Data Science & ML Agent Skills

HAIPipe NN Pipeline Overview

Provides a foundational architecture map and decision guide for managing neural network pipelines within the HAIPipe research framework.

Haipipe NN Model Tuner

Standardizes machine learning algorithm implementation through a universal wrapper contract for seamless training, inference, and serialization.

HaiPipe Record Processor

Transforms raw source datasets into temporally-aligned structured record sets for academic research and machine learning.

HAIPipe Case Processing (Layer 3)

Transforms temporal RecordSets into event-triggered CaseSets for machine learning feature extraction.

Academic Evaluation & Display

Automates the generation of publication-ready tables and figures from model performance data for academic research.

HAIPipe NN ModelSet & Pipeline Orchestrator

Orchestrates neural network training, evaluation, and deployment through a model-agnostic pipeline and standardized asset packaging system.

HAIPipe ML Data Preparation

Transforms structured CaseSets into ML-ready datasets with automated splitting, feature engineering, and vocabulary management.

Paper Incubator

Automates the creation and interactive refinement of LaTeX academic paper drafts from research data and architectural blueprints.

PubMed Research

Conducts professional-grade biomedical literature searches and manages citations using the PubMed database.

Ruvector Memory Conventions

Standardizes vector memory workflows and MCP tool interactions for persistent codebase intelligence and context management.

Ask Gemini Collaboration

Enables seamless model-to-model collaboration by delegating research, code reviews, and architectural validation to Google Gemini.

Training Loop Patterns

Implements production-grade deep learning training loops using battle-tested architectural patterns for optimized performance and stability.

Groq & Ollama AI Bridge

Enables high-speed chat completions via Groq Cloud and local text embeddings through Ollama for efficient RAG workflows.

Ask OpenCode

Delegates coding tasks and cross-model feedback to multiple AI providers through the OpenCode CLI bridge.

RDKit Cheminformatics Toolkit

Performs advanced molecular analysis, descriptor calculation, and chemical reaction modeling for drug discovery and computational chemistry.

Autonomous Agent Architect

Architects reliable, production-ready AI agent workflows using constrained loops and proven reliability patterns.

Sensitivity Analysis

Performs systematic testing of input variables to identify key drivers and assess model risk across finance, engineering, and strategy.

Agno AI Agent Framework

Build and deploy production-ready multi-agent systems with MCP integration and automated workflows.

Availability Heuristic Thinking Pattern

Mitigates cognitive bias in decision-making by prioritizing statistical base rates over vivid, anecdotal evidence.

Base Rate Fallacy Logic

Corrects probability judgments by integrating statistical base rates with case-specific information to avoid common cognitive biases.

Data Network Effects

Leverages the data flywheel mental model to build compounding competitive advantages through automated machine learning and user-generated signals.

Scientific Research Brainstorming

Accelerates scientific discovery by generating hypotheses, identifying research gaps, and facilitating interdisciplinary ideation through structured collaborative dialogue.

ModelsLab AI Suite

Integrates a comprehensive suite of AI generation APIs for creating images, videos, audio, and 3D content directly within development workflows.

Online Learning System Design

Implements continuous model updates and incremental learning patterns to handle evolving data streams without full retraining.

Supply and Demand Analysis

Predicts market price and quantity changes by analyzing the interaction between producer supply and consumer demand at equilibrium.

Gambler's Fallacy Recognition

Identifies and mitigates the gambler's fallacy to improve decision-making in probabilistic and high-risk scenarios.

RAG Thinking Patterns

Implements sophisticated Retrieval-Augmented Generation architectures to ground AI responses in real-time external knowledge and eliminate hallucinations.

Scientific Critical Thinking

Evaluates research rigor by assessing methodology, statistical validity, and evidence quality using industry-standard frameworks like GRADE and Cochrane.

Text-to-Chart Visualizer

Creates and validates professional Vega-Lite visualizations from data files and dbt query results.

Scholar Evaluation & Scientific Review

Systematically evaluates scholarly research, academic papers, and technical proposals using the peer-reviewed ScholarEval framework.