Data Science & ML Claudeスキル

K-Scale Kinfer Inference

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

Scientific Brainstorming Partner

Facilitates creative scientific ideation by generating hypotheses, exploring interdisciplinary connections, and challenging research assumptions.

K-Scale Ksim Robotics RL

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

Scientific Visualization & Plotting

Creates journal-ready, publication-quality scientific figures with standardized styling, multi-panel layouts, and colorblind-safe palettes.

Weighted Limit

Implements weighted limits and colimits for J-indexed diagrams within enriched category theory frameworks.

Adaptive Walk-Forward Epoch Selection

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

Self-Evolving Agent (DGM)

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

Range Bar Evaluation Metrics

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

Sheaf-Theoretic Coordination

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

Monoidal Category Theory Logic

Implements and applies the formal axioms of monoidal categories to define structural relationships and coherent transformations in complex systems.

Möbius Inversion & Poset Analysis

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

ClinicalTrials.gov Search & Analysis

Accesses the ClinicalTrials.gov API v2 to search, filter, and export global clinical study data for medical research and patient matching.

Advanced Excel & Data Analysis

Automates the creation, editing, and analysis of professional Excel spreadsheets with advanced formula support and financial modeling standards.

World Extractable Value (WEV)

Quantifies and extracts financial value from system inefficiencies by modeling transitions between selfish equilibria and optimal states.

Hijaling Structured Hy & JAX Generator

Generates syntactically guaranteed Hy s-expressions and JAX-compatible functions using constrained LLM decoding.

Collaborative Data Sonification

Transforms complex datasets into immersive auditory experiences using the Erie sonification grammar and multi-agent collaboration.

Mojo SIMD Optimization

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

R Object-Oriented Programming

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

Mutual Awareness Backlink

Formalizes and analyzes bidirectional observation relationships between agents using sheaf-theoretic consistency and structured decompositions.

Topos Polynomial Functors

Models complex interactions and compositional systems using the categorical framework of polynomial functors and dialectica categories.

Denario Autonomous Research

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

Design Experiment

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

Sim2Real Predictive Coding

Bridges the gap between robotic simulations and real-world deployment using active inference and predictive coding frameworks.

Latent-Latency Spectral Bridge

Optimizes the tradeoff between representation compression and computational response time using spectral graph theory and convergence analysis.

Meta Prompt Creator

Generates high-performance, structured prompts for LLMs using research-backed techniques like XML tagging, few-shot examples, and chain-of-thought reasoning.

Council Consultation Ensemble

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

Topos Unified Framework

Unifies topos-theoretic resources, categorical databases, and infinity-topoi for advanced mathematical modeling and cognitive agent development.

ReasoningBank Agent Learning

Implements adaptive learning and high-performance trajectory tracking for autonomous agents using the AgentDB vector backend.

PyMC Bayesian Modeling

Builds, fits, and validates sophisticated Bayesian statistical models using PyMC's probabilistic programming framework.

ICIJ Document Analysis

Processes large-scale document leaks using investigative journalism methodologies to extract entities and build searchable databases.