Data Science & ML Agent Skills

RFdiffusion Protein Design

Generates novel protein backbones and binder scaffolds using diffusion-based generative modeling for de novo protein structure design.

ProteinMPNN Sequence Design

Designs optimized protein sequences from structural backbones using deep learning-based inverse folding.

Ligand-Aware Protein Design

Designs optimized protein sequences for binding sites and enzymes using Ligand-aware Message Passing Neural Networks.

BindCraft Protein Binder Design

Generates high-affinity protein binders using end-to-end AlphaFold2 hallucination and rigorous structural validation.

Protein Design Quality Control

Evaluates and filters protein designs using research-backed metrics for binding, expression, and structural integrity.

SolubleMPNN Protein Design

Optimizes protein sequences for high-yield soluble expression in E. coli using specialized inverse-folding models.

Protein Design Workflow

Orchestrates end-to-end protein design pipelines from target preparation to validated structure selection.

Cell-Free Protein Expression Guide

Optimizes cell-free protein synthesis (CFPS) experiments through system selection, codon optimization, and troubleshooting guidance.

TensorFlow Data Pipeline Architect

Builds high-performance, scalable data pipelines using the tf.data API to maximize GPU and TPU utilization.

TensorFlow Model Deployment

Deploys, optimizes, and converts TensorFlow models for production environments including mobile, edge, and cloud.

Agentic Workflow Discovery

Automates the discovery and implementation of autonomous AI agent patterns, including task decomposition, tool use, and memory management.

Multimodal RAG Patterns

Implements advanced retrieval-augmented generation systems for images, text, and hybrid document content using CLIP and Voyage AI.

Golden Dataset Management

Protects and maintains high-quality AI/ML test datasets through robust backup, restoration, and data integrity validation.

TensorFlow Neural Networks

Builds, trains, and optimizes complex neural networks using TensorFlow's Keras API and custom low-level implementations.

Agent SDK Builder

Guides users through an interactive interview and research process to build custom AI agents using the OpenHands SDK.

Jupyter Notebooks

Manages, executes, and converts Jupyter notebooks to streamline data science and machine learning workflows.

Golden Dataset Curator

Manages the automated curation and multi-agent validation of high-quality datasets for LLM evaluation.

RAG Retrieval Patterns

Implements robust Retrieval-Augmented Generation (RAG) patterns to ground LLM responses with accurate, cited, and validated external data.

Alternative Agent Frameworks

Implement and compare multi-agent orchestration frameworks like CrewAI, OpenAI Agents SDK, and Microsoft Agent Framework for specialized AI workflows.

LangGraph Checkpointing & Persistence

Manages fault-tolerant workflow persistence and state recovery for LangGraph AI agents.

Golden Dataset Curator

Manages the multi-agent curation of high-quality training and testing datasets with automated quality scoring and bias detection.

High-Performance LLM Inference

Optimizes Large Language Model inference for production environments using vLLM, advanced quantization, and speculative decoding techniques.

LLM Evaluation & Quality Assessment

Implements automated quality gates, LLM-as-judge patterns, and RAGAS metrics to ensure reliable and grounded AI outputs.

Query Decomposition

Breaks down complex search queries into independent sub-concepts to improve retrieval accuracy and coverage in RAG systems.

Audio Language Models

Implements real-time voice agents, high-accuracy transcription, and expressive text-to-speech using native speech-to-speech models.

Alternative Agent Frameworks

Provides implementation patterns and comparison guides for multi-agent orchestration frameworks including CrewAI, OpenAI Agents SDK, and Microsoft Agent Framework.

LLM Output Evaluation & Quality Assurance

Implements advanced LLM-as-judge patterns and RAGAS metrics to evaluate AI output quality and detect hallucinations.

Agentic RAG Patterns

Builds self-correcting RAG systems using LangGraph for adaptive retrieval, document grading, and web search fallbacks.

Agent Loops & Reasoning

Implements autonomous agentic workflows and reasoning patterns for complex, multi-step LLM tasks.

Audio Language Models

Implements real-time voice agents, high-accuracy transcription, and text-to-speech using leading audio AI providers.