K-Dense
Official@k-dense-ai · United States of America
A world leader in empowering scientists with AI agentic tools.
Agent Skills by K-Dense
Showing 383 vetted skills indexed across 6 GitHub repositories.
K-Dense-AIpathogen-variant-surveillance
Query live pathogen genomic surveillance data through the GenSpectrum LAPIS API.
K-Dense-AIpi-agent
Configure, extend, and integrate the Pi terminal coding harness via CLI, SDK, and RPC.
K-Dense-AIbenchling-integration
Automate Benchling registry, inventory, ELN, and workflow operations via the Python SDK and REST API.
K-Dense-AIlab-hardware-cad
Design parametric laboratory hardware in build123d and export verified STEP, STL, and DXF files.
K-Dense-AIdeepspot-m
Generate virtual spatial transcriptomics from H&E histology tiles with DeepSpot-M.
K-Dense-AIiso-standards-readiness
Organizes and structurally validates readiness evidence for ISO 13485, 14971, 17025, and 15189 standards.
K-Dense-AInetworkx
Create, analyze, and visualize complex networks and graphs in Python with NetworkX.
K-Dense-AIanndata
Create, read, and manipulate annotated data matrices in h5ad and zarr formats.
K-Dense-AIscikit-survival
Build and evaluate right-censored survival models with scikit-survival pipelines and censoring-aware metrics.
K-Dense-AIscientific-brainstorming
Facilitates structured scientific ideation with provenance tracking, adversarial review, and transparent evaluation matrices.
K-Dense-AIpymc
Build and validate Bayesian models in Python using PyMC MCMC and variational inference.
K-Dense-AIpkpd-modeling
Analyze pharmacokinetic and pharmacodynamic data with NCA, compartmental fitting, and population PK scripts.
K-Dense-AIresearch-lookup
Compile verified scholarly references and evidence packets for scientific manuscripts using Parallel Search and Extract.
K-Dense-AIshap
Compute and validate SHAP feature attributions for machine-learning model explanations.
K-Dense-AIumap-learn
Generate nonlinear dimensionality reduction embeddings with UMAP for visualization, clustering, and supervised learning.
K-Dense-AIimaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons.
K-Dense-AIgeomaster
Process satellite imagery, vector data, and rasters for geospatial analysis and Earth observation.
K-Dense-AIsympy
Perform exact symbolic mathematics in Python including algebra, calculus, equation solving, and code generation.
K-Dense-AIvaex
Process and analyze billion-row tabular datasets with out-of-core DataFrames.
K-Dense-AIonekgpd
Query individual-level variants, carriers, and kinship in the 1000 Genomes Project cohort.
K-Dense-AIget-available-resources
Detect effective CPU, memory, disk, scheduler, and accelerator limits into a redacted JSON snapshot.
K-Dense-AIparallel-web
Runs web search, URL extraction, deep research, and entity enrichment through the Parallel CLI.
K-Dense-AIexploratory-data-analysis
Profile scientific CSV, JSON, NumPy, HDF5, FASTA, and image files with bounded local analysis.
K-Dense-AIexperimental-design
Generate randomized allocation schedules and DOE matrices for planning experiments before data collection.
Frequently Asked Questions About K-Dense
FAQPage SchemaWhat scientific tasks can I perform using K-Dense?▼
You can perform complex bioinformatics tasks including single-cell RNA-seq analysis, protein structure prediction, mass spectrometry processing, and genomic interval manipulation. The platform also supports molecular dynamics simulations, metabolic modeling, and the generation of publication-ready scientific figures and manuscripts.
Who is the target persona for these scientific capabilities?▼
The primary users are computational biologists, bioinformaticians, medicinal chemists, and clinical researchers. These professionals utilize the platform to bridge the gap between raw experimental data and structured, reproducible research findings through standardized computational pipelines.
What are the prerequisites for running these scientific analyses?▼
Users require access to standard Python environments and specific domain-relevant data formats such as AnnData, BAM/SAM, PDB, or DICOM files. Many modules rely on established libraries like RDKit, Biopython, and PyTorch, which must be configured within your local or cloud-based research environment.