发现data science & ml类别的 Claude 技能。浏览 61 个技能,找到适合您 AI 工作流程的完美功能。
Automates machine learning lifecycles through experiment tracking, model versioning, and production-grade deployment pipelines.
Evaluates the robustness of research findings by testing how conclusions change under varying analytical assumptions and data conditions.
Leverages SAP's open-source tabular foundation model to perform predictive analytics on structured business data without model training.
Implements high-performance persistent memory and pattern learning for stateful AI agents using AgentDB.
Implements high-performance semantic vector search and intelligent document retrieval for RAG systems and context-aware applications.
Transforms raw datasets into impactful visual narratives using advanced data visualization techniques and narrative design principles.
Facilitates visual agent design and advanced reasoning configuration for building sophisticated, multi-step AI workflows.
Builds and manages structured knowledge graphs to enhance AI reasoning and map complex data relationships.
Implements high-performance adaptive learning and memory distillation for AI agents using the AgentDB vector engine.
Integrate 9 reinforcement learning algorithms to build self-improving AI agents that learn from experience and optimize behavior autonomously.
Orchestrates multi-agent AI swarms for parallel task execution and dynamic coordination using the agentic-flow framework.
Generates professional terminal-based and image-based data visualizations to enhance analytical insights and documentation.
Guides rigorous, intellectually honest interpretation of data query results to ensure objective and actionable conclusions.
Generates professional data-driven presentations and whitepapers using Marp and Pandoc with full citation support and reproducibility.
Implements a rigorous 6-phase framework for conducting and analyzing qualitative research with mandatory bias prevention and reproducible methodology.
Automates the creation and management of robust data pipelines using Hamilton DAGs and the FlowerPower framework.
Automates the translation of MetaTrader 5 (MQL5) indicators into validated Python implementations for algorithmic trading.
Quantifies and extracts economic value from coordination inefficiencies and world transitions using Markov blanket arbitrage and Multiverse Finance.
Implements a recursive, autopoietic loop for state management that synchronizes memory storage, pattern-matching recall, and generative world-building.
Validates World Extractable Value (WEV) and topological system states using GF(3) logic and cybernetic reafference loops.
Models developmental biology cell fate transitions through gradient flow, potential surfaces, and fractional diffusion dynamics.
Verifies GF(3) symmetry conservation and Markov blanket integrity across renormalization group flows for cybernetic system stability.
Verifies thread ancestry and reconstructs balanced world states to facilitate epistemic arbitrage and skill orchestration.
Implements adaptive learning and meta-cognitive capabilities for AI agents to optimize strategies based on historical experience.
Replaces temporal succession with deterministic seed-chaining to enable verifiable, frame-invariant state transitions.
Implements production-grade sorting and searching algorithms with comprehensive complexity analysis and unit testing templates.
Builds high-performance, autonomous AI agents using battle-tested system prompts and production-ready tool implementations.
Builds, optimizes, and debugs LLM prompts and technical documentation using advanced prompt engineering patterns and brutal concision.
Formalizes AI agency and belief systems using condensed mathematics and categorical limit constructions.
Integrates spatio-temporal Earth intelligence and geographic embeddings with crypto-economic data for planetary-scale spatial reasoning.
Scroll for more results...