data science & ml Claude 스킬을 발견하세요. 61개의 스킬을 탐색하고 AI 워크플로우에 완벽한 기능을 찾아보세요.
Conducts systematic, academic-grade literature reviews and research syntheses across major scientific and technical databases.
Generates professional, publication-quality statistical graphics and data visualizations directly from Python DataFrames.
Accelerates high-performance data processing and analysis using the Polars DataFrame library and Apache Arrow.
Enables rapid bioinformatics queries and sequence analysis across 20+ genomic databases directly from your terminal or Python scripts.
Queries and interprets NCBI ClinVar data to evaluate genetic variant pathogenicity and clinical significance for genomic medicine.
Processes and analyzes genomic datasets including SAM, BAM, VCF, and FASTA files using a Pythonic interface to htslib.
Implements robust tool and function calling patterns for Java-based AI agents using the LangChain4j framework.
Simplifies and scales neural network development by organizing PyTorch code into modular, production-ready structures.
Solves complex single and multi-objective optimization problems using state-of-the-art evolutionary algorithms and visualization tools.
Optimizes vector database performance by tuning HNSW parameters, implementing quantization, and balancing latency against recall.
Optimizes vector search and RAG applications through strategic embedding model selection, chunking, and pipeline implementation.
Implements high-performance similarity search and vector retrieval patterns for RAG and semantic search applications.
Implements robust Retrieval-Augmented Generation (RAG) systems using the LangChain4j framework to enhance Java-based AI applications with external knowledge.
Queries the ClinicalTrials.gov API v2 to search, filter, and export comprehensive clinical trial data for research and analysis.
Empowers Claude to design rigorous statistical experiments, build predictive models, and implement production-grade MLOps pipelines.
Processes, modifies, and analyzes DICOM medical imaging files using the pydicom library.
Facilitates advanced materials science analysis and computational workflows by manipulating crystal structures, phase diagrams, and electronic data.
Performs specialized time series machine learning tasks including classification, forecasting, and anomaly detection using scikit-learn compatible APIs.
Accesses and queries the NIH Metabolomics Workbench repository for metabolite structures, experimental study data, and standardized nomenclature.
Integrates Claude with the DNAnexus cloud genomics platform to develop bioinformatics pipelines, manage data, and orchestrate workflows.
Automates laboratory data management and R&D workflows by integrating Benchling's registry, inventory, and ELN systems via Python SDK and REST API.
Implement and optimize production-grade prompt patterns including few-shot learning and chain-of-thought reasoning for enhanced LLM performance.
Implements Model Context Protocol (MCP) servers using LangChain4j to bridge AI models with enterprise tools and data resources.
Generates professional, publication-ready clinical decision support documents, biomarker-stratified cohort analyses, and evidence-based treatment guidelines.
Accelerates LLM fine-tuning by 2x while reducing memory consumption by 80% for models like Llama, Mistral, and Phi.
Accesses and queries the Catalogue of Somatic Mutations in Cancer (COSMIC) for precision oncology and genomic research.
Performs exact symbolic mathematical computations including algebra, calculus, and physics modeling directly in Python.
Analyzes generated prompts to provide deep insights into element usage, quality comparisons, and style-based recommendations.
Generates optimized race-day pacing and fueling strategies tailored to individual fitness levels and specific course topography.
Integrates LangChain4j into Spring Boot applications using auto-configuration and declarative AI Services.
Scroll for more results...