仓库/Skill 库

CryptoMindAI 是一个面向加密货币市场量化分析的开源研究框架，结合系统化策略、统计分析、回测、样本外验证与 AI 辅助研究；项目聚焦可复现实验与方法学稳健性，而非单纯生成交易信号CryptoMindAI is an open-source research framework for quantitative analysis of cryptocurrency markets, combining systematic strategies, statistical analysis, backtesting, out-of-sample validation and AI-assisted research. The project focuses on reproducible experimentation and methodological robustness rather than simply generating trading signals.

基于反事实决策影响与验证效用的效用引导型政策验证可复现研究框架A reproducible research framework for utility guided policy verification using counterfactual decision impact and verification utility.

一个可复现的研究原型，针对漂移感知欺诈检测，采用 actor-critic 强化学习、动态特征重加权与自适应回放，应对交易分布的持续演化A reproducible research prototype for drift-aware fraud detection using actor-critic reinforcement learning, dynamic feature reweighting, and adaptive replay under evolving transaction distributions.

证据优先的 AI 科研平台，支持文献综述、科学写作、配图生成与可发表论文产出Evidence-first AI research platform for literature review, scientific writing, figure generation, and publication-ready papers.

一个独立开发的板块轮动预测项目，2026 年重构为含回顾性方法学审计的可复现研究工具包An independently developed sector-rotation forecasting project, rebuilt in 2026 as a reproducible research toolkit with a retrospective methodological audit.

EconOps：面向经济学实证研究的透明、可复现研究工作流EconOps is a reproducible research workflow for transparent empirical work in economics.

一个端到端的研究智能系统：摄取学术论文并进行语义理解，映射研究领域的关系与演进，探测尚未探索的研究空白，并使用多 Agent AI 流水线生成文献综述与回答研究问题——全部以纯 Python 构建。An end-to-end research intelligence system that ingests academic papers, understands them semantically, maps how research areas relate and evolve, detects unexplored research gaps, and uses a multi-agent AI pipeline to generate literature reviews and answer research questions — all built in pure Python.

模板化的元研究范例：自文档化的可复现研究仓库。Template meta-research exemplar: self-documenting reproducible research repo

The Triplicate：数据驱动的大幅面报纸排版引擎 —— docxology/template 可复现研究范式的公开范例（测试覆盖率 ≥90%，无 mock，GitHub 与 Zenodo 10.5281/zenodo.20533675 双重发布）。The Triplicate: a data-driven large-format newspaper layout engine — public exemplar of the docxology/template reproducible-research paradigm (≥90% test coverage, no mocks, double-published GitHub + Zenodo 10.5281/zenodo.20533675).

SwipeTA 背后关于图表识别、市场模式与噪声反馈的可复现研究Reproducible research on chart-reading, market patterns, and noisy feedback behind SwipeTA.

从研究问题到论文——全自动化。基于多框架的机器学习研究流水线（CrewAI · AutoGen · LangGraph），支持流式 UI 与人在环控制。From a research question to a paper — automatically. Multi-framework ML research pipeline (CrewAI · AutoGen · LangGraph) with streaming UI and human-in-the-loop control.

Colophon——经过生产验证的 Quarto + LaTeX 脚手架，用于课程书籍、手册与技术参考书。开箱即用支持横向页面、附录、带题注的表格以及正确的引用样式。Colophon — a production-tested Quarto + LaTeX scaffold for course books, manuals, and technical handbooks. Landscape pages, appendices, captioned tables, and citation styling handled correctly out of the box.

系统综述与验证的质量模板——扩展 Consultant 角色原型。Quality template for systematic review and validation - Extends Consultant archetype