3. Data, Science & AI

Advises on optimizing DataFusion SQL queries and DataFrame operations for performance, focusing on predicate pushdown, partition pruning, and join ordering.

Searches and lists statistical tables from Danmarks Statistik by subject or keyword, enabling users to find specific datasets for analysis or research.

Checks data freshness and age in DuckDB tables to determine if data requires refreshing or to validate currency before analysis.

Fetches and stores Danmarks Statistik API data in DuckDB for analytical use cases.

Lists all Danmarks Statistik tables stored in DuckDB, including metadata, to help users explore available local datasets.

Performs SQL joins and multi-table analysis on DST data in DuckDB, providing patterns for common dimension-based comparisons (time, region).

Retrieves detailed metadata including variables, dimensions, and structure for Danmarks Statistik tables to enable informed data schema comprehension before retrieval.

Enables exploration of Danmarks Statistik's subject hierarchy to discover available data topics and organizational structure for research.

Executes SQL queries on Danmarks Statistik data in DuckDB for analysis, filtering, aggregation, and joins with table summaries.

Enables creation and configuration of Claude Code subagents through structured .md files, including tool restrictions and model selection.

Generates interactive Chart.js visualizations for DST data analysis, enabling trend display and dashboard creation from database tables.

Documents data science libraries (pandas, numpy, sklearn) and best practices for statistical analysis, regression modeling, and script organization with strict directory requirements.

Provides ethical web scraping techniques, anti-bot evasion methods, and legal compliance strategies for data extraction.

Provides techniques for optimizing SQL database queries, indexing strategies, and performance tuning.

Guides Ollama integration for local AI inference, covering setup, model management, and API usage in Python and Node.js.

Retrieves messages from Discord channels using the Discord API for data analysis, monitoring, or integration purposes.

Guides identification of LLM-appropriate tasks, pipeline design, and agent-assisted iteration in development projects.

Provides architectural patterns for multi-agent systems including supervisor, swarm, and hierarchical designs with context isolation.

Transforms user requirements into structured, executable prompts following Claude 4.x best practices, incorporating explicitness and contract-style.

Provides unified CLI access for managing AI agent workflows, document templates, and content schemas in the Blueprint framework.

Routes AI tasks to optimal LLM tiers based on complexity, maximizing free-tier usage and reducing costs.

Enables unified database operations for logging, querying, and storing data across BidDeed.AI and Life OS ecosystems via Supabase.

Provides context engineering utilities for AI/ML systems, routing to a vendored library and enforcing repo-specific guardrails (atomic PRs, evidence, governance).

Orchestrates multiple AI agents with specialized domain expertise to run independent tasks or deliver comprehensive analysis from diverse perspectives.