Data Science & ML Agent Skills

Stata Integration for Claude

Executes Stata commands and manages statistical workflows directly through the Claude interface.

Funsloth Dataset Validator

Validates and analyzes datasets to ensure they are optimized for Unsloth fine-tuning and Chinchilla optimality.

scvi-tools Single-Cell Analysis

Analyzes single-cell omics data using deep generative models for tasks like batch correction, integration, and differential expression.

Text-to-Speech

Implements high-performance, secure text-to-speech synthesis using Kokoro TTS for real-time voice applications.

Stirrup Market Scanner

Monitors financial markets autonomously to generate AI-driven trading signals using multi-agent consensus and the Stirrup framework.

GPU Cloud CLI

Executes machine learning workloads and local commands on remote NVIDIA GPUs by prefixing them with 'gpu' for instant cloud compute.

MarkItDown File Converter

Converts various file formats including PDF, Office docs, and media into clean Markdown for LLM analysis and text processing.

Gemini Deep Research

Conducts autonomous, multi-source research tasks and generates comprehensive reports using Google's Gemini Deep Research API.

Scientific Bibliography & Research Manager

Streamlines scientific research by fetching arXiv paper sources and automating BibTeX citation management via the NASA ADS API.

Scientific Data Visualization

Transforms complex datasets into publication-quality figures and interactive visualizations using established design principles and domain-specific conventions.

Funsloth RunPod Training Manager

Automates the lifecycle of LLM fine-tuning workloads on RunPod GPU instances using the Unsloth framework.

Funsloth Model Upload

Automates the generation of professional model cards and the deployment of fine-tuned LLMs to the Hugging Face Hub.

Scientific Code Implementation

Implements high-performance, conceptually dense scientific and numerical analysis code following research workflow standards.

Llama.cpp C/C++ Integration

Provides a comprehensive C/C++ API reference and implementation patterns for high-performance local LLM inference using llama.cpp.

GreyCat SDK & GCL Reference

Provides a comprehensive reference for developing native C extensions and GCL applications within the GreyCat ecosystem.

Research Synthesis

Synthesizes fragmented research findings into coherent, structured narratives with evidence-based uncertainty quantification.

FunSloth Unsloth Training Generator

Generates optimized training notebooks and scripts for fine-tuning LLMs using the Unsloth framework.

Funsloth Local GPU Training

Manages local GPU fine-tuning workflows using Unsloth to optimize LLM training performance and resource utilization.

Hugging Face Training Manager

Simplifies the deployment and management of Unsloth fine-tuning jobs on Hugging Face cloud GPUs.

Senior Data Scientist

Provides expert guidance and automated tools for statistical modeling, experiment design, causal inference, and production-grade machine learning pipelines.

Wake Word Detection

Implements high-performance, privacy-preserving wake word detection for always-listening voice assistants using openWakeWord and test-driven development.

Local LLM Integration

Integrates local Large Language Models using llama.cpp and Ollama while implementing robust security measures against prompt injection and resource-based attacks.

Model Quantization

Optimizes Large Language Models through 4-bit and 8-bit quantization to enable efficient deployment on resource-constrained hardware.

Prompt Craft

Optimizes AI prompts by applying architecture-specific techniques for autoregressive and reasoning-based models.

Video Toolkit

Analyzes, transcribes, and edits video files using AI-powered frame extraction, local speech-to-text, and multi-modal audio understanding.

Excel Spreadsheet Assistant

Automates the creation, editing, and analysis of professional Excel spreadsheets with advanced formula support and data visualization.

Business Analyst Expert

Transforms complex business data into actionable insights and strategic recommendations using modern BI tools and predictive analytics.

LangChain Architecture

Architects sophisticated LLM applications using LangChain patterns for agents, memory management, and retrieval-augmented generation.

Vector Index Tuning

Optimizes vector database performance by tuning HNSW parameters, quantization strategies, and memory usage for high-scale search infrastructure.

Prompt Engineer

Optimizes and designs high-performance LLM prompts using advanced techniques like chain-of-thought and few-shot learning.