Skill UI

Access the BRENDA SOAP API to retrieve enzyme kinetic parameters, reaction equations, organism-specific data, and environmental preferences, enabling biochemical research, metabolic pathway reconstruction, and enzyme engineering workflows.

Offers MATLAB and GNU Octave guidance for matrix math, data import/export, visualizations, statistics, signal processing, differential equations, and general scripting—helpful when writing or translating MATLAB/Octave code and running scripts under either interpreter.

QuTiP is a Python toolbox for simulating open and closed quantum systems, offering solvers for master equations, trajectory methods, visualization, and analysis tailored to quantum research, education, and exploratory physics studies.

Creates formally structured .docx academic documents with auto-updating TOC, OMML equations, styled headings, footnotes/endnotes, and bibliography formatting for research reports or policy briefs.

Create programmatic mathematical and technical animation videos with Manim, the Python animation engine. Use it to render explainer clips, equations, graphs, and 3D scenes into polished MP4 output.

Provides comprehensive style guidance for writing and refining scientific manuscripts for Acta Automatica Sinica (AAS). This guide covers the structure of the reporting abstract (Purpose/Method/Result/Conclusion), handling bilingual requirements, formatting rules for equations, figures, and adherence to national standards for units and citations (GB/T 7714). Ideal for papers in control theory, robotics, and intelligent systems.

A guide on how to present highly convincing empirical evidence in academic writing, especially in economics, when regression tables or complex math are limited. This skill teaches readers to translate statistical findings into clear, impactful prose by focusing on magnitude in plain units, synthesizing the body of evidence, defining ranges of precision, and maintaining intellectual honesty.

This skill provides a scholarly layer on top of standard Word document generation. It is designed to create highly formal academic papers (theses, journal articles, conference papers) adhering to strict style guides like APA, MLA, Chicago, and IEEE. Key features include managing complex citation styles, handling numbered equations, generating live cross-references (figures, tables), and implementing multi-column journal layouts.

A comprehensive guide for authors writing for high-impact journals like Physical Review Letters (PRL). It addresses the strict 'deductible budget' model where figures, equations, references, and text all count against a single limit. Provides systematic steps to triage content—such as moving derivations to Supplemental Material, compressing figures, and tightening prose—to ensure the core scientific claims remain clear and within publication guidelines.

This guide assists researchers in the rigorous construction of psychological theories and formal models for academic manuscripts. It provides a step-by-step methodology to move from initial intuition to an explicit, testable theoretical structure. Users learn to define core assumptions, specify underlying causal mechanisms, and formalize models using mathematical equations or precise conceptual frameworks, ensuring the derived model behavior is the central contribution.

SymPy is a powerful Python library designed for symbolic mathematics. Unlike numerical solvers, it performs exact calculations using mathematical symbols, allowing users to model and solve complex problems across various domains. Core capabilities include symbolic calculus (derivatives, integrals, limits), advanced algebra, solving systems of equations, linear algebra (determinants, eigenvalues), and specialized modules for physics and number theory. It can also generate executable code in languages like C and Fortran, making it invaluable for academic research and scientific computing.

A comprehensive knowledge base covering the theoretical fundamentals and advanced algorithms of Deep Reinforcement Learning (Deep RL). It details core concepts like Bellman equations, policy gradients, and the trade-offs between policy optimization and Q-learning. The guide analyzes leading algorithms such as PPO, SAC, TRPO, and DDPG, and provides rigorous best practices for debugging and running scientifically sound RL experiments.