Data Science & ML Claudeスキル

D3.js Data Visualization

Generates interactive, publication-quality data visualizations using the D3.js library across any JavaScript environment.

Voice AI Architect

Architects and implements high-performance, low-latency voice agents for natural human-AI interaction.

AI Agent Architect

Designs and builds autonomous AI agents using sophisticated tool use, memory systems, and multi-agent orchestration patterns.

AI Product Engineering

Develops production-grade AI features using robust LLM integration patterns, RAG architecture, and cost-effective prompt engineering.

Atlas Persistent Memory

Manages persistent semantic memory and knowledge graph integration for AI agents to maintain context across sessions.

Diverga: Social Science Research Suite

Orchestrates complex social science research and systematic reviews using 24 specialized agents and integrated academic database tools.

Microsoft Agent Type Implementation

Implements and configures specialized agent types within the Microsoft Agent Framework for diverse conversational and workflow-driven AI applications.

Microsoft Agent Patterns

Orchestrates complex multi-agent systems using Microsoft Agent Framework patterns like AutoGen and Semantic Kernel.

AgentsDB Learning Patterns

Implements self-learning agent workflows by tracking operational trajectories and recognizing successful automation patterns.

Innovation Experiment Designer

Transforms high-level innovation PRDs into actionable experiment plans with specific hypotheses, success metrics, and evaluation strategies.

Microsoft Agent DevUI

Provides an interactive local development and debugging interface for testing Microsoft Agent Framework agents.

Innovation Agent Architect

Proposes high-level multi-agent and workflow architectures for CustomGPT.ai Labs projects to streamline the path from PRD to production.

ATS Criteria Extraction

Extracts structured recruitment data from CVs for automated processing and ATS integration.

Reasoning Pentad (V2)

Implements a high-dimensional reasoning framework using simultaneous generators and the Dokkado Protocol for rigorous theoretical derivation.

CV-JD Matching Baseline

Implements rule-based resume and job description matching with deterministic scoring and detailed explainability.

LLM Auto-Update

Automatically synchronizes the latest LLM model specifications, pricing, and API documentation to ensure optimal architecture decisions.

Voice AI Development

Builds high-performance, low-latency voice AI applications and real-time agents using industry-standard APIs and protocols.

Voice AI Agent Architect

Architects high-performance voice-based AI systems focusing on low-latency, natural conversation flow, and robust turn-taking.

Neural Network Trainer

Executes and monitors neural network training runs using best-practice configurations and mandatory logging backends.

HAIPipe NN ModelSet & Pipeline Orchestrator

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

Academic Evaluation & Display

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

HAIPipe Case Processing (Layer 3)

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

HaiPipe Record Processor

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

Haipipe NN Model Tuner

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

HAIPipe NN Pipeline Overview

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

Haipipe Model Instance Layer

Orchestrates model lifecycles and provides HuggingFace-style APIs for modular neural network research pipelines.

HAIPipe Source Data Processor

Standardizes raw academic and medical data files into structured SourceSet DataFrames for research pipelines.

Notebook Analysis Pipeline

Manages a robust four-stage pipeline that converts modular Python scripts into interactive Jupyter notebooks and comprehensive markdown documentation.

Haipipe NN Algorithm Layer

Standardizes the integration of external machine learning libraries and custom neural network modules within the Haipipe architecture.

Feature Engineering Patterns

Transforms raw data into optimized features to improve machine learning model performance and predictive accuracy.