Data Science & ML Agent Skills

MLOps Engineer

Builds and automates production-grade machine learning pipelines, experiment tracking systems, and cloud-native ML infrastructure.

LLM Performance Evaluation

Implements comprehensive evaluation strategies for LLM applications using automated metrics, human feedback loops, and benchmarking.

Scientific Protein Modeling (ESM)

Facilitates advanced protein design, structure prediction, and representation learning using the Evolutionary Scale Modeling (ESM) toolkit.

Data Processor & Analyzer

Processes and analyzes enterprise RAG retrieval results through statistical computation, format conversion, and automated report generation.

Claude Flow V3 Deep Integration

Refactors agentic architectures by integrating agentic-flow@alpha to eliminate code redundancy and maximize swarm performance.

AgentDB Learning

Implements and trains reinforcement learning algorithms to create self-improving autonomous agents using the AgentDB plugin system.

Flow Nexus Neural

Trains and deploys custom neural network architectures across distributed sandbox environments.

ReasoningBank AgentDB

Implements adaptive learning and experience replay for agents using a high-performance vector database to optimize decision-making over time.

Flow Nexus Platform

Orchestrates intelligent agent swarms, manages secure code sandboxes, and handles application deployment within the Flow Nexus ecosystem.

AgentDB Memory Patterns

Implements high-performance persistent memory and pattern-learning capabilities for stateful AI agents using AgentDB.

ReasoningBank Intelligence

Implements adaptive learning and meta-cognitive capabilities to enable AI agents to recognize patterns and optimize strategies through continuous experience.

Local Offline TTS

Generates high-quality speech from text locally using Sherpa-ONNX models without requiring cloud connectivity.

User Research Synthesis

Synthesizes raw qualitative and quantitative research into actionable product insights and prioritized opportunity areas.

Single-Cell Deep Learning (scvi-tools)

Performs advanced deep learning analysis for single-cell genomics using the scvi-tools framework.

Data Exploration & Profiling

Profiles datasets and assesses data quality to discover patterns and understand schemas before analysis.

Data Validation & QA

Validates data analysis methodology, accuracy, and documentation to ensure high-quality, reproducible insights for stakeholders.

Single-Cell RNA-seq QC

Automates quality control and filtering for single-cell RNA sequencing data following scverse and scanpy best practices.

Data Context Extractor

Generates tailored data analysis skills by capturing tribal knowledge, schema details, and business metrics from analysts.

Lab Instrument Data Converter

Standardizes laboratory instrument data by converting various file formats into the Allotrope Simple Model (ASM) for LIMS and downstream analysis.

Data Visualization & Charting

Generates professional, accessible, and insightful data visualizations using Python's leading charting libraries like Matplotlib and Seaborn.

Nextflow Bioinformatics Pipelines

Automates the deployment and management of nf-core bioinformatics pipelines for genomic data analysis.

Statistical Analysis

Applies advanced statistical methods to analyze data distributions, detect trends, and validate hypotheses with scientific rigor.

Imaging Data Commons Access

Queries and downloads large-scale public cancer imaging datasets from the NCI Imaging Data Commons using Python and SQL.

FRED Economic Data

Queries the FRED API for over 800,000 economic time series to support macroeconomic research and financial analysis.

Book SFT Pipeline

Automates the end-to-end process of converting literary works into high-quality datasets for fine-tuning AI models on specific authorial voices and writing styles.

Context Engineering Fundamentals

Provides foundational principles and implementation patterns for managing language model context windows and attention mechanics in AI agent systems.

Memory Systems

Design and implement sophisticated agent memory architectures, from vector stores to temporal knowledge graphs, for cross-session persistence.

Context Engineering & Optimization

Optimizes AI context window usage through strategic compression, observation masking, and partitioning to improve performance and reduce costs.

Context Compression Manager

Optimizes AI agent token usage through advanced context summarization and structured information preservation.

Advanced LLM Evaluation

Implements sophisticated LLM-as-a-judge frameworks and evaluation rubrics to ensure production-grade quality and bias mitigation.