Data Science & ML Agent Skills

LatchBio Integration

Builds and deploys serverless bioinformatics workflows using the Latch Python SDK and cloud infrastructure.

Pysam Bioinformatics Toolkit

Simplifies genomic data processing by providing a Pythonic interface for reading, writing, and manipulating SAM, BAM, CRAM, and VCF files.

Arboreto GRN Inference

Infers gene regulatory networks from expression data using high-performance machine learning algorithms like GRNBoost2 and GENIE3.

Environmentalist Analyst

Analyzes complex events and policies through the lens of ecological science, sustainability frameworks, and conservation biology to evaluate environmental impact.

Adaptive Rejection Sampler

Provides specialized guidance for implementing efficient Adaptive Rejection Sampling algorithms for log-concave probability distributions.

ENA Database Access

Accesses the European Nucleotide Archive to retrieve genomic sequences, raw reads, and metadata for bioinformatics pipelines.

Biomni

Executes autonomous multi-step biomedical research tasks including genomics analysis, drug discovery, and clinical interpretation.

LangChain Architecture

Architects sophisticated LLM applications using the LangChain framework with support for autonomous agents, memory management, and RAG patterns.

UniProt Database Search & Mapping

Accesses the UniProt knowledgebase to search, retrieve, and map protein sequence and functional information.

SHAP Model Interpretability

Explains machine learning model predictions and feature importance using Shapley values to provide transparent and actionable AI insights.

HuggingFace Model Inference

Provides procedural guidance for setting up HuggingFace model inference services using Flask, covering environment setup, model caching, and robust API implementation.

RAG Implementation Toolkit

Builds robust Retrieval-Augmented Generation systems using vector databases, semantic search, and optimized retrieval pipelines.

NeuroKit2 Biosignal Processing

Processes and analyzes physiological signals including ECG, EEG, EDA, and respiratory patterns for research and clinical applications.

Treasure Data Parent Segment Analysis

Queries and analyzes Treasure Data CDP parent segments to uncover deep customer insights and behavioral patterns.

LLM Evaluation Suite

Implements comprehensive evaluation frameworks for LLM applications using automated metrics, human feedback, and comparative benchmarking.

PyTDC Drug Discovery ML

Provides AI-ready datasets, benchmarks, and molecular oracles for drug discovery and therapeutics machine learning.

Pymatgen Materials Science

Automates materials science workflows including crystal structure analysis, phase diagrams, and Materials Project integration.

Open Targets Scientific Database

Queries the Open Targets Platform to identify therapeutic drug targets, evaluate disease associations, and analyze clinical trial data.

Excel Analysis & Automation

Automates complex Excel data processing, visualization, and formatting using powerful Python libraries like Pandas and OpenPyXL.

ARC-AGI Git Merge & Pattern Tasks

Facilitates solving complex pattern recognition tasks by combining git workflow management with mathematical grid transformation analysis and implementation.

Scientific Resource Detection & Strategy

Identifies system hardware capabilities and provides data-driven recommendations for optimizing computationally intensive tasks like model training and large-scale data processing.

ML Model Leaderboard Navigator

Provides systematic guidance for identifying, verifying, and extracting current performance data from machine learning benchmarks and embedding leaderboards.

Scientific Critical Thinking

Evaluates scientific rigor by assessing research methodology, statistical validity, and potential biases using industry-standard frameworks.

Scientific Peer Review Toolkit

Provides a systematic framework for evaluating the methodology, statistics, and integrity of scientific manuscripts and grant proposals.

STRING Database Analysis

Queries the STRING database to analyze protein-protein interaction networks and perform comprehensive functional enrichment for systems biology.

PyTorch Model Recovery

Reconstructs PyTorch model architectures from weight files and state dictionaries by analyzing tensor shapes and naming patterns.

MTEB Retrieval and Ranking

Optimizes semantic similarity retrieval tasks through expert guidance on document preprocessing, embedding model selection, and similarity ranking.

Raman Spectroscopy Peak Fitting

Analyzes and fits peaks in Raman spectroscopy data using physically-constrained models like Lorentzian, Gaussian, and Voigt functions.

Modernize Scientific Stack

Upgrades legacy Python 2 scientific computing code and analysis pipelines to modern Python 3 standards using contemporary libraries like NumPy and pandas.

Modernize Scientific Stack

Migrates legacy Python 2 scientific computing code to Python 3 using modern libraries like pandas, numpy, and pathlib.