Skill UI

A sophisticated tool for optimizing crypto trades across multiple Decentralized Exchanges (DEXs). It aggregates quotes from major aggregators (like 1inch, Paraswap, and 0x) to find the optimal multi-hop route, calculate split orders for large trades, and assess MEV risk, ensuring minimum slippage and gas costs.

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.

PathML is a Python toolkit for computational pathology workflows, loading 160+ slide formats, preprocessing H&E images, constructing spatial graphs, training HoVer-Net/HACTNet models, and analyzing multiplex imaging for ML-ready pathology data.

Pysam offers Python bindings to htslib for reading and writing SAM/BAM/CRAM alignments, VCF/BCF variants, and FASTA/FASTQ sequences, enabling coverage stats, pileup analysis, variant queries, and seamless integration into NGS pipelines.

This skill provides programmatic access to the CZ CELLxGENE Census, a comprehensive collection of versioned public single-cell and spatial transcriptomics data. It enables efficient querying of population-scale cell metadata, gene expression slices, and embeddings without downloading entire datasets. Suitable for analyzing human, mouse, and other organism data across tissues and diseases. Integrates with Scanpy, AnnData, and TileDB-SOMA for large-scale analysis and machine learning workflows.

Python library for digital pathology whole slide images: tissue detection, tile extraction, filters, and stain normalization. Ideal for preparing H&E datasets for deep learning and quick tile-based analysis.

Build local, research-only computational pathology workflows with PathML: load and tile whole-slide images, run preprocessing and QC pipelines, manage h5path data, quantify multiplex images, construct spatial graphs, and plan bounded model inference.

A Python library for reading, querying, filtering, and writing genomic file formats including SAM/BAM/CRAM, VCF/BCF, FASTA/FASTQ, and tabix data. Supports pileup, coverage analysis, indexing, and CRAM reference operations with HTSlib integration. Ideal for bioinformatics workflows requiring low-level streaming access to genomic data.

This meta-skill fetches the top academic papers from the arXiv API in a specified category. It generates a structured digest for each paper, renders this digest into a professional PowerPoint (PPTX) presentation (one slide per paper), and finally saves the comprehensive digest to long-term memory for future reference. Designed for daily 'morning briefings' of academic research.

This guide outlines rigorous standards for conducting heterogeneity analysis in economic research. It stresses that heterogeneity should not merely involve slicing data by region or size, but must be theoretically driven, linking multiple dimensions (e.g., ownership, financing constraints, industry type) to core economic mechanisms. The analysis must demonstrate significant group differences and clearly connect findings to differential policy implications, elevating the discussion from mere observation to actionable policy science.

A comprehensive guide on transforming preliminary research findings into publication-quality manuscripts for top-tier finance journals. It covers best practices for slimming over-wide regression tables, generating standardized figures (IRF, Event Study), ensuring continuous numbering, and adhering to strict academic formatting standards.