K-Dense-AI

A multi-objective optimization framework featuring NSGA-II, NSGA-III, MOEA/D, Pareto fronts, and constraint handling. It includes benchmarks like ZDT and DTLZ for engineering design and optimization problems.

Comprehensive citation management for academic research, allowing you to search Google Scholar and PubMed, extract metadata, validate citations, and generate BibTeX entries. Use this skill to find papers, verify citations, convert DOIs, or ensure reference accuracy in scientific writing.

Generates professional clinical decision support (CDS) documents for pharmaceutical and clinical research, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). It supports GRADE evidence grading, statistical analysis, and biomarker integration.

Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, and integrate with Protocols.io/Jupyter/REDCap for programmatic ELN workflows.

Google quantum computing framework. Ideal for Google Quantum AI hardware, designing noise-aware circuits, and quantum characterization experiments, focusing on noise modeling and low-level circuit design.

Parses FCS (Flow Cytometry Standard) files v2.0-3.1. Extracts events as NumPy arrays, reads metadata/channels, and converts to CSV/DataFrame for flow cytometry data preprocessing.

Medicinal chemistry filters for compound triage. Apply drug-likeness rules (Lipinski, Veber, CNS), structural alert catalogs (PAINS, NIBR, ChEMBL), complexity metrics, and the medchem query language for library filtering.

This skill provides structured manuscript and grant review using checklist-based evaluation, ideal for formal peer reviews assessing methodology, statistical validity, and reporting standards compliance with constructive feedback.

Formulates structured, testable hypotheses from experimental observations or data, including predictions, proposed mechanisms, and experimental designs, following the scientific method.

Infers gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). It's used to analyze transcriptomics data (bulk/single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions, supporting distributed computation for large datasets.

A comprehensive Python toolkit for creating, analyzing, and visualizing complex networks and graphs. It's ideal for working with network data, analyzing relationships, computing graph algorithms, detecting communities, and visualizing network topologies, applicable to fields like social and biological networks.

Performs comprehensive exploratory data analysis on scientific data files across 200+ formats. It automatically detects file types and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations to understand data structure, content, and quality.

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.

NGS analysis toolkit for BAM to bigWig conversion, QC (correlation, PCA, fingerprints), and visualization of ChIP-seq, RNA-seq, and ATAC-seq data through heatmaps/profiles (TSS, peaks).

Conducts comprehensive, systematic literature reviews across multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). Ideal for meta-analyses and research synthesis in biomedical, scientific, and technical domains, it generates professionally formatted Markdown and PDF documents.

MATLAB and GNU Octave for numerical computing, including matrix operations, data analysis, visualization, and scientific computing. Use for scripts involving linear algebra, signal/image processing, differential equations, optimization, statistics, or scientific visualizations, as well as for syntax help, functions, or conversions in MATLAB.

PyTorch Geometric (PyG) is for graph neural networks, supporting node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use it specifically with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.

A self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. It helps organize research materials, ingest diverse content sources, generate AI-powered notes and summaries, create podcasts, and chat with documents.

Differential gene expression analysis (Python DESeq2). Identifies DE genes from bulk RNA-seq counts using Wald tests, FDR correction, and generating volcano/MA plots for RNA-seq analysis.

A vendor-agnostic lab automation framework for controlling multiple equipment types (e.g., Hamilton, Tecan, Opentrons) and unifying programming across different vendors. Ideal for complex workflows, multi-vendor setups, and simulation, though Opentrons-only protocols might be simpler with opentrons-integration.

Programmatically query the CELLxGENE Census (61M+ cells) to get expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. It is best for population-scale queries and reference atlas comparisons.

Distributed computing for larger-than-RAM pandas/NumPy workflows, scaling existing code beyond memory or across clusters. Ideal for parallel file processing, distributed ML, and integration with pandas.

Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench) for glycoprotein engineering, therapeutic antibody optimization, and vaccine design.

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Access large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research without authentication, querying by metadata, visualizing in browser, and checking licenses.

Molecular ML for property prediction (ADMET, toxicity) using diverse featurizers and pre-built datasets, supporting traditional ML or GNNs. It's excellent for quick experiments with pre-trained models and extensive featurization, often leveraging MoleculeNet benchmarks.

