Skill UI

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 tool performs a rigorous Level 2 semantic epistemic review of Agent-Native Research Artifacts (ARAs). It assesses six critical dimensions—including evidence relevance, falsifiability, and methodological rigor—to determine the content's intellectual soundness. It is used after initial structural validation to provide objective, constructive criticism, scoring the work from Strong Accept to Reject.

This skill converts complex, narrative technical documents, research excerpts, or natural language problem descriptions into a highly structured Mathematical Problem Specification (MPS). It systematically extracts variables, constraints, objectives, and uncertainty parameters. By adhering to a strict Zero-Inference Protocol, it ensures all extracted elements are strictly grounded in the source text, making it invaluable for formalizing real-world optimization, data science, and engineering problems.

This skill generates detailed, structured research protocols for various academic, clinical, or market research studies. It ensures all critical components—such as objectives, study design, participant criteria, methodology, data management, statistical analysis plan, and ethical considerations—are comprehensively documented, providing a robust framework for any scientific investigation.

This skill guides researchers on the mandatory, rigorous evaluation of complex systems models (e.g., AgSy). It details best practices for model validation, emphasizing the comparison of observed vs. simulated data using independent, held-out datasets. Key components covered include standard fit statistics (RMSE, NSE), sensitivity analysis (identifying core drivers), uncertainty propagation, and multi-objective trade-off/scenario analysis to ensure scientific credibility.

This guide provides a rigorous framework for constructing formal academic models, tailored for top-tier management journals. It emphasizes the four essential components—decision variables, constraints, objective functions, and assumptions—while providing detailed guidelines on ensuring model completeness, mathematical solvability, and, most critically, the defensibility of every assumption against academic scrutiny.

A guide for developing rigorous analytical or stochastic models for Manufacturing & Service Operations Management (M&SOM). It emphasizes translating operational decisions, objectives, and uncertainties into explicit structural results, such as policy forms (e.g., order-up-to levels) and comparative statics, ensuring the core insight remains operational rather than merely descriptive.

Guides agents through bounded parameter optimization for configurable systems with measurable objectives: define search space, budget, and baseline, run trials one at a time, log evidence, and recommend a configuration for HPO, inference tuning, simulations, or RL/control experiments.