MaybeBio

Knowledge base from '交我算 HPC+AI平台用户手册' by 上海交通大学网络信息中心. Use when answering questions about HPC cluster usage, SLURM job scheduling, module environment, data transfer, GPU computing, and common troubleshooting on SJTU HPC clusters.

Trigger on SJTU HPC, 交我算, Slurm, srun, sbatch, IDEKube, hpc/sy SSH; use for cluster jobs and transfer.

Log in to the SJTU HPC platform (also known as "交我算") as the user to perform job queries, submissions, cancellations, and data management. Use this skill when the user requests operations related to HPC or "交我算".

Knowledge base from "数据结构（C++语言版）第3版" by 邓俊辉 (Deng Junhui). Use when learning or applying data structures in C++ with rigorous theoretical foundations - covers vectors, lists, stacks, queues, binary trees, graphs, search trees (BST/AVL/Splay/B/Red-Black/kd), dictionaries (skip list, hash), priority queues (heap, leftist heap), strings (KMP/BM/KR), and sorting (quicksort, selection, Shell).

Knowledge base from "Hello 算法" (Python 版) by 靳宇栋 (@krahets), Release 1.3.0. Use when learning or applying data structures and algorithms in Python - covers complexity analysis, arrays, linked lists, stacks, queues, hash maps, trees, heaps, graphs, search, sorting, divide-and-conquer, backtracking, dynamic programming, and greedy algorithms.

Knowledge base from "数据结构（用面向对象方法与C++语言描述）第3版" by 殷人昆. Use when learning or applying data structures with C++ and object-oriented design - covers linear structures, stacks, queues, arrays, strings, trees, graphs, sets, dictionaries, search structures, sorting, and external sorting.

研究方案生成与方法缝合 - 输入批量文献Method章节+dc-analysis输出+可选仓库README，针对用户指定的问题（可从dc-analysis开放问题中选择或自定义），从全域文献Method中检索可缝合的方法组件，生成包含数据策略、模型架构设计、训练策略、Benchmark评估和B计划的完整课题研究方案（直接保存文件，对话仅显示摘要）。支持多方案Fork、架构Mermaid schematic、方法缝合溯源。特别适用于AI4S计算领域的研究方案设计。Use when user needs to synthesize a research proposal from literature methods, stitch together existing methods into novel solutions, or design a complete ML/DL research pipeline (data→model→training→evaluation). Input: method sections md + dc-analysis output + optional repo READMEs.

批量文献讨论-结论分析与创新点挖掘 - 从多篇论文摘要+讨论+结论中提取真实研究问题和真正创新方向，重点关注原文中未尝试、未解决的方向，生成问题-创新映射报告（直接保存文件，对话仅显示摘要）。需要intro-analysis输出作为主题先验知识以收束研究方向。包含讨论五步解析、问题-创新配对、真实创新头脑风暴、Mermaid可视化逻辑链。Use when user needs innovation point mining, finding real unsolved problems, or writing the novelty section of a research paper. Input: markdown file with abstracts+discussions+conclusions + introduction-analysis output for theme reference. Output: structured innovation analysis report.

批量文献引言分析与综述生成 - 当用户需要进行文献综述、领域调研、或从多篇论文的引言中梳理研究脉络时使用。输入单个包含多篇论文摘要+引言的markdown文件，输出结构化的综述报告（直接保存为文件，对话中仅显示简要摘要），包含时间线、多主题深度分析、观点论战、Mermaid可视化图表。特别适用于生物医学计算、AI4S等交叉领域的文献调研工作。Use when user needs literature review, domain research, or extracting research progress from multiple paper introductions. Input: single markdown file with abstracts+introductions. Output: structured review report saved as markdown file, brief summary in dialog. Includes timeline, deep theme analysis, viewpoint debates, and Mermaid visualizations.

Knowledge base from "GROMACS Documentation Release 2026.2" by the GROMACS development team, enriched with Justin A. Lemkul's practical tutorial workflows and Chinese manual theory notes. Use when applying GROMACS for molecular dynamics simulations: system preparation, force field selection, ligand parametrization, .mdp parameter tuning, mdrun performance optimization, free energy calculations (alchemical + umbrella sampling), membrane protein simulation, virtual sites, trajectory analysis, and troubleshooting.

Construct optimized PubMed search queries through systematic iterative refinement. Use when user mentions literature search, building PubMed queries, finding papers, constructing search strings, or needs systematic literature review methodology. Trigger for requests like "search for X papers", "build a query for Y", "find literature on Z", or any biomedical literature search needs.

融合周志华《机器学习》(西瓜书)、李航《机器学习方法》、南瓜书公式推导、清华大学课件的统计学习与机器学习理论skill。涵盖监督学习、无监督学习、深度学习、强化学习等全套理论体系。用于学习机器学习理论、查阅概念公式、推导算法原理、辅助论文写作或工程实现。

Knowledge base from '高等数学'. Use when applying engineering calculus/analysis frameworks for limits, derivatives, integrals, differential equations, multivariable calculus, vector analysis, infinite series, or studying/referencing standard Chinese engineering mathematics concepts.

大学工科物理（马文蔚《物理学》第七版上/下册）全部 16 章核心知识。用于公式推导、解题方法、物理概念解释、工程应用分析。提供力学、电磁学、振动与波、光学、热学、相对论、量子物理、原子核与粒子物理的系统性参考。

深度学习新手入门知识库 — 整合李宏毅(LeeDL)和李沐(d2l)两本教材,覆盖从ML基础到ChatGPT/扩散/强化学习/视觉RL的24章。提供框架速查、代码模板、故障决策树和概念检索

Complete scikit-learn 1.9.0 code-writing reference. Use when writing sklearn code for classification, regression, clustering, dimensionality reduction, model selection, pipeline construction, or any sklearn estimator. Covers all model families, preprocessing, metrics, cross-validation, and common pitfalls from the official 1.9.0 documentation.

Knowledge base from Amber 2026 Reference Manual and official tutorials. Code-first technical reference for AmberTools26/Amber26 — MD simulation, force fields, free energy, enhanced sampling, and trajectory analysis. Use when writing Amber commands, input files, or MD workflows.

Knowledge base from curated multi-omics bioinformatics resources. Use when applying multi-omics data analysis, selecting tools for RNA-seq, ChIP-seq, ATAC-seq, Hi-C, DNA-seq, proteomics pipelines, integrating multiple omics layers, cancer genomics analysis, or designing cross-omics workflows. Covers tool combinations, analysis strategies, and practical decision guides.