Skill UI

This skill guides the design and implementation of a complete, production-grade Machine Learning pipeline. It employs a multi-agent orchestration workflow, systematically covering all stages of the ML lifecycle: data ingestion and quality assurance, feature engineering, model training, optimization, and robust deployment (MLOps). It ensures built-in reproducibility, monitoring, and scalability.

Mastering the full lifecycle of machine learning models from data ingestion to deployment. This expertise covers building robust, production-grade MLOps pipelines using orchestrators like Kubeflow, Airflow, or Prefect. Key skills include feature store implementation with Feast, rigorous data validation, experiment tracking (e.g., MLflow), model registry management, and automated deployment workflows. Essential for automating model training and ensuring reproducibility at scale.

Pyvene is a declarative framework designed for performing causal interventions on PyTorch neural networks. It allows researchers to conduct advanced experiments such as activation patching, causal tracing (ROME-style), and interchange intervention training (IIT). Use this library when you need to test causal hypotheses about model behavior, deeply interpret model components, or ensure reproducibility in advanced AI research.

A comprehensive skill for managing academic citations throughout the research and writing process. It guides users through searching major databases (Google Scholar, PubMed), extracting accurate metadata from diverse IDs (DOI, PMID, arXiv), validating citation integrity, and generating standardized BibTeX entries. Essential for maintaining scientific writing accuracy and reproducibility.

A comprehensive framework for planning, configuring, executing, and analyzing complex Computational Fluid Dynamics (CFD) simulations using pseudospectral methods. It enforces a rigorous, multi-stage workflow, guiding users from defining state equations and boundary conditions to generating resource estimates, running dry-runs, and preparing site-specific MPI jobs. Designed for high-fidelity scientific computing and reproducibility.

Geniml provides a robust framework for running machine learning and statistical workflows over genomic interval sets. It treats coordinates, assemblies, and model artifacts as explicit contracts, enabling users to validate data structures (like BED files) and plan complex runs (such as Region2Vec or scEmbed) locally. The tool emphasizes reproducibility, adherence to biological data standards, and running without unnecessary network calls.

PathML is a robust computational platform engineered for local, research-only workflows in computational pathology. It facilitates comprehensive analysis pipelines, including whole slide image (WSI) loading and tiling, preprocessing, quality control (QC), quantification of multiplex images, and the construction of spatial graphs. Designed with strict adherence to data privacy and research reproducibility, it supports advanced biological data analysis.

A comprehensive tool supporting rigorous, evidence-bounded, and structured peer-review of scientific manuscripts, research protocols, and academic proposals. It guides reviewers through critical assessments of methods, statistics, ethical compliance, reproducibility, and claim-evidence alignment, while strictly enforcing confidentiality and human accountability throughout the review process.

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.

This skill guides the systematic process of conducting comprehensive literature reviews across multiple academic databases (e.g., PubMed, arXiv, Semantic Scholar). It supports meta-analyses, scoping reviews, and state-of-the-art investigations. The rigorous workflow includes structured searching, data extraction, citation verification, thematic synthesis, and generating publication-quality reports (PDF/Markdown) complete with mandatory scientific schematics (like PRISMA flow diagrams) to ensure academic rigor and reproducibility.

The BIDS skill provides a comprehensive framework for organizing, standardizing, and managing complex neuroscience and biomedical datasets. It covers querying, validating, and converting various modalities (MRI, EEG, MEG, etc.) to ensure compliance with the BIDS standard for research reproducibility and efficient data sharing.

This skill orchestrates a complete, reproducible pipeline for bulk RNA-seq differential expression analysis. It guides users from raw FASTQ reads through QC, trimming, alignment (STAR/Salmon), quantification, generating a gene-level counts matrix, and concluding with differential expression analysis (DESeq2) and pathway enrichment. It ensures statistical soundness and reproducibility by connecting dedicated tools and enforcing proper experimental design.