Data Science & ML Agent Skills

LLaVA Multimodal Assistant

Enables advanced vision-language capabilities for image understanding, multi-turn visual conversations, and document analysis.

vLLM High-Performance Inference Serving

Serves Large Language Models with maximum throughput and efficiency using vLLM's PagedAttention and continuous batching.

DSPy Declarative AI Programming

Builds complex AI systems using Stanford's declarative programming framework to optimize prompts and create modular RAG systems automatically.

CLIP Vision-Language Model

Enables zero-shot image classification and semantic image search by connecting visual concepts with natural language.

GGUF Quantization & Model Optimization

Optimizes AI models for efficient local inference using the GGUF format and llama.cpp quantization techniques.

Speculative Decoding LLM Accelerator

Accelerates LLM inference speeds by up to 3.6x using advanced decoding techniques like Medusa heads and lookahead decoding.

Model Merging & Fusion

Merges multiple fine-tuned AI models using mergekit to combine specialized capabilities like math and coding without expensive retraining.

PyTorch FSDP Expert

Optimizes large-scale AI model training using PyTorch Fully Sharded Data Parallelism for efficient memory management and scaling.

nnsight Model Interpretability

Interprets and manipulates neural network internals for any PyTorch model, including massive foundation models via remote execution.

Unsloth Fine-Tuning

Accelerates LLM fine-tuning workflows with Unsloth to achieve up to 5x faster training speeds and 80% reduced memory consumption.

Pinecone Vector Database Integration

Manages high-performance vector search and storage for production RAG and AI applications using Pinecone's serverless infrastructure.

GRPO RL Fine-Tuning

Implements Group Relative Policy Optimization (GRPO) using the TRL library to enhance model reasoning and structured output capabilities.

TensorBoard ML Visualization

Visualizes machine learning training metrics and model performance to streamline experiment tracking and model debugging.

LLM Guidance & Constrained Generation

Enforces structured LLM outputs using regex and grammars to guarantee valid JSON, XML, and code generation.

RWKV Model Architecture

Implements and optimizes RWKV architectures, a hybrid RNN-Transformer model offering linear-time inference and infinite context windows.

MLflow Lifecycle Management

Manages the machine learning lifecycle by tracking experiments, versioning models, and streamlining production deployments.

LLM Evaluation Harness

Evaluates Large Language Models across 60+ academic benchmarks to measure reasoning, coding, and mathematical capabilities using industry-standard metrics.

PyTorch Lightning Training & Scaling

Streamlines deep learning development by decoupling research code from engineering boilerplate for automated distributed training and hardware scaling.

FAISS Vector Similarity Search

Accelerates large-scale similarity search and clustering for dense vectors using Facebook AI's high-performance library.

Stable Diffusion Image Generation

Generates high-quality images and performs advanced image transformations using Stable Diffusion models and the HuggingFace Diffusers library.

Resource Discovery & Strategy

Detects system hardware capabilities and provides optimized computational strategies for scientific and data-intensive tasks.

Excel & Spreadsheet Scientific Toolkit

Empowers Claude to create, analyze, and format professional Excel spreadsheets and financial models with automated formula recalculation.

LabArchives Integration

Automates electronic lab notebook workflows by providing programmatic access to LabArchives for research data management and documentation.

Scientific Schematics & Diagrams

Generates publication-quality scientific diagrams, neural network architectures, and flowcharts using specialized Python libraries.

Reactome Pathway Database & Analysis

Accesses the Reactome database to perform biological pathway analysis, gene mapping, and enrichment studies for systems biology.

ClinicalTrials.gov Search & Analytics

Facilitates programmatic access to the ClinicalTrials.gov API v2 for advanced trial discovery, patient matching, and medical research data extraction.

LatchBio Bioinformatics Integration

Builds and deploys production-grade bioinformatics pipelines as serverless workflows on the Latch platform.

Scientific Research Brainstorming

Facilitates creative scientific problem-solving by generating hypotheses and exploring interdisciplinary connections as a research ideation partner.

bioRxiv Research Database

Searches and retrieves life sciences preprints from the bioRxiv database by keywords, authors, and categories.

OpenAlex Scholarly Database

Accesses and analyzes over 240 million scholarly works, authors, and institutions via the OpenAlex API for automated scientific discovery.