Descubre Habilidades de Claude para data science & ml. Explora 61 habilidades y encuentra las capacidades perfectas para tus flujos de trabajo de IA.
Designs, evaluates, and optimizes high-performance LLM prompts using systematic engineering patterns and rigorous testing frameworks.
Evaluates AI systems for fairness and implements mitigation strategies using demographic parity, equalized odds, and proxy detection.
Design and optimize high-performance Retrieval-Augmented Generation (RAG) pipelines for LLM applications.
Extracts and converts PDF content into clean, LLM-ready markdown or text using AI-powered and high-fidelity local tools.
Analyzes, transforms, and manipulates facial features using a comprehensive suite of AI-powered image processing APIs.
Empowers autonomous agents with nine reinforcement learning algorithms for self-optimization through experience.
Implements high-performance semantic vector search and intelligent document retrieval for RAG systems and AI agents.
Guides developers in choosing the optimal neural network architecture based on data modality, problem constraints, and performance requirements.
Routes AI and machine learning tasks to specialized Yzmir engineering packs based on specific project requirements and technical domains.
Diagnoses machine learning training issues and routes users to specific optimization strategies based on model symptoms.
Builds robust evaluation frameworks to measure, validate, and optimize AI agent performance and context engineering strategies.
Manages fast, reproducible scientific Python environments by unifying conda and PyPI ecosystems within a single workflow.
Builds production-grade multi-agent systems, AgentOS runtimes, and complex agentic workflows with native MCP integration.
Builds and manages AI-powered conversational search agents and RAG systems using Algolia.
Provides high-performance local speech-to-text transcription using GPU-accelerated Whisper models.
Generates production-grade, structured system prompts by analyzing complex user requirements and defining optimal AI agent architectures.
Trains autonomous AI agents using nine reinforcement learning algorithms and WASM-accelerated neural inference for rapid behavioral optimization.
Performs systematic, objective technical analysis of weekly price charts to identify trends, support levels, and probabilistic price scenarios.
Generates professional, responsive D3.js v7 data visualizations including charts, maps, and network diagrams through a guided discovery process.
Search and cite academic literature directly through Google Scholar with verified metadata and PDF downloads.
Trains and deploys distributed neural networks within E2B sandboxes for scalable AI model development and orchestration.
Simplifies the development and deployment of complex AI agents and multi-agent workflows using the LangGraph-based Deep Agents framework.
Streamlines the development of type-safe AI agents using the Pydantic AI framework for Python.
Provides a structured diagnostic framework for fixing broken data science workflows, notebook errors, and incorrect analysis results.
Provides expert guidance and automated workflows for building, testing, and documenting R packages using industry-standard tools like devtools and roxygen2.
Orchestrates iterative refinement cycles across multiple LLMs to produce high-quality, peer-reviewed outputs through competitive judging.
Refines complex AI outputs through iterative multi-model battles and consensus-driven self-critique.
Evaluates research rigor by assessing methodology, experimental design, and statistical validity using frameworks like GRADE and Cochrane.
Configures Pipelex inference backends and API keys to enable live execution of MTHDS AI methods.
Converts PDF documents into LLM-optimized formats like Markdown and JSON using IBM's Docling toolkit.
Scroll for more results...