Data Science & ML Claudeスキル

Evidence Quality Appraiser (b2)

Systematically evaluates research study quality and risk of bias using context-adaptive methodologies and industry-standard appraisal tools.

Mixed Methods Integration Specialist (E3)

Integrates qualitative and quantitative research data to generate rigorous meta-inferences and professional joint displays.

Audio Normalize for Transcription

Preprocesses and normalizes audio files using FFmpeg to optimize them for high-accuracy speech-to-text transcription.

RL Trading Reward Function Optimizer

Eliminates HOLD bias in reinforcement learning trading models by calibrating reward functions and slippage penalties.

Trading Prediction Outcome Tracker

Automates the recording of actual trading results against predicted signals to enable accurate performance metrics and model retraining.

Quarto Anti-Slop

Enforces reproducible research and academic writing standards for Quarto and RMarkdown documents to eliminate generic AI-generated content.

AgentDB Reinforcement Learning

Implements and trains autonomous agents using nine specialized reinforcement learning algorithms for self-improving behavior.

Flow Nexus Neural

Train, deploy, and manage distributed neural networks across sandboxed E2B environments using multiple architectures and federated learning.

Macro Fiscal & Labor Scenario Analyzer

Analyzes US fiscal deficit expansion and Treasury risk scenarios during periods of rising unemployment and high GDP growth.

Multi-Timeframe RL Training

Trains Reinforcement Learning models across multiple market timeframes with automated data resampling and professional market alignment.

Trading Backtest Capital Accounting

Corrects financial logic in trading simulators to prevent inflated equity curves and inaccurate drawdown metrics.

Training Code Verification

Validates machine learning training scripts and configurations to ensure path accuracy, weight consistency, and environment compatibility.

Scientific Peer Review Toolkit

Evaluates scientific manuscripts and grant proposals for methodological rigor, statistical accuracy, and reporting standards.

Advanced Excel & Financial Modeling

Automates professional spreadsheet creation, data analysis, and financial modeling with industry-standard formatting and formula verification.

Model Version Protocol

Manages version compatibility between trained trading models and live trading environments by embedding metadata into checkpoints.

AI & ML Engineering

Builds production-grade AI systems using modern patterns like RAG, programmatic prompting, and Model Context Protocol (MCP).

Kaggle Competition Suite

Streamlines the end-to-end machine learning competition lifecycle including data handling, model training, and submissions.

MaxFuse Notebook Import Conventions

Standardizes import patterns and file paths for MaxFuse Jupyter notebooks to ensure reliable package integration.

Trading Symbol Database Selection

Optimizes financial market universe selection using a multi-stage pipeline and SQLite-backed data management.

Reward Scaling Calibration

Calibrates reinforcement learning reward scales to eliminate unrealistic drawdown metrics in algorithmic trading models.

Docling Advanced Document Extraction

Extracts structured data from complex PDFs, scanned documents, and multi-column layouts using the advanced Docling engine and Granite vision-language models.

Business Analyst

Transforms complex business data into actionable insights and strategic recommendations using advanced analytics and predictive modeling.

Stitched Image Quality Control

Automates quality control for stitched microscopy images by detecting saturation failures and visible tile grid patterns.

Data Storytelling

Transforms raw data into persuasive narratives and executive-ready presentations using proven storytelling frameworks and visualization techniques.

LLM Project Architect & Methodology

Guides the design, evaluation, and implementation of robust LLM-powered projects and agentic architectures.

AI Image & PDF Analyzer

Analyzes and describes visual content from images and PDF files using the Gemini 1.5 Flash vision model.

LLM Evaluation Framework

Implements comprehensive evaluation strategies for Large Language Model applications using automated metrics, human feedback, and rigorous benchmarking.

Research Paper Ingest

Converts research paper PDFs into structured, reproducible Markdown summaries for technical analysis and knowledge management.

ReasoningBank with AgentDB

Implements high-performance adaptive learning and memory distillation for autonomous agents using the AgentDB vector engine.

PDF Text Extraction for LLMs

Extracts and converts PDF documents into LLM-friendly formats like Markdown to support RAG pipelines and document analysis.