Data Science & ML Agent Skills

Literature Gap Identifier

Identifies and prioritizes research gaps from systematic literature reviews to justify new studies and grant proposals.

Blinding Procedures for Research

Implements rigorous blinding protocols to minimize bias and ensure objectivity in experimental studies and clinical trials.

PolicyEngine Aggregation Patterns

Implements standardized patterns for summing tax and benefit variables across entities using the adds attribute and add() function.

Synthesis Matrix

Generates structured evidence synthesis matrices to organize and compare research data for systematic reviews.

ReasoningBank with AgentDB

Implements high-performance adaptive learning and memory distillation for AI agents using the AgentDB vector backend.

Effect Size Calculator

Calculates and interprets standardized effect sizes to quantify the magnitude of research findings beyond simple p-values.

ReasoningBank Intelligence

Implements adaptive learning and meta-cognitive capabilities for AI agents to optimize strategies based on historical experience.

Data Science & Sparsification

Implements L0 regularization and intelligent sampling techniques to optimize neural network sparsification and survey data calibration.

LLM Evaluation & Benchmarking

Implements comprehensive evaluation frameworks for LLM applications using automated metrics, LLM-as-Judge patterns, and human feedback loops.

HoloViz Plotting Fundamentals

Simplifies the creation of interactive, publication-quality visualizations using hvPlot and HoloViews within the HoloViz ecosystem.

HoloViz Colormaps & Styling

Applies perceptually uniform colormaps and accessible visual styling to data visualizations using Colorcet and the HoloViz ecosystem.

HoloViz Parameterization Expert

Implements type-safe, declarative configuration and reactive logic using the Param library for Python applications.

Book SFT Pipeline

Converts literary works into high-quality supervised fine-tuning (SFT) datasets for training distinctive author-voice and style-transfer models.

Vector Index Tuner

Optimizes vector index performance for production-grade latency, recall, and memory efficiency in AI applications.

LLM Prompt Engineering Patterns

Implements advanced prompt engineering techniques like few-shot learning and chain-of-thought to maximize LLM performance and reliability.

LLM Application Evaluation

Implements robust evaluation frameworks for AI applications using automated metrics, human feedback, and LLM-as-judge patterns.

LLM Project Architect

Architects and implements robust LLM-powered projects from initial ideation through deployment using agentic methodologies.

LangChain Architecture Master

Designs and implements sophisticated LLM applications using the LangChain framework for agents, memory management, and complex task workflows.

Cybernetic Immune System

Implements a cognitive immune framework using active inference and information geometry for robust system self-maintenance.

LangChain Reference Architecture

Implements production-ready architectural patterns and scalable designs for enterprise LangChain applications.

Hydra Experiment Setup

Standardizes machine learning experiment management using Hydra and OmegaConf configuration patterns.

RunPod Model Uploader

Automates the transfer of HuggingFace models to RunPod Network Volumes via Google Colab to minimize GPU billing costs.

Google ADK Python

Builds, evaluates, and deploys code-first AI agents and multi-agent systems using Google's Agent Development Kit.

NetCDF Metadata

Extracts and analyzes metadata from NetCDF and CDL files into structured CSV format for documentation and data analysis.

Market Analysis Expert

Analyzes market trends and technical indicators to provide actionable trading insights and detailed risk assessments.

Contingency Module Architect

Designs resilient contingency module architectures to manage failure scenarios within AI governance frameworks.

Julia Numerical Computing

Executes complex numerical calculations, linear algebra operations, and scientific computing tasks using the high-performance Julia language.

DocETL Pipeline Developer

Builds and executes LLM-powered data processing pipelines for unstructured document analysis using DocETL and Claude Haiku.

ERA5 Climate Data Downloader

Retrieves global atmospheric, land, and ocean climate reanalysis data from the Copernicus Climate Data Store using the CDS API.

Gemini Token Optimization

Optimizes token usage and reduces operational costs when delegating tasks to the Gemini CLI.