Data Science & ML Claudeスキル

Memory Systems

Design and implement sophisticated agent memory architectures, from vector stores to temporal knowledge graphs, for cross-session persistence.

Context Engineering & Optimization

Optimizes AI context window usage through strategic compression, observation masking, and partitioning to improve performance and reduce costs.

Context Engineering Fundamentals

Provides foundational principles and implementation patterns for managing language model context windows and attention mechanics in AI agent systems.

Context Compression Manager

Optimizes AI agent token usage through advanced context summarization and structured information preservation.

Kreuzberg Document Intelligence

Extracts structured text, metadata, and tables from over 75 document formats using a high-performance Rust core.

K-Dense Web Integration

Connects Claude to the K-Dense Web platform for advanced, end-to-end scientific research workflows and multi-agent AI collaboration.

Rowan: Quantum Chemistry & Molecular Simulation

Automates advanced quantum chemistry workflows and protein-ligand modeling using a cloud-based Python API.

MATLAB & Octave Scientific Computing

Performs advanced numerical computing, matrix operations, and scientific visualizations using MATLAB and GNU Octave syntax.

Atomic Agents Project Structure

Scaffolds and organizes modular AI agent projects using standardized directory layouts and configuration patterns.

Atomic Agents Context Providers

Injects dynamic, runtime data into AI agent system prompts to enable context-aware decision making and information sharing.

Atomic Prompt Design

Generates structured, effective system prompts for AI agents using a modular architecture of background identity, processing steps, and output instructions.

Atomic Agents Schema Designer

Defines robust, type-safe data contracts and Pydantic-based schemas for AI agents using the Atomic Agents framework.

Atomic Agents Configuration

Orchestrates and configures modular, structured AI agents using the Atomic Agents framework for robust LLM applications.

LLM Project Methodology

Guides the end-to-end development of LLM-powered applications, from task evaluation and pipeline design to cost estimation and agent architecture.

Multi-Agent Architecture Patterns

Designs and implements robust multi-agent systems using supervisor, swarm, and hierarchical patterns to optimize context management and reasoning.

Context Compression Strategies

Optimizes AI agent performance and token usage by implementing advanced context summarization and management strategies for long-running sessions.

Advanced LLM Evaluation

Implements production-grade LLM-as-a-judge patterns to evaluate model outputs using structured rubrics, bias mitigation, and pairwise comparison techniques.

Context Optimization Expert

Optimizes LLM context windows through strategic compaction, observation masking, and partitioning to reduce token costs and improve agent performance.

Context Engineering Fundamentals

Master the core principles of AI context management to optimize agent performance and token efficiency.

Agent Memory Systems

Implements sophisticated multi-layer memory architectures for AI agents to persist state, track entities, and maintain temporal knowledge across sessions.

Context Degradation Diagnostics

Diagnoses and mitigates performance failures in agentic systems caused by large context windows, attention loss, and information noise.

BDI Mental State Modeling

Transforms external RDF context into agent mental states to enable cognitive reasoning, explainability, and semantic interoperability in multi-agent systems.

RAG Architect

Designs and implements production-grade Retrieval-Augmented Generation pipelines with advanced chunking, retrieval, and evaluation strategies.

Agent Designer

Architects and evaluates robust multi-agent systems using industry-standard patterns and sophisticated orchestration strategies.

Cortex-M Backend for ExecuTorch

Optimizes and deploys PyTorch models to Arm Cortex-M processors using the CMSIS-NN backend.

GGUF Model Quantization

Optimizes large language models for efficient local inference using GGUF format and llama.cpp quantization techniques.

TransformerLens Interpretability

Analyzes and manipulates transformer model internals using mechanistic interpretability techniques like activation patching and circuit analysis.

Llama.cpp Inference Serving

Deploys high-performance LLM inference on CPU, Apple Silicon, and non-NVIDIA GPUs using GGUF quantization.

Model Pruning & LLM Compression

Reduces Large Language Model size and accelerates inference using advanced pruning techniques like Wanda and SparseGPT.

Long Context Transformer Engineering

Extends Transformer model context windows using advanced positional encoding and interpolation techniques like RoPE, YaRN, and ALiBi.