Hugging Science is a curated catalog of scientific datasets, models, blog posts, and interactive Spaces, designed for users engaged in AI/ML work across various scientific domains like biology, chemistry, and physics.

Statistical visualization with pandas integration for quick exploration of distributions, relationships, and categorical comparisons. It's best for box plots, violin plots, pair plots, and heatmaps, built on matplotlib.

Query the U.S. Treasury Fiscal Data REST API for federal financial data, no API key required. Access national debt, Treasury statements, securities auctions, interest and foreign exchange rates, savings bonds, or U.S. government revenue and spending statistics.

Constraint-based metabolic modeling (COBRA) covers FBA, FVA, gene knockouts, flux sampling, and SBML models for systems biology and metabolic engineering analysis.

Deep generative models for single-cell omics are ideal for advanced modeling, batch effects, and multimodal data, offering probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, and multi-modal integration (TOTALVI, MultiVI). For standard analysis pipelines, use scanpy.

Build and analyze phylogenetic trees using MAFFT, IQ-TREE 2, and FastTree. Visualize them with ETE3 or FigTree for applications in evolutionary analysis, microbial genomics, and molecular clock studies.

Perform zero-shot time series forecasting with Google's TimesFM foundation model. It handles any univariate time series (sales, sensors, energy, vitals, weather) without custom model training, supporting CSV/DataFrame/array inputs for point forecasts and prediction intervals, and includes a preflight system checker.

A hardware-agnostic quantum ML framework with automatic differentiation, ideal for training quantum circuits via gradients, building hybrid quantum-classical models, and ensuring device portability across major quantum platforms. It's best for variational algorithms, quantum neural networks, and integration with PyTorch/JAX/TensorFlow.

Query the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biological data including genes, drugs, diseases, phenotypes, and more.

This skill evaluates scientific claims and evidence quality, useful for assessing experimental design, identifying biases, and applying evidence grading frameworks. It's ideal for understanding evidence quality and identifying flaws, but not for formal peer review writing.

Create professional infographics with Nano Banana Pro AI, featuring smart iterative refinement and Gemini 3 Pro for quality review. It integrates research and web search for accurate data, supporting 10 infographic types, 8 industry styles, and colorblind-safe palettes.

This skill offers production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with a scikit-learn-like API, suitable for standard RL experiments and quick prototyping with Gymnasium environments. For high-performance parallel training or multi-agent systems, pufferlib is recommended instead.

Extract cognitive patterns and thinking fingerprints from any text. Use this skill to analyze how someone thinks, understand cognitive style, profile writing or speech patterns, or compare thinking styles between people.

Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. It's ideal for deploying AI/ML models, running GPU-accelerated workloads, serving web endpoints, and scaling Python code to cloud containers with the Modal SDK.

A computational materials science toolkit for crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, and format conversion.

A comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems, assisting with gap analysis, Quality Manuals, procedures, Medical Device Files, and understanding ISO 13485 requirements.

A Python framework for computational fluid dynamics simulations, supporting Navier-Stokes (2D/3D), shallow water, and stratified flows, as well as turbulence and vortex dynamics analysis. It offers pseudospectral methods with FFT, HPC support, and comprehensive output analysis.

PyHealth enables building deep-learning pipelines for healthcare, supporting the loading of diverse EHR/signal/imaging datasets, defining tasks like mortality prediction or drug recommendation, and training with various models.

Utilizes PyTorch Lightning to organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, and implement data pipelines, callbacks, logging, and distributed training for scalable neural network training.

Standard single-cell RNA-seq analysis pipeline for quality control, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Ideal for exploratory scRNA-seq analysis using established workflows.

Search 78 public scientific, biomedical, materials science, and economic databases via REST APIs, covering fields like physics, chemistry, biology, and materials.

Zarr-Python 3 provides chunked N-D arrays for cloud storage, featuring compressed arrays, parallel I/O, S3/GCS compatibility via fsspec, and integration with NumPy/Dask/Xarray for large-scale scientific computing pipelines.

This high-performance reinforcement learning framework is optimized for speed and scale, ideal for fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (e.g., Atari, NetHack), achieving 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3.