Skill UI

Automates detection and deep exploratory analysis across 200+ scientific data formats, assessing quality, extracting metadata, and recommending visualizations while generating markdown reports that guide downstream workflows and highlight structure and distributions.

Geniml is a comprehensive Python package designed for applying machine learning techniques to genomic interval data stored in BED files. It provides advanced methods like Region2Vec, BEDspace, and scEmbed to learn embeddings for genomic regions, single cells, and metadata. Use it for dimension reduction, clustering, similarity searches, and sophisticated bioinformatic analyses in genomics. Core functionalities include: learning region embeddings (Region2Vec), joint embeddings of regions and metadata (BEDspace), single-cell chromatin accessibility embedding (scEmbed), and building consensus...

GeoPandas extends pandas for geospatial vector data, enabling reading/writing shapefiles, GeoJSON, GeoPackage and PostGIS, performing CRS management, spatial joins, overlays, buffering, area/distance calculations, and producing static or interactive choropleth maps.

Detects system CPU, GPU, memory, and disk availability before heavy scientific tasks, writing `.claude_resources.json` with strategic recommendations (parallelism, out-of-core, GPU acceleration) so analysts choose appropriate compute approaches.

gget is a CLI/Python client that unifies querying over 20+ bioinformatics databases, letting researchers fetch gene info, sequences, BLAST results, structures, and enrichment data interactively or within scripts.

Gtars is a high-performance toolkit written in Rust with Python bindings, specialized for computational genomics. It provides advanced functionality for manipulating genomic interval data, including overlap detection (IGD), coverage track generation (BigWig), and genomic tokenization for machine learning preprocessing. Ideal for researchers working with BED files, single-cell data, and ML-driven biological models.

Histolab streamlines whole-slide microscopy by automating tissue detection, tile extraction, and stain normalization for H&E scans, making it ideal for lightweight dataset prep and quick tile-based analysis.

Hypogenic automates LLM-driven hypothesis generation and testing over tabular datasets, blending literature insights with empirical analysis to accelerate discovery in domains like deception detection or AI content evaluation.

This skill acts as an elite Art Director for generating premium, highly actionable, and structurally sound frontend design references. It moves beyond generic AI aesthetics by enforcing principles like strong hierarchy, generous spacing, and image-led composition. Ideal for creating realistic, development-ready concepts for landing pages, hero sections, and multi-section websites.

Latch is a Python framework designed for building, deploying, and managing complex, serverless bioinformatics pipelines. It allows users to define workflows using decorators for native Python, Nextflow, or Snakemake, while providing robust tools for cloud data management (LatchFile/LatchDir) and precise resource allocation (GPU/CPU). Ideal for running large-scale analyses such as RNA-seq and protein structure prediction (AlphaFold).

Guides using matplotlib to craft static, animated, and interactive plots through both pyplot and object-oriented APIs, detailing styling, subplots, and export options for publication-ready scientific workflows.

Medchem Filtering Toolkit is a Python library offering drug-likeness heuristics, structural alert and PAINS filters, group detection, catalogs, and complexity scoring to triage compound libraries and prioritize leads in drug discovery workflows.