 +1,6 @@ --- name: research-grants -description: "Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements." +description: Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/research-lookup/SKILL.md b/scientific-skills/research-lookup/SKILL.md index b1d930d..ef02e9b 100644 --- a/scientific-skills/research-lookup/SKILL.md +++ b/scientific-skills/research-lookup/SKILL.md @@ -1,6 +1,6 @@ --- name: research-lookup -description: "Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations." +description: Look up current research information using Perplexity Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/scanpy/SKILL.md b/scientific-skills/scanpy/SKILL.md index 6bb322a..47fd5e3 100644 --- a/scientific-skills/scanpy/SKILL.md +++ b/scientific-skills/scanpy/SKILL.md @@ -1,6 +1,6 @@ --- name: scanpy -description: "Single-cell RNA-seq analysis. Load .h5ad/10X data, QC, normalization, PCA/UMAP/t-SNE, Leiden clustering, marker genes, cell type annotation, trajectory, for scRNA-seq analysis." +description: Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata. license: SD-3-Clause license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/scientific-brainstorming/SKILL.md b/scientific-skills/scientific-brainstorming/SKILL.md index 3c2af70..316d3aa 100644 --- a/scientific-skills/scientific-brainstorming/SKILL.md +++ b/scientific-skills/scientific-brainstorming/SKILL.md @@ -1,6 +1,6 @@ --- name: scientific-brainstorming -description: "Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving." +description: Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/scientific-critical-thinking/SKILL.md b/scientific-skills/scientific-critical-thinking/SKILL.md index eb578b0..8445fbd 100644 --- a/scientific-skills/scientific-critical-thinking/SKILL.md +++ b/scientific-skills/scientific-critical-thinking/SKILL.md @@ -1,6 +1,6 @@ --- name: scientific-critical-thinking -description: "Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims." +description: Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/scientific-schematics/SKILL.md b/scientific-skills/scientific-schematics/SKILL.md index 3f5ae1d..d9dc684 100644 --- a/scientific-skills/scientific-schematics/SKILL.md +++ b/scientific-skills/scientific-schematics/SKILL.md @@ -1,6 +1,6 @@ --- name: scientific-schematics -description: "Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations." +description: Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/scientific-slides/SKILL.md b/scientific-skills/scientific-slides/SKILL.md index 8352fbd..0834f6d 100644 --- a/scientific-skills/scientific-slides/SKILL.md +++ b/scientific-skills/scientific-slides/SKILL.md @@ -1,6 +1,6 @@ --- name: scientific-slides -description: "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." +description: 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. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/scientific-visualization/SKILL.md b/scientific-skills/scientific-visualization/SKILL.md index 1dbaa0a..2630d66 100644 --- a/scientific-skills/scientific-visualization/SKILL.md +++ b/scientific-skills/scientific-visualization/SKILL.md @@ -1,6 +1,6 @@ --- name: scientific-visualization -description: "Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots." +description: Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/scientific-writing/SKILL.md b/scientific-skills/scientific-writing/SKILL.md index 0f22a46..2c848fd 100644 --- a/scientific-skills/scientific-writing/SKILL.md +++ b/scientific-skills/scientific-writing/SKILL.md @@ -1,6 +1,6 @@ --- name: scientific-writing -description: "Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process: (1) create section outlines with key points using research-lookup, (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions." +description: Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/scikit-bio/SKILL.md b/scientific-skills/scikit-bio/SKILL.md index 507fe72..96ee627 100644 --- a/scientific-skills/scikit-bio/SKILL.md +++ b/scientific-skills/scikit-bio/SKILL.md @@ -1,6 +1,6 @@ --- name: scikit-bio -description: "Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis." +description: Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis. license: BSD-3-Clause license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/scvi-tools/SKILL.md b/scientific-skills/scvi-tools/SKILL.md index 0c485c9..487a455 100644 --- a/scientific-skills/scvi-tools/SKILL.md +++ b/scientific-skills/scvi-tools/SKILL.md @@ -1,6 +1,6 @@ --- name: scvi-tools -description: This skill should be used when working with single-cell omics data analysis using scvi-tools, including scRNA-seq, scATAC-seq, CITE-seq, spatial transcriptomics, and other single-cell modalities. Use this skill for probabilistic modeling, batch correction, dimensionality reduction, differential expression, cell type annotation, multimodal integration, and spatial analysis tasks. +description: Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy. license: BSD-3-Clause license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/seaborn/SKILL.md b/scientific-skills/seaborn/SKILL.md index ed43f62..74f9607 100644 --- a/scientific-skills/seaborn/SKILL.md +++ b/scientific-skills/seaborn/SKILL.md @@ -1,6 +1,6 @@ --- name: seaborn -description: "Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for exploratory analysis and publication figures." +description: Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization. license: BSD-3-Clause license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/stable-baselines3/SKILL.md b/scientific-skills/stable-baselines3/SKILL.md index 13491e1..5473431 100644 --- a/scientific-skills/stable-baselines3/SKILL.md +++ b/scientific-skills/stable-baselines3/SKILL.md @@ -1,6 +1,6 @@ --- name: stable-baselines3 -description: Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill should be used when users request RL algorithm implementation, agent training, environment design, or RL experimentation. +description: Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/statistical-analysis/SKILL.md b/scientific-skills/statistical-analysis/SKILL.md index ac9b72a..e5a4a74 100644 --- a/scientific-skills/statistical-analysis/SKILL.md +++ b/scientific-skills/statistical-analysis/SKILL.md @@ -1,6 +1,6 @@ --- name: statistical-analysis -description: "Statistical analysis toolkit. Hypothesis tests (t-test, ANOVA, chi-square), regression, correlation, Bayesian stats, power analysis, assumption checks, APA reporting, for academic research." +description: Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/statsmodels/SKILL.md b/scientific-skills/statsmodels/SKILL.md index 9a2aa9a..23a9ea2 100644 --- a/scientific-skills/statsmodels/SKILL.md +++ b/scientific-skills/statsmodels/SKILL.md @@ -1,6 +1,6 @@ --- name: statsmodels -description: "Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis." +description: Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis. license: BSD-3-Clause license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/string-database/SKILL.md b/scientific-skills/string-database/SKILL.md index 04b3552..ff8508b 100644 --- a/scientific-skills/string-database/SKILL.md +++ b/scientific-skills/string-database/SKILL.md @@ -1,6 +1,6 @@ --- name: string-database -description: "Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology." +description: Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/torch_geometric/SKILL.md b/scientific-skills/torch_geometric/SKILL.md index 97ec3d9..77b0b87 100644 --- a/scientific-skills/torch_geometric/SKILL.md +++ b/scientific-skills/torch_geometric/SKILL.md @@ -1,6 +1,6 @@ --- name: torch-geometric -description: "Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning." +description: Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/torchdrug/SKILL.md b/scientific-skills/torchdrug/SKILL.md index 5f0d6a1..a6db783 100644 --- a/scientific-skills/torchdrug/SKILL.md +++ b/scientific-skills/torchdrug/SKILL.md @@ -1,6 +1,6 @@ --- name: torchdrug -description: "Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets, for PyTorch-based ML on molecules, proteins, and biomedical graphs." +description: PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc. license: Apache-2.0 license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/treatment-plans/SKILL.md b/scientific-skills/treatment-plans/SKILL.md index eab3fb2..50bc71d 100644 --- a/scientific-skills/treatment-plans/SKILL.md +++ b/scientific-skills/treatment-plans/SKILL.md @@ -1,6 +1,6 @@ --- name: treatment-plans -description: "Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability." +description: Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability. allowed-tools: [Read, Write, Edit, Bash] license: MIT license metadata: diff --git a/scientific-skills/umap-learn/SKILL.md b/scientific-skills/umap-learn/SKILL.md index 253d74a..c2c5622 100644 --- a/scientific-skills/umap-learn/SKILL.md +++ b/scientific-skills/umap-learn/SKILL.md @@ -1,6 +1,6 @@ --- name: umap-learn -description: "UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data." +description: UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data. license: BSD-3-Clause license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/uniprot-database/SKILL.md b/scientific-skills/uniprot-database/SKILL.md index f66869a..27d6c16 100644 --- a/scientific-skills/uniprot-database/SKILL.md +++ b/scientific-skills/uniprot-database/SKILL.md @@ -1,6 +1,6 @@ --- name: uniprot-database -description: "Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control." +description: Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/uspto-database/SKILL.md b/scientific-skills/uspto-database/SKILL.md index 4d13a8a..24712f1 100644 --- a/scientific-skills/uspto-database/SKILL.md +++ b/scientific-skills/uspto-database/SKILL.md @@ -1,6 +1,6 @@ --- name: uspto-database -description: "Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches." +description: Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches. license: Unknown metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/vaex/SKILL.md b/scientific-skills/vaex/SKILL.md index cf64006..186eadc 100644 --- a/scientific-skills/vaex/SKILL.md +++ b/scientific-skills/vaex/SKILL.md @@ -1,6 +1,6 @@ --- name: vaex -description: Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that don't fit in memory. +description: Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/zarr-python/SKILL.md b/scientific-skills/zarr-python/SKILL.md index 3119de9..9396c21 100644 --- a/scientific-skills/zarr-python/SKILL.md +++ b/scientific-skills/zarr-python/SKILL.md @@ -1,6 +1,6 @@ --- name: zarr-python -description: "Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines." +description: Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines. license: MIT license metadata: skill-author: K-Dense Inc. diff --git a/scientific-skills/zinc-database/SKILL.md b/scientific-skills/zinc-database/SKILL.md index ab8b9a4..57f15a0 100644 --- a/scientific-skills/zinc-database/SKILL.md +++ b/scientific-skills/zinc-database/SKILL.md @@ -1,6 +1,6 @@ --- name: zinc-database -description: "Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery." +description: Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery. license: Unknown metadata: skill-author: K-Dense Inc.