Machine Learning MCP Server: Breaking Down the Classic Modeling Workflow into 30 MCP Tools
A community-sourced MCP skill located at @user_053d27d0/mcp-ml-toolkit-zx, version 1.0.1, categorized under dev-programming, sourced from the community, published by user_053d27d0, with a declaration of requires_api_key=false. It consolidates 30 MCP tools covering classic algorithms and evaluation/tuning workflows such as logistic regression, KNN, SVM, decision trees, random forests, naive Bayes, linear regression, Ridge, Lasso, K-Means, DBSCAN, PCA, t-SNE, cross-validation, ROC, and grid search, targeting structured tabular data. The article follows a fixed structure to introduce its positioning, core features, installation and activation, typical usage, and applicable scenarios. It also notes that the currently scraped materials lack installation commands and tool input parameter definitions, so the official page should be treated as authoritative.
Read MoreMachine Learning: Three Deterministic Algorithms, Reproducible Results
This is a community-sourced Skill published on SkillHub (Location: @user_f4fc8899/bio-machine-learning-integrated), version 1.4.20, categorized under data-analysis. It incorporates three built-in deterministic algorithms: k-means clustering, k-NN classification, and linear regression (including R²), ensuring reproducible results. Execution is handled by a registered managed executor: it accepts recorded JSON input, returns structured content, and outputs Markdown when necessary. It does not run upstream local toolchains or operate third-party accounts; the deliverable is solely a verified server-side response. The official page could not be accessed during this scraping attempt; therefore, verifiable installation commands, directory paths, configuration file fields, or input JSON field definitions were not obtained. This description is based on factual reporting without speculation or fabrication. The page displays a rating of 100000, 1014 downloads, and 0 installations, with tags indicating `requires_api_key=false` and `pricing_type=alipay`. It is suitable for data analysis, structural exploration, and comparative scenarios requiring result consistency. Please note that it only covers these three algorithms, and field details should be verified against the official page before deployment.
Read MoreAutomating Accounting Research: Delegating the Empirical Research Process to Skill
This article introduces the community-released Skill "Accounting Research Automation" (acct-research-kit, version 1.0.9, categorized as professional, no API key required). It packages high-frequency tasks in accounting empirical research into 47 modules, including PDF plain text extraction, sentiment analysis, a CLI entry point, 30 machine learning methods, and a complete empirical workflow. The experimental research toolchain encompasses design review, data cleaning, specification curves, Latin squares, staggered DID robust estimation, archive-based design criteria detectors, design generators, and a research closed-loop. The literature drafting tools feature card indexing, construct vocabulary normalization, and R1–R5 candidate generation. Additionally, it includes upstream data acquisition (Juchao Annual Reports, National Bureau of Statistics macro data, stock exchanges, CNKI, utilizing a zero-dependency anti-crawling architecture) and content collection (WeChat Official Accounts, official websites, and journal materials into the ima knowledge base). The article details the utility of each module and notes that official pages and APIs were inaccessible during this review. Consequently, unverified installation commands and reproducible examples are omitted, cautioning users to pay attention to compliance and adaptation issues regarding community-sourced resources.
Read MoreMachine Learning Stock Selection Model: Backtesting Alpha Factors with XGBoost/LightGBM/Ridge
The machine learning stock selection model is a strategy Skill based on XGBoost, LightGBM, and Ridge. It utilizes 20 factor features for rolling training and quintile backtesting, providing IC evaluation capabilities.
Read MoreMLflow Wrapper: A Wrapper Tool for MLflow
Mlflow Wrap is an MLflow wrapper tool released by community users. Positioned as a wrapper, it aims to reduce the complexity of MLflow interactions. Currently, public documentation does not provide specific installation commands or usage examples.
Read MoreAutoML: Auto-optimization of Structured Data Models
AutoML is a machine-learning optimization skill for structured/tabular data. It automates the iterative experimentation workflow—data analysis, model selection, hyperparameter tuning, and evaluation & decision making—and supports CPU execution of RandomForest, XGBoost, LightGBM, CatBoost, GBDT, ExtraTrees, and HistGB, enabling developers to quickly optimize configurations for classification or regression models.
Read MoreAndrew Ng AI Learning Skill: Answering Questions in Coding Assistants Based on His Teaching Framework
The SkillHub community skill "Andrew Ng AI Learning" (@user_9d5a2a39/andrew-ng-distilled, v1.0.8) distills content from CS229, Deep Learning Specialization, Agent Design Patterns, Data-Centric AI, and Agent Productionization into a knowledge base loadable by Agents. Styled after Andrew Ng’s teaching, it requires no API key (requires_api_key=false). The article outlines its positioning, coverage topics, and trigger words, and provides instructions on installing the CLI via skillhub.md and loading it into skills directories for Cursor or Claude Code using the `--dir` flag, alongside examples of typical inquiries and notes on community sources and paths.
