Explore skills

Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. Use when users ask for recent project recommendations, canonical paper details, markdown-based summaries, recommendation feedback, feed export, or Atom feed URLs.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. It's used for genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. This skill is ideal for accelerating NumPy, pandas, scikit-learn, scikit-image, NetworkX, GeoPandas, or Faiss workloads, covering physics simulation, differentiable rendering, and particle systems.

This tool performs spectral similarity analysis and compound identification for metabolomics, comparing mass spectra, computing similarity scores, and identifying unknown compounds from spectral libraries. It is ideal for metabolite identification, spectral matching, and library searching.

A fast in-memory DataFrame library for datasets that fit in RAM, ideal when pandas is too slow. It features lazy evaluation, parallel execution, and an Apache Arrow backend, making it suitable for 1-100GB datasets and ETL pipelines.

This skill demonstrates using the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval, covering various assays like binding, screening, BLI/SPR, and thermostability, and is triggered by relevant keywords or code imports.

A meta-skill for creating publication-ready figures, including multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (e.g., Nature, Science, Cell). It orchestrates matplotlib/seaborn/plotly with publication styles, but for quick exploration, use seaborn or plotly directly.

scVelo performs RNA velocity analysis to estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data, complementing Scanpy/scVI-tools for trajectory inference.

This skill processes and analyzes large tabular datasets (billions of rows) that exceed available RAM, excelling at out-of-core DataFrame operations, fast aggregations, and efficient visualization. It's ideal for working with massive CSV/HDF5/Arrow/Parquet files and performing quick statistics on big data.

Use when you need exact symbolic math in Python — algebra, calculus, equation solving, symbolic linear algebra, or code generation via lambdify/LaTeX. Prefer NumPy or SciPy when floating-point approximations are sufficient.

A comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill for working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, and handling competing risks.

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Gemini 3.1 Pro Preview ensures quality, regenerating only if below your document's threshold, specializing in neural networks, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.