data science & ml Claude 스킬을 발견하세요. 61개의 스킬을 탐색하고 AI 워크플로우에 완벽한 기능을 찾아보세요.
Generates balanced, deterministic execution schedules by interleaving three color streams using GF(3) mathematical conservation.
Automates the creation of production-grade Pegasus scientific workflows from high-level pipeline descriptions.
Visualizes solar observation data, EUV imagery, and machine learning model outputs using SunPy and Matplotlib.
Transforms raw SDO/AIA solar observation data into standardized, ML-ready formats through automated calibration and registration pipelines.
Enables Claude to interactively explore, analyze, and modify open Microsoft Excel workbooks using natural language commands.
Develops and deploys deep learning models for solar physics using preprocessed Sun and Space Weather data.
Converts Snakemake and Nextflow pipelines into robust Pegasus workflows for high-performance computing environments.
Downloads solar observation data from SDO, STEREO, and Solar Orbiter missions for scientific analysis and machine learning.
Delegates coding tasks and cross-model feedback to multiple AI providers through the OpenCode CLI bridge.
Implements self-improving code architectures that use formal proofs and evolutionary search to safely enhance system utility.
Establishes rigorous and defensible ground truth labels for evaluation datasets based on authoritative guidelines.
Streamlines academic research data analysis by enforcing reproducible dbt pipelines and interactive Streamlit dashboards.
Implements Schmidhuber's compression progress theory to provide intrinsic curiosity rewards for autonomous AI learning and exploration.
Extracts structured training examples from document sets to create high-quality datasets for teaching LLMs specific tasks or styles.
Transcribes audio and video files into text via a specialized Speech2Text API with support for JWT authentication and task polling.
Verifies mathematical claims and generates Lean 4 formal proofs or counterexamples using the Harmonic Aristotle API.
Enhances decision-making through a multi-model adversarial reasoning protocol and reliability-weighted aggregation.
Provides expert guidance and routine lookup for the ctrlsys control systems library, covering LQR design, Kalman filtering, and system identification.
Provides expert guidance on control system design, analysis, and identification using the ctrlsys library.
Extracts structured training pairs from academic peer reviews and source documents to build high-quality datasets for LLM fine-tuning.
Build and deploy production-ready multi-agent systems with MCP integration and automated workflows.
Facilitates reproducible academic research and data pipelines using dbt and Streamlit while enforcing rigorous data integrity standards.
Programmatically creates, edits, and optimizes Jupyter and Google Colab notebooks with precise JSON formatting and metadata management.
Standardizes the integration of external machine learning libraries and custom neural network modules within the Haipipe architecture.
Manages a robust four-stage pipeline that converts modular Python scripts into interactive Jupyter notebooks and comprehensive markdown documentation.
Standardizes raw academic and medical data files into structured SourceSet DataFrames for research pipelines.
Orchestrates model lifecycles and provides HuggingFace-style APIs for modular neural network research pipelines.
Provides a foundational architecture map and decision guide for managing neural network pipelines within the HAIPipe research framework.
Standardizes machine learning algorithm implementation through a universal wrapper contract for seamless training, inference, and serialization.
Builds, trains, and deploys predictive machine learning models with robust preprocessing and standardized evaluation pipelines.
Scroll for more results...