Read MoreMathematical Modeling and the Paper Factory: A Skill Pipeline from Data Analysis to Competition Papers
The SkillHub community skill "Mathematical Modeling and Paper Factory" (@user_0210c829/math-modeling-framework, v1.1.0) is designed for data analysis and modeling involving XGBoost, regression, classification, and clustering. It also covers competitions such as CUMCM, MCM, and ICM, as well as academic paper drafting. The official documentation outlines mandatory chart skeletons, quality gates, data leakage checks, compliance with LaTeX and GB/T 7714 standards, and writing styles to eliminate AI traces. It requires the OpenClaw environment; for delivery via Tencent Docs, use `qclaw_tdoc_mcp_call`. This article introduces its positioning, core capabilities, installation methods, and usage notes. Please refer to the SkillHub page and installation documentation for factual accuracy.
Read MoreDrafting and Revising ML/CV/NLP Papers in Agents: Academic Paper Writing
This article introduces the "Academic Paper Writing" skill (@org-02qudk26/research-paper-writing, v1.0.0), published by Zhiyu Technology on SkillHub. Classified under the professional category, it targets the drafting and revision of research papers in Machine Learning (ML), Computer Vision (CV), and Natural Language Processing (NLP), with a focus on improving the Abstract, and is configured with `requires_api_key=false`. The article explains its positioning and verifiable capabilities, providing CLI checks and installation commands based on `skillhub.cn/install/skillhub.md`, as well as the skills directories for Cursor, Claude Code, and Codex, and demonstrates how to trigger it in a conversation. It reminds users that experiments and citations must be manually verified, and details should be based on the local `SKILL.md`.
Read MoreLottery Prediction Skill: Integrating Double Color Ball Machine Learning Prediction into Agents
The Lottery Prediction skill is a data-analysis class skill (v3.8.0) in the SkillHub community edition, located at @user_8558a957/lottery-predictor. Its description claims to utilize an ensemble of Random Forest, Gradient Boosting, and rules, along with 15-dimensional feature engineering, achieving 80.8% accuracy for red balls, with no API key required. The article explains its positioning and verifiable capabilities, provides two activation methods—`skillhub install` and the official AI installation prompt—and lists skill directory paths for platforms like Cursor. It also cautions about the randomness of lotteries and the limitations of the self-reported metrics.
Read Morez-asset/za_ppt: Generate Beamer/Quarto Presentation Slides from Academic Papers
z-asset/za_ppt is a plugin in the DeepSeek Harness (DSH) ecosystem, designed to reduce the time spent on report writing and slide preparation in asset pricing and machine learning research. It focuses on converting research papers into structured Beamer or Quarto slide decks. The plugin covers five core capabilities: literature review, data processing, model training, report writing, and slide preparation, and supports installation via dsh plugin or npm. Its domain calibration is centered on empirical asset pricing and machine learning. It depends on @deepseek-ai/cordis and dsh-skill and is released under the MIT License.
Read MoreZ Research · Data Stage: A Data Discovery and Quality Assessment Plugin for Asset Pricing and Machine Learning
Z Research · Data Stage is a dedicated plugin within the DeepSeek Harness ecosystem for empirical asset pricing and machine learning research. It addresses the time-consuming challenges of data discovery and quality assessment through standardized workflows, supporting tasks such as data processing, model training, and report generation. Users can install it via CLI or npm and directly trigger its features using natural language instructions in a DSH session. The plugin relies on specific peer dependencies and is well suited to researchers who need to process financial and AI data efficiently, significantly reducing manual effort and operational costs.
Read More@zasset/za-analysis: An End-to-End Analytics Plugin for Asset Pricing and Machine Learning Research
DeepSeek Harness (DSH) offers an end-to-end plugin named ZA Research Analysis, specifically designed for empirical asset pricing and machine learning research. The plugin integrates full-workflow automation for literature reviews, data processing, model training, and report/PPT generation. Users can install it via the command line and trigger relevant skills through natural-language instructions within DSH sessions, making it suitable for research scenarios such as factor models and cross-sectional return forecasting.
Read MoreIntroducing the DSH Plugin: dsh-mlops (ML Pipeline Workflows)
`dsh-mlops` is a plugin in the DSH ecosystem that aims to simplify the building and maintenance of machine learning pipelines through standardized workflows. It covers the full lifecycle, from data preparation, training, and evaluation through deployment and monitoring. The plugin runs with the permissions of the current DSH process, but official resources currently do not provide a specific feature list, installation command, or usage examples. It is recommended to inspect the source code before installation to verify that it meets your usage requirements.
Read More