Data Science & ML Agent Skills

GWOSC Gravitational Wave Data Tool

Searches and downloads gravitational wave event data and strain files from the Gravitational Wave Open Science Center.

Zenodo Research Data Access

Searches, retrieves, and downloads scientific datasets, software, and research artifacts from the Zenodo open repository.

HEPData Physics Explorer

Searches and retrieves experimental high-energy physics data tables and cross-section measurements from the HEPData repository.

Qwen Image Edit Workflows

Constructs and optimizes sophisticated Qwen2.5-VL image editing pipelines in ComfyUI using natural language instructions.

Director Story-to-Video Pipeline

Orchestrates a comprehensive 8-phase AI film production pipeline from initial story planning to final video assembly with character consistency.

LTX-V2 Video Generation

Builds high-fidelity 19B parameter video workflows for LTX-V2 text-to-video and image-to-video generation.

WAN 2.2 Video Workflow Generator

Automates the creation of high-quality First-Last-Frame video transitions using the WAN 2.2 dual-noise architecture.

ML Pipeline Automation

Orchestrates end-to-end machine learning workflows using industry-standard tools like Airflow, Kubeflow, and MLflow.

ComfyUI Model Compatibility Matrix

Provides precise configuration parameters and compatibility rules for Stable Diffusion, Flux, and video generation models within ComfyUI.

Flux Txt2Img Workflows

Generates and configures high-performance Flux.1 and Flux 2 image generation pipelines for ComfyUI.

ComfyUI Prompt Engineering

Optimizes ComfyUI image generation with advanced prompt engineering syntax, model-specific strategies, and CLIP encoding best practices.

Qwen Image 2512 Workflows

Generates high-fidelity text-to-image workflows for Qwen 2512 models, supporting lightning-fast sampling and advanced component loading.

WAN 2.2 Text-to-Video Workflows

Builds and optimizes high-fidelity video generation pipelines using the WAN 2.2 14B Mixture-of-Experts architecture.

Julia Scientific Package Mapper

Maps over 130 Python scientific libraries to their high-performance, native Julia equivalents for bioinformatics, chemistry, and quantum research.

Julia Scientific Package Mapping

Bridges the gap between Python and Julia ecosystems by providing direct package mappings for 137 high-density scientific AI and data science skills.

DSPy Haystack Integration

Optimizes Haystack RAG pipelines by leveraging DSPy's data-driven prompt tuning and programmatic optimization capabilities.

Recommendation System Engineering

Deploys production-ready recommendation architectures featuring multi-tier caching, feature stores, and automated A/B testing frameworks.

Llamafile Local LLM

Simplifies the installation, configuration, and management of Mozilla Llamafile for running local, OpenAI-compatible LLMs.

ComfyUI Troubleshooting Guide

Diagnoses and resolves common ComfyUI execution errors, performance bottlenecks, and configuration issues.

INSPIRE-HEP Research Assistant

Search and retrieve high-energy physics literature, citation data, and BibTeX records from the INSPIRE-HEP database.

Scientific Validation

Implements a rigorous scientific methodology to empirically validate hypotheses, claims, and theories through statistical testing and bias prevention.

Quality Scoring & Data Evaluation

Evaluates training data quality using multi-dimensional metrics to ensure high-performance LLM fine-tuning and alignment.

Z-Image Workflow Builder

Generates and manages high-fidelity Z-Image text-to-image workflows for ComfyUI using RedCraft and Turbo models.

Everyrow AI Data Processing

Integrates AI-powered qualitative analysis into Python pandas workflows for intelligent data sorting, deduplication, and merging.

LiteLLM Interface

Simplifies LLM interactions by providing a unified Python interface for 100+ AI providers with consistent OpenAI-format syntax.

LLM Integrator

Integrates large language models with the emotive-mascot engine to create sentiment-driven, emotionally responsive conversational interfaces.

Mozilla Llamafile Integration

Configures and manages local LLM inference using Mozilla Llamafile to provide offline, OpenAI-compatible AI capabilities.

Context Engineering for AI Agents

Optimizes LLM context windows by implementing sophisticated trimming, summarization, and memory management strategies for AI agents.

PyTorch Deep Learning

Build, train, and optimize high-performance neural networks using the PyTorch deep learning framework.

QLoRA Fine-Tuning

Enables memory-efficient fine-tuning of large language models using 4-bit quantization and LoRA adapters.