Data Science & ML Claudeスキル

Stirrup Market Scanner

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

Funsloth Model Upload

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

Funsloth Dataset Validator

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

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.

Text-to-Speech

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

Wake Word Detection

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

Model Quantization

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

Funsloth RunPod Training Manager

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

Senior Data Scientist

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

Financial Modeling Suite

Builds advanced financial models including DCF analysis, Monte Carlo simulations, and sensitivity testing for robust investment decision-making.

Recursive Language Model Context Processor

Processes massive contexts through programmatic exploration and recursive analysis to achieve significant token savings.

Recursive Language Model (RLM)

Processes massive text contexts with high token efficiency using recursive inference-time scaling and Go-based exploration.

Stata Integration for Claude

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

Video Toolkit

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

Biopython Bioinformatics

Streamlines computational molecular biology tasks including sequence analysis, NCBI database queries, and structural bioinformatics.

Model Versioning Tracker

Tracks and manages AI/ML model versions, performance metrics, and lineage for streamlined model registry management.

Recommendation Engine Builder

Designs and implements personalized recommendation systems using collaborative filtering, content-based models, and hybrid approaches.

ML Model Evaluation Suite

Evaluates machine learning model performance using a comprehensive suite of metrics to ensure accuracy and deployment readiness.

Scientific Critical Thinking

Evaluates research rigor and methodology through systematic assessment of statistical validity, biases, and evidence quality.

ClinVar Database Assistant

Queries and interprets NCBI ClinVar data to provide standardized genetic variant classifications and clinical significance evidence.

Flox CUDA Development

Streamlines NVIDIA CUDA setup and GPU computing environments using Flox for deep learning and high-performance development.

Qiskit Quantum Computing

Builds, optimizes, and executes quantum circuits and algorithms across various hardware providers and simulators.

Histolab Pathology Processing

Automates digital pathology image processing and tile extraction for whole slide images in deep learning pipelines.

Pysam Genomic Data Toolkit

Processes and analyzes genomic data formats including BAM, VCF, and FASTA using a Pythonic interface to htslib.

Phylogenomics Workflow Generator

Automates the generation of scheduler-aware phylogenomic workflows from genome assemblies using single-copy orthologs.

Scientific Data Extractor

Extracts and validates structured data from scientific PDF collections for systematic reviews and meta-analyses.

Machine Learning Feature Engineering

Optimizes machine learning model performance by automating feature creation, selection, and complex data transformations.

Opentrons Lab Automation

Automates laboratory liquid handling by generating Python Protocol API v2 scripts for Flex and OT-2 robots.

Adaptyv Protein Engineering

Streamlines automated protein testing and validation through cloud-based laboratory workflows and sequence optimization tools.

Plotly Visualization

Generates interactive, publication-quality scientific and statistical visualizations using the Plotly Python library.