Data Science & ML Agent Skills

Example Analysis Skill

Provides a standardized workflow for data preparation, exploratory analysis, and high-quality visualization using Python libraries.

Basilica CLI Helper

Rent high-performance GPUs and manage machine learning training jobs on Basilica's decentralized compute marketplace.

CrewAI

Facilitates the development and orchestration of collaborative multi-agent AI systems and automated workflows.

Gemini Google Maps Tool

Integrates Gemini AI with Google Maps grounding to provide accurate, location-aware responses and recommendations for over 250 million places worldwide.

Vector RAG Tool

Indexes codebases and documents for semantic search to enable local Retrieval-Augmented Generation (RAG) using Ollama and FAISS.

scArches

Streamlines single-cell omics analysis through deep learning-based data integration, reference mapping, and model surgery techniques.

CellPhoneDB Analysis

Facilitates single-cell RNA-seq analysis of cell-cell communication and ligand-receptor interactions using the CellPhoneDB framework.

Notebook Creator

Generates standardized Jupyter notebooks for fantasy football data analysis, integrating DuckDB connections, dbt mart queries, and professional visualization patterns.

Sprint 1 Executor

Executes structured, atomic tasks for fantasy football analytics, FASA optimization, and trade intelligence within a standardized sprint framework.

D3.js Visualization

Generates sophisticated, interactive data visualizations and custom SVG graphics with precise control over visual elements and transitions.

LA-Bench Procedure Generator

Generates detailed experimental procedures from LA-Bench datasets by orchestrating a multi-agent workflow for parsing, reference fetching, and quality validation.

TTS LiveKit Plugin

Deploys a self-hosted Text-to-Speech API using MeloTTS and integrates it with LiveKit voice agents for high-quality, low-latency speech synthesis.

LA-Bench Workflow

Orchestrates the end-to-end generation, validation, and iterative improvement of detailed laboratory experimental procedures using the LA-Bench framework.

Procedure Refiner

Iteratively improves LA-Bench experimental procedures through automated validation, regeneration, and data persistence cycles.

Senior Computer Vision

Implements production-grade computer vision systems including object detection, segmentation, and real-time video processing using industry-standard frameworks.

Prompt Engineering

Designs, optimizes, and troubleshoots large language model prompts using research-backed techniques and structured design patterns.

Medallion Schema Reference

Automates schema validation and business logic extraction to ensure accuracy when generating PySpark ETL transformation code.

Polars Data Processing

Provides expert guidance for high-performance data manipulation and ETL pipeline optimization using the Polars library in Python.

Model Coordination

Coordinates multiple AI models in parallel to perform comparative analysis, aggregate decision-making, and track performance across diverse LLM providers.

Autonomous Trading

Orchestrates end-to-end stock trading operations by performing automated screening, multi-model AI analysis, and order execution via Alpaca.

Mean-Variance Optimization

Calculates optimal portfolio weights and identifies the tangency portfolio to maximize the Sharpe ratio based on user-provided asset data.

MetaNova NOVA Miner

Facilitates the setup, optimization, and management of molecular mining operations on Bittensor Subnet 68 for decentralized drug discovery.

TRL Training on Hugging Face

Trains and fine-tunes language models using Transformer Reinforcement Learning methods on fully managed Hugging Face cloud GPU infrastructure.

Innovation Game Miner

Develops, optimizes, and submits high-performance competitive algorithms for Boolean Satisfiability, Vehicle Routing, and Knapsack challenges on The Innovation Game platform.

Google ADK & CopilotKit Agent Builder

Builds full-stack AI agents by integrating Google ADK backends with CopilotKit-powered React frontends and Gemini models.

RAG Systems

Implements robust Retrieval-Augmented Generation (RAG) pipelines including document ingestion, hybrid search, reranking, and intelligent query routing.

AI Multimodal

Processes and generates multimedia content including audio, video, images, and documents using the Google Gemini API.

Analysis Orchestration

Optimizes AI-assisted qualitative research through model selection guidance, cost estimation, and document processing strategies.

Gioia Methodology

Constructs and validates hierarchical data structures for qualitative research, transforming grounded participant language into abstract theoretical dimensions.

PocketFlow

Orchestrates complex LLM applications using graph-based abstractions, agentic design patterns, and modular task decomposition.