Data Science & ML Claude 스킬
data science & ml Claude 스킬을 발견하세요. 61개의 스킬을 탐색하고 AI 워크플로우에 완벽한 기능을 찾아보세요.
ElevenLabs AI Voice Agents
Build, deploy, and manage production-ready conversational AI voice agents with low-latency ASR, TTS, and turn-taking models.
Google Gemini Embeddings
Implements Google Gemini embeddings API for high-performance RAG and semantic search applications.
Machine Learning Model Training
Trains production-ready machine learning models using industry-standard frameworks like scikit-learn, PyTorch, and TensorFlow.
Google Gemini File Search
Integrates Google Gemini's managed RAG capabilities to provide high-performance document Q&A and knowledge base search across 100+ file formats.
Recommendation Engine Builder
Implements advanced recommendation systems using collaborative filtering, matrix factorization, and hybrid algorithms for personalized user experiences.
SWE-bench Lite Benchmark Runner
Evaluates MCP servers using the SWE-bench Lite dataset to measure software engineering performance and accuracy.
Multi-Model AI Council
Generates consensus-driven technical decisions by synthesizing insights from Claude, Codex, and Gemini through a three-stage voting pipeline.
Data Gouv
Accesses, downloads, and analyzes French public datasets from the official data.gouv.fr portal using specialized Python tools and documentation.
Metaxy Metadata Manager
Manages and tracks feature versions, dependencies, and data lineage for multi-modal data and machine learning pipelines.
ETL Core Reliability Patterns
Implements production-grade ETL patterns including idempotency, checkpointing, and robust error handling for data pipelines.
Pandera Data Validation
Validates pandas DataFrames using Pandera to ensure data integrity and type safety in Python data pipelines.
Data Anomaly Detector
Detects and analyzes outliers in diverse datasets using a combination of statistical methods and machine learning algorithms.
Pydantic Data Validation
Implements robust, record-level data validation using Pydantic models for reliable ETL and API workflows.
Data Profiler
Generates detailed statistical profiles and correlation analysis for DataFrames to accelerate exploratory data analysis.
Exploratory Data Analysis
Performs systematic data profiling and visualization to uncover patterns and assess data quality before modeling.
Qdrant Vector Database
Manages vector embeddings and semantic search operations through the Qdrant REST API.
Pandas Data Optimizer
Optimizes Python data processing using production-grade pandas patterns for large-scale DataFrame manipulation and memory efficiency.
Classification Modeling
Build and evaluate robust binary and multiclass classification models using industry-standard machine learning algorithms and metrics.
VM0 AI Sandbox
Executes AI agents in secure, isolated sandbox environments via the VM0 platform API.
MiniMax AI Suite
Integrates MiniMax APIs for high-performance Chinese language processing, expressive text-to-speech, and cinematic AI video generation.
Perplexity Search & Research
Integrates real-time, AI-powered web search and multi-source synthesis with verified citations directly into the Claude terminal.
Cohort Analysis
Analyzes user retention and behavioral patterns over time to optimize customer lifecycle and lifetime value.
Params Proto Declarative ML Management
Streamlines machine learning experiment configuration using declarative decorators and automatic CLI generation.
Data Validation & Pipeline Helpers
Standardizes data quality across ETL pipelines with custom validation patterns, schema evolution, and automated test assertions.
DeepSeek AI Integration
Integrates DeepSeek's high-performance language models for cost-effective chat, reasoning, and code generation.
OpenAI API Integration
Integrates OpenAI's full suite of models including GPT-4o, DALL-E, and Whisper directly into your terminal via curl.
Hugging Face Transformers Best Practices
Implements best practices for Hugging Face Transformers including model loading, fine-tuning, and inference optimization.
RAG Implementation Guide
Implements production-ready Retrieval-Augmented Generation (RAG) systems with optimized vector storage, chunking, and retrieval patterns.
Question Creator
Generates standardized benchmark test cases for the CAC evaluation system across code, math, logic, and comprehensive categories.
CSV Wrangler
Cleans and processes malformed or messy CSV files using automated detection of encodings, delimiters, and data types.
Scroll for more results...