Skill UI

This guide provides comprehensive, version-aware documentation for using PufferLib in reinforcement learning pipelines. It details best practices for adapting Gymnasium/PettingZoo environments, managing different PufferLib versions (3.0.0 vs 4.0 source), and executing safe, reproducible training and evaluation routines. Key focus areas include environment contract validation, sandboxing native builds, and maintaining data provenance.

pydicom is a comprehensive Python library designed for reading, inspecting, writing, and transforming local DICOM datasets and associated pixel data. It supports complex metadata handling, various transfer syntaxes, and provides tools for bounded de-identification and preflight checks. It is essential for medical image processing pipelines that require robust handling of Protected Health Information (PHI).

PyHealth is a modular Python toolkit designed for developing deep learning pipelines in clinical and healthcare settings. It provides a standardized 5-stage framework (Dataset → Task → Model → Trainer → Metrics) to handle complex, multi-modal data, including EHR records, physiological signals, and medical imaging. Use cases include predicting mortality, readmission risks, recommending drugs, or performing medical code mapping (ICD/ATC).

PyLabRobot provides a comprehensive, software-only framework for developing and reviewing complex laboratory automation protocols, including liquid handling and resource management. It simulates offline device interactions and resource tracking, ensuring rigorous planning without physical hardware connection. It mandates explicit human verification before any live execution, prioritizing safety and reproducibility.

A powerful Python library for analyzing, validating, converting, and transforming complex materials structures and associated computational data. It provides functionalities for handling compositions, periodic crystals, molecules, local phase diagrams, symmetry assignments, and electronic structure I/O, ensuring strict provenance tracking for all transformations.

PyOpenMS is a powerful Python library providing bindings to the OpenMS platform for comprehensive mass spectrometry data analysis. It supports end-to-end workflows in proteomics and metabolomics, including feature detection, peptide/protein identification, quantification (label-free/isobaric), and advanced data processing. Users can leverage ready-to-run scripts for tasks like format conversion, accurate mass searching, and multi-sample quantification.

PySam provides a powerful Python interface for low-level, streaming access to HTSlib-supported genomic data formats. It enables reading, querying, filtering, and writing complex formats such as SAM/BAM/CRAM, VCF/BCF, FASTA/FASTQ, and tabix-indexed tables. It is essential for bioinformatics pipelines requiring precise control over genomic data manipulation, including pileup and coverage calculations.

PyTDC is a specialized Python package designed to interact with the Therapeutics Data Commons. It facilitates the discovery of machine learning tasks, loading approved datasets, generating task-appropriate data splits, and evaluating predictions for drug discovery research. The tool strongly emphasizes performing metadata-only discovery and planning before initiating resource-intensive data downloads or network operations.

Provides comprehensive guidance on determining the optimal scaling strategy for Qdrant vector databases. Covers when to transition from vertical to horizontal scaling, how to select the right number of nodes and shards, and best practices for setting replication factors to ensure zero-downtime operation and fault tolerance. Also details proper shard management and common scaling pitfalls to avoid.

RDKit is a comprehensive cheminformatics library providing robust Python APIs for molecular structure manipulation and analysis. It supports tasks ranging from molecular I/O (SMILES, SDF) and calculating physical descriptors (MW, LogP) to advanced substructure searching, 3D coordinate generation, and chemical reaction modeling. It is an essential toolkit for drug discovery, computational chemistry, and academic cheminformatics research.

Master the art of writing highly competitive research proposals for major funding bodies, including NSF, NIH, DOE, DARPA, and NSTC. This skill provides comprehensive guidance on structuring technical narratives, developing specific aims, justifying budgets, incorporating broader impact statements, and ensuring compliance with diverse agency-specific guidelines and formatting requirements.

Provides developmental, qualitative, and evidence-traceable review of scholarly works (papers, protocols, ideas). It also rigorously audits low-stakes research assessment rubrics for construct validity, fairness, and governance. Crucially, this tool is strictly forbidden from making high-impact personnel decisions, ranking individuals, or determining final outcomes.