3. Data, Science & AI

Detects system resources (CPU, GPU, memory, disk) and provides computational strategy recommendations for scientific tasks.

Integrates with Benchling R&D platform to access DNA/protein registries, inventory, ELN, and workflows via API for lab data automation.

High-performance in-memory DataFrame library with lazy evaluation and Apache Arrow backend, designed as a fast pandas replacement for ETL pipelines.

Comprehensive toolkit for processing and analyzing physiological signals including ECG, EEG, and EDA for neuroscience and psychophysiology research.

Framework for designing, simulating, and executing quantum circuits on Google Quantum AI hardware with noise modeling capabilities.

Converts Product Requirements Documents (PRDs) into Ralph's required prd.json format for autonomous agent system integration.

Guides creation and optimization of Claude Code subagents, covering design, system prompts, tool access, and model selection for specialized AI assistants.

Provides comprehensive documentation for Materialize's SQL syntax, data ingestion, sources, sinks, views, and clusters for real-time data processing workflows.

Generates dynamic prompts using templates and patterns for optimized LLM interactions and AI workflow composition.

Scrapes social media, business, and e-commerce data from platforms like Twitter, Instagram, and Amazon using Apify actors.

Processes documents to extract and transform data, supporting data pipelines and analysis workflows.

Facilitates structured multi-agent debates by generating diverse perspectives and arguments on topics using LLM-based agents.

Framework for evaluating AI agent performance with benchmarking, behavior verification, and metrics like pass@k using code, model, and human graders.

Enables progressive URL scraping via Bright Data service for efficient web data collection in data pipelines.

Manages custom AI agent creation, personality assignment, voice mapping, and parallel orchestration for dynamic task execution.

Processes Excel spreadsheet files for data extraction, manipulation, and transformation in data workflows.

Transcribes audio files into text using OpenAI's Whisper API, leveraging advanced speech recognition AI.

Provides a command-line interface for Google's Gemini AI model to perform one-shot Q&A, text summarization, and content generation.

Batch-generates AI images via OpenAI API with random prompts and creates a static HTML gallery for display.

Summarizes per-model cost usage data from CodexBar CLI, providing current model details or full breakdowns from cost JSON files.

Enables local speech-to-text conversion using the Whisper CLI without requiring an API key.

Guides best practices for Oracle CLI usage, including prompt handling, file bundling, engine configuration, and session management.

Generates spectrograms and feature-panel visualizations from audio files using the songsee command-line interface.

Generates and edits images using Google's Gemini 3 Pro Image AI model for AI-powered visual content creation.