Data Science & ML Claudeスキル

Birkhoff Average

Calculates time averages of observables along trajectories to analyze qualitative behavior and stability in dynamical systems.

Chaotic Attractor Dynamics

Analyzes complex dynamical systems and strange attractors with sensitive dependence on initial conditions.

Reference Class Forecasting

Establishes objective statistical baselines for predictions and projects by anchoring them in historical reality and the 'Outside View.'

Bifurcation Generator

Generates visual bifurcation diagrams to analyze parameter-dependent transitions in dynamical systems.

QRI Valence & Symmetry Theory

Implements the Symmetry Theory of Valence (STV) to map phenomenal states to mathematical structures for consciousness research and qualia-aware system design.

K-Scale Kinfer Inference

Deploys high-performance reinforcement learning policies to real-world robots using a specialized Rust-based ONNX inference engine.

ALife Simulation & Artificial Life Research

Facilitates the research, modeling, and implementation of complex artificial life systems, from cellular automata to evolutionary dynamics.

Natural Transformation

Implements category-theoretic natural transformations to map between computational functors while preserving structural integrity.

Influence Propagation Network Analysis

Analyzes and traces the spread of ideas, topics, and behaviors across social networks using high-order graph theory.

Self-Evolving Agent (DGM)

Implements Darwin Gödel Machine patterns to enable AI agents to autonomously improve their code and capabilities through open-ended evolution.

Mojo SIMD Optimization

Optimizes Mojo tensor and array operations using SIMD vectorization to maximize computational throughput on modern hardware.

Ordered Locale Topology & Triadic Systems

Implements point-free topology and triadic decision-making for formal verification and MCP server orchestration.

K-Scale Ksim Robotics RL

Trains humanoid robot locomotion and manipulation policies using a JAX-native Reinforcement Learning framework built on MuJoCo.

Clinical Decision Support

Generates professional, publication-ready clinical decision support documents and biomarker-stratified cohort analyses for pharmaceutical and clinical research.

Denario Autonomous Research

Automates the end-to-end scientific research pipeline from initial hypothesis generation to publication-ready LaTeX manuscripts.

ZX-Calculus Quantum Reasoning

Enables diagrammatic reasoning and optimization for quantum circuits using Z-spiders, X-spiders, and rewrite rules.

Design Experiment

Guides the planning, parameter selection, and documentation of LLM fine-tuning and evaluation experiments.

MLX BitNet GF(3)

Implements and visualizes 1.58-bit ternary Large Language Models on Apple Silicon using GF(3) logic and color-coded weight analysis.

R Object-Oriented Programming

Guides R developers in choosing and implementing the optimal OOP system, including S7, S3, S4, and vctrs.

Adaptive Walk-Forward Epoch Selection

Optimizes training epochs for machine learning models using Walk-Forward Efficiency and efficient frontier analysis.

Range Bar Evaluation Metrics

Evaluates financial models using state-of-the-art metrics specifically designed for range bar (price-based sampling) data.

Riksarkivet File Upload

Uploads local images and XML files to a public server to generate URLs for transcription and document viewing tools.

Sheaf-Theoretic Coordination

Implements topological sheaf theory to manage distributed coordination and data consistency across multi-agent systems.

Label Studio Feedback Integration

Streamlines the process of importing document pages and transcriptions into Label Studio for manual review and human-in-the-loop feedback.

Infinity Topos Theory

Facilitates advanced (∞,1)-category theory modeling, Lean 4 formalization, and Geometric Algebra extensions.

Möbius Inversion & Poset Analysis

Calculates Möbius functions and alternating sums on posets to solve complex combinatorial, graph theory, and network centrality problems.

DuckLake Meta-Cognitive Orchestrator

Orchestrates complex DuckLake ecosystems through meta-cognitive analysis, category mapping, and triadic execution scheduling.

Context Engineering Principles

Optimizes LLM performance by implementing token-efficient context management strategies for AI agents and tools.

Algorithm Extraction & Documentation

Extracts and structures algorithm pseudocode from academic research papers into actionable implementation plans.

Council Consultation Ensemble

Leverages a multi-model ensemble to provide diverse, parallel insights from GPT, Gemini, and Claude for complex problem-solving.