data science & ml Claude 스킬을 발견하세요. 61개의 스킬을 탐색하고 AI 워크플로우에 완벽한 기능을 찾아보세요.
Provides foundational strategies for managing AI agent context windows, attention mechanics, and token usage to improve model performance.
Implements production-grade LLM-as-a-judge techniques to evaluate AI outputs using direct scoring, pairwise comparison, and bias mitigation.
Maximizes LLM context efficiency and reduces token costs through strategic compaction, masking, and partitioning techniques.
Provides expert guidance for designing and implementing distributed multi-agent architectures to scale task complexity beyond single-context limits.
Implements sophisticated memory architectures for AI agents to persist state, build knowledge graphs, and maintain long-term context.
Transforms external RDF context into agent mental states to enable deliberative reasoning and explainable AI within cognitive architectures.
Facilitates drug discovery and therapeutic machine learning by providing AI-ready datasets, benchmarks, and molecular oracles.
Queries and analyzes over 240 million scholarly works, authors, and institutions using the OpenAlex open-access database.
Processes and visualizes massive tabular datasets exceeding available RAM using high-performance out-of-core DataFrame operations.
Accesses and analyzes protein-protein interaction networks and functional enrichment data using the STRING database API.
Builds, analyzes, and visualizes complex networks and graph data structures using the Python NetworkX library.
Performs differential gene expression analysis on bulk RNA-seq data using the DESeq2 framework within Python.
Automates laboratory workflows and hardware control using a hardware-agnostic Python interface for liquid handlers and analytical equipment.
Queries the ChEMBL database for bioactive molecules, drug targets, and medicinal chemistry data to support drug discovery research.
Queries the NHGRI-EBI GWAS Catalog to retrieve genetic variant associations, study metadata, and comprehensive summary statistics for genomic research.
Accelerates data processing and analysis using the high-performance Polars DataFrame library for Python and Rust.
Analyzes biological data including sequences, phylogenetic trees, and microbial community diversity using the scikit-bio Python library.
Analyzes whole-slide pathology images and multiparametric imaging data using a comprehensive computational pathology toolkit.
Empowers AI agents to conduct scientific research by providing standardized access to over 600 bioinformatics, cheminformatics, and genomics tools.
Manages annotated data matrices for single-cell genomics and large-scale biological datasets using the AnnData Python framework.
Analyzes single-cell omics data using deep generative models for batch correction, multimodal integration, and differential expression.
Queries and retrieves comprehensive gene information from NCBI databases for genomic research and functional analysis.
Converts chemical structures into high-quality numerical features for molecular machine learning and cheminformatics tasks.
Accelerates drug discovery and molecular research using graph neural networks and PyTorch-based machine learning.
Manages microscopy data and metadata via the OMERO Python API for scientific imaging and high-content screening workflows.
Accesses and analyzes functional genomics data from the NCBI Gene Expression Omnibus (GEO) repository.
Manage large-scale N-dimensional arrays with chunking, compression, and cloud-native storage for scientific computing workflows.
Implements professional machine learning workflows in Python using scikit-learn for classification, regression, clustering, and data preprocessing.
Performs comprehensive single-cell RNA-seq analysis workflows including quality control, clustering, and trajectory inference.
Infers gene regulatory networks from transcriptomics data using scalable algorithms like GRNBoost2 and GENIE3.
Scroll for more results...