Skill UI

Provides a detailed, multi-platform workflow to monitor long-running computational experiments. It checks the status of jobs across various environments (SSH, vast.ai, Modal), collects screen logs, fetches structured JSON results, and pulls detailed training metrics (loss curves, accuracy) from Weights & Biases (W&B). Essential for MLOps and automated result review.

This skill provides a comprehensive framework for building, registering, debugging, and operating complex bioinformatics workflows on the Latch platform. It supports multiple industry-standard pipelines (Nextflow, Snakemake) and utilizes the Python SDK, CLI, and Latch Data/Registry. Use this when developing, deploying, or managing robust, data-intensive computational pipelines in a controlled environment.

This guide provides a comprehensive methodology for load testing and capacity planning within Snowflake data warehouses. It covers optimizing query performance by adjusting warehouse sizes (Scale UP), simulating high concurrency using multi-threading (Scale OUT), and configuring advanced scaling policies (Standard, Economy, Maximized). Users can benchmark critical queries using SQL and simulate real-world user traffic using Python, ensuring robust and cost-efficient production environments.

Provides essential guidelines for designing rigorous, generalizable field experiments in crop research. Covers multi-environment trials (MET), proper randomization, blocking strategies, split-plot designs, and Genotype-by-Environment (G×E) analysis. Use this tool when planning or defending the scientific rigor of an agricultural manuscript.

A comprehensive guide for executing and reporting rigorous analyses in global environmental change (GEC) research. This skill covers norms for quantitative, qualitative, and mixed-methods studies, emphasizing honest uncertainty reporting, robust heterogeneity testing, ensuring reproducibility, and integrating multiple data strands to withstand expert, interdisciplinary review.

This guide provides a comprehensive framework for authors to rigorously defend their research design in manuscripts concerning Global Environmental Change (GEC). It covers methodological pluralism, including quantitative causal inference, qualitative case studies, experiments, and mixed-methods integration. Learn how to strengthen your design, justify causal claims, address confounders, and link local evidence to multi-scale global processes.

This package ensures full reproducibility for international macroeconomics research. It is designed for projects utilizing complex, multi-source, and often restricted data (such as IMF or central bank files). It mandates capturing the entire data lineage, pinning the execution environment (R, Python, Stata), and documenting access instructions, allowing any authorized replicator to rebuild the analysis from scratch.

A comprehensive framework designed to ensure environmental economics manuscripts meet rigorous data-availability and reproducibility standards, especially for journals like JEEM. This package guides users to document the entire research pipeline, handling complex issues like data versioning, proprietary satellite/admin data, and multi-step spatial operations by establishing a credible end-to-end reproduction path.

A comprehensive guide to ensuring the quantitative rigor and full reproducibility of econometrics manuscripts, particularly for submissions to high-tier journals like QE. Covers structural estimation (GMM, MSM), moment construction, data cleaning best practices, and comprehensive validation checks (e.g., multi-start, Monte Carlo recovery). It ensures that all results can be regenerated from raw data using pinned environments and documented scripts.