Descubre Habilidades de Claude para data science & ml. Explora 61 habilidades y encuentra las capacidades perfectas para tus flujos de trabajo de IA.
Enables Claude to perform complex scientific research by providing access to over 600 bioinformatics, genomics, and cheminformatics tools.
Manipulates, analyzes, and visualizes phylogenetic trees and genomic data with the Environment for Tree Exploration (ETE) framework.
Evaluates research rigor, methodology, and statistical validity to perform critical analysis of scientific claims.
Optimizes trade execution using advanced algorithms like TWAP, VWAP, and Iceberg orders to minimize market impact and slippage.
Performs objective technical analysis on weekly price charts to identify trends, support levels, and probabilistic price scenarios.
Automates programmable chemical synthesis by treating chemical procedures as executable XDL code on modular robotic hardware.
Implements rigorous evaluation strategies for LLM applications using automated metrics, human-in-the-loop feedback, and advanced benchmarking.
Builds Retrieval-Augmented Generation (RAG) systems to ground LLM applications with vector databases and semantic search capabilities.
Optimizes LLM performance and reliability through advanced prompting techniques like chain-of-thought and few-shot learning.
Architects sophisticated LLM applications using LangChain patterns for autonomous agents, stateful memory management, and modular chains.
Orchestrates end-to-end MLOps pipelines from data preparation through production deployment and monitoring.
Navigates complex mathematical and ontological possibility spaces using Badiou-inspired event logic and Kripke semantics.
Models continuous performance curves and high-order musical gestures using topological category theory and Mazzola's Diamond Conjecture.
Identifies and resolves global consistency obstructions in topological AI systems using Čech cohomology and GF(3) balancing.
Optimizes interaction sequences using information theory to maximize learning efficiency and minimize surprise.
Exploits knowledge differentials across domains using propagator-based networks and deterministic parallel synthesis.
Implements sheaf-theoretic neural network coordination for distributed consensus and complex graph-based multi-agent systems.
Extracts behavioral patterns and interaction sequences to train cognitive surrogate systems and predictive models.
Analyzes and optimizes neural network training dynamics using Stochastic Differential Equations and Fokker-Planck convergence metrics.
Formalizes Martin Buber's relational philosophy using category theory and homotopy type theory to enhance AI social intelligence.
Generates visual phase portraits and vector fields for 2D dynamical systems to analyze state space behavior.
Automates safe, structure-preserving self-modification for AI agents using covariant transport and Darwin Gödel Machine evolution loops.
Implements a recursive, autopoietic loop for state management that synchronizes memory storage, pattern-matching recall, and generative world-building.
Bridges Scholze-Clausen condensed mathematics and analytic stacks with sheaf neural networks for advanced topological computation.
Composes complex dynamical systems and resource sharers using categorical colimits and operad algebra.
Optimizes multi-turn AI conversations by reducing token usage through advanced summarization and context management techniques.
Facilitates chaotic context injection by performing interleaved random walks across multiple DuckDB database clusters using coupled pendulum dynamics.
Calculates the time average of observables along trajectories to analyze the long-term qualitative behavior of dynamical systems.
Implements interventional and counterfactual reasoning patterns for deliberate System 2 deep learning and causal world modeling.
Analyzes social network dynamics to trace idea adoption, influence flow, and interperspectival relationships.
Scroll for more results...