Data Science & ML Claudeスキル

AI Engineer Professional

Architects production-grade LLM applications, advanced RAG systems, and intelligent multi-agent workflows with enterprise-level safety and observability.

Extended Reasoning & Thinking

Enables deep, multi-step chain-of-thought reasoning for complex problem-solving and logic verification within Claude.

Bismark Methylation Calling

Extracts methylation levels from Bismark-aligned bisulfite sequencing data to generate per-cytosine reports.

ML Experiment Tracker

Streamlines machine learning experiment logging, model versioning, and reproducibility using industry-standard tools like MLflow, Weights & Biases, and DVC.

ML Experiment Tracker

Standardizes machine learning workflows by implementing systematic experiment logging, data versioning, and reproducibility patterns.

RAG Architect

Architects and optimizes Retrieval-Augmented Generation (RAG) systems to ground AI applications in factual, domain-specific knowledge.

Citation Verifier

Verifies, normalizes, and enriches academic paper citations and identifiers for research accuracy and metadata consistency.

Fal AI Audio Integration

Integrates fal.ai high-performance audio models for seamless text-to-speech and speech-to-text conversion within development workflows.

Fal Platform Manager

Manages AI model deployments, monitors usage metrics, and tracks pricing via the Fal.ai platform APIs.

DeepScan Research Monitor

Manages and monitors long-running academic research workflows and citation graph explorations within Claude Code.

Memory Systems Design

Architects short-term, long-term, and graph-based memory systems to enhance AI agent persistence and reasoning.

LLM Evaluation & Benchmarking

Implements comprehensive evaluation frameworks for LLM applications using automated metrics, LLM-as-Judge patterns, and human feedback loops.

Fal AI Media Upscaler

Enhances the resolution and quality of images and videos using advanced AI models via the fal.ai platform.

GLM-OCR Markdown Toolkit

Converts PDFs, PPTs, and images into clean Markdown using AI-assisted GLM OCR with strict integrity verification.

RAG Chunking Strategies

Implements optimized document splitting and processing workflows for Retrieval-Augmented Generation (RAG) systems.

ChIP-seq Biological Quality Control

Performs specialized biological validation for ChIP-seq data by calculating cross-correlation metrics and fraction of reads in peaks.

Recursive Systems Architect

Designs and implements self-referential systems, metacognitive architectures, and recursive logic patterns.

Research Comparative Synthesis

Synthesizes and compares findings across multiple research reports to identify cross-run trends and knowledge gaps.

SAP Cloud SDK for AI

Integrates enterprise-grade AI capabilities into SAP BTP applications using the SAP Cloud SDK for AI for JavaScript/TypeScript and Java.

Prompt Engineering Patterns

Optimizes LLM performance and reliability through advanced prompt engineering techniques like few-shot learning and chain-of-thought reasoning.

AgentDB Memory Patterns

Implements high-performance persistent memory and learning patterns for AI agents using AgentDB.

ML Experiment Tracker

Streamlines machine learning workflows through systematic experiment logging, data versioning, and reproducibility tracking.

Research Briefing

Builds focused academic literature briefings and explores citation graphs using the PapersFlow research ecosystem.

LLM Prompt Optimizer

Transforms vague or inconsistent prompts into high-performance instructions that maximize LLM output quality and efficiency.

Prompt Analyzer & Insights

Analyzes generated prompts to provide deep insights into element usage, quality comparisons, and style-based recommendations.

Investment Analysis & Financial Valuation

Performs professional-grade stock analysis, financial statement interpretation, and intrinsic company valuations.

Cost-Aware LLM Pipeline

Optimizes LLM API expenses by implementing intelligent model routing, budget tracking, and efficient caching strategies.

Agent Harness Construction

Optimizes AI agent architectures by refining action spaces, tool definitions, and observation formats for higher task completion rates.

VideoDB

Manages end-to-end video workflows including ingestion, semantic search, programmatic editing, and real-time desktop perception.

Hybrid Structured Text Parser: Regex & LLM

Implements a cost-effective hybrid framework that prioritizes regex patterns for structured text parsing and reserves LLM validation for complex edge cases.