Skill UI

A comprehensive tool for analyzing social media campaign performance. It calculates key metrics such as Engagement Rate, ROI, CTR, and provides industry benchmarks across major platforms (Instagram, Facebook, LinkedIn, etc.). Use this when auditing campaigns, optimizing ad spend, or measuring overall marketing effectiveness.

Query the NIH Metabolomics Workbench via REST API to fetch metabolites, RefMet nomenclature, mass-spec searches, and detailed study datasets for biomarker discovery and metabolomics research.

Query BindingDB for measured drug-target affinities (Ki, Kd, IC50, EC50) via REST endpoints or downloaded TSVs to support target-centric drug discovery, SAR analysis, lead profiling, and benchmarking datasets.

This skill provides comprehensive commands to manage the entire AI model evaluation lifecycle using Arize. Users can list, retrieve metadata, and export results from experiments. It is ideal for comparing multiple model runs, benchmarking performance against a dataset, and analyzing model accuracy using structured evaluation workflows (CRUD operations).

Python framework for single- and multi-objective optimization with NSGA-II/III, MOEA/D, and SPEA2. Supports constraints, ZDT/DTLZ benchmarks, Pareto front analysis, and visualization for engineering design.

This guide demonstrates how to deploy GPU workloads on the CoreWeave platform using Kubernetes (kubectl). It covers deploying vLLM inference services for large language model (LLM) testing and running batch CUDA jobs for benchmarking. This is ideal for users running their first GPU workloads, testing inference pipelines, or verifying cluster access on bare-metal GPU nodes (A100, H100).

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.

A comprehensive guide detailing how to package all necessary supplementary evidence for academic submissions in AI, statistics, and machine learning domains. It covers best practices for ensuring reproducibility, including managing proofs, simulation scripts, benchmark data, random seeds, and minimizing metadata risks for reviewers.

This skill guides the design of real-data validation for academic manuscripts, specifically for forecasting and financial engineering strands. It covers data provenance, rolling out-of-sample tests, benchmark batteries, and statistical significance of improvements. It ensures robustness against look-ahead bias and parameter sensitivity, helping authors meet rigorous external review standards for empirical studies in journals like Chinese Journal of Management Science.

A structured guide on translating behavioral or game-theoretic arguments into pre-specified, quantitative, and testable hypotheses for Experimental Economics (ExpEcon) manuscripts. This methodology emphasizes moving beyond informal intuition by defining the experimental game, deriving benchmark predictions, layering competing behavioral accounts, and generating comparative-statics hypotheses that treatments must adjudicate. It is essential for manuscripts aiming to robustly test theory through design.

This skill guides authors in determining the suitability of their manuscripts for the journal Genome Biology. It details the journal's scope, which requires integrating large-scale genomic or epigenomic data with novel computational methods or statistical frameworks. It emphasizes that successful submissions must provide both methodological advances and meaningful biological insights, adhering strictly to standards like open-source code, public data deposition (GEO, SRA, ENCODE), and rigorous benchmarking.

This guide provides rigorous guidelines for structuring theoretical papers submitted to the International Conference on Database Theory (ICDT). It emphasizes that proofs and formal evidence are the primary contribution, not benchmarks or experiments. It teaches authors how to match their specific theoretical claims (e.g., complexity, expressiveness) to the appropriate academic evidence, ensuring that any proposed experiment is proportional, honest, and merely supplements the core theoretical results.