data▌

Data manipulation, analysis, and visualization with Pandas, NumPy, and Matplotlib. \n \n Covers DataFrame and Series creation, indexing, filtering, and type conversions for structured data handling \n Includes data cleaning techniques: missing value handling, deduplication, string operations, and date/time parsing \n Provides GroupBy aggregation, pivot tables, multi-level indexing, and window functions for exploratory analysis \n Integrates Matplotlib and Seaborn for statistical plotting, trend

Query your data warehouse to answer business questions with cached patterns and concept mappings. \n \n Supports pattern lookup and caching for repeated question types, with outcome recording to improve future queries \n Includes concept-to-table mapping cache and table schema discovery via INFORMATION_SCHEMA or codebase grep \n Provides run_sql() and run_sql_pandas() kernel functions returning Polars or Pandas DataFrames for analysis \n CLI commands for managing concept, pattern, and table cach

Bulk enrichment of company, people, or product data with web-sourced fields like CEO names, funding, and contact info. \n \n Accepts inline JSON data or CSV files; outputs enriched results to CSV \n Runs asynchronously with progress tracking via monitoring URL and polling commands \n Requires parallel-cli tool and internet access; handles large datasets with configurable timeouts \n Supports flexible field requests through natural language intent descriptions (e.g., \"CEO name and founding year\

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Build a production-ready, AI-powered data collection agent for any public data source. Runs on a schedule, enriches results with a free LLM, stores to a database, and improves over time.

Advanced data modeling tool for complex multi-table schemas with automated relationship management and ER diagram generation. \n \n Designed for enterprise-level scenarios requiring multi-entity relationships, foreign key automation, and visual documentation; most simple table creation should use relational-database-tool directly with SQL \n Generates Mermaid class diagrams following strict type mapping, naming conventions, and constraint rules for consistent schema design \n Supports required/u

SQL-powered analysis of Excel and CSV files with schema inspection, aggregation, and multi-format export. \n \n Execute arbitrary SQL queries against uploaded data, including joins across multiple files, window functions, and pivot-style aggregations \n Inspect file structure (sheets, columns, data types, row counts) and generate statistical summaries (mean, median, stddev, percentiles, null counts) for numeric and string columns \n Export query results to CSV, JSON, or Markdown; results are cac

Query onchain data on Base using SQL with per-query x402 payments. \n \n Access decoded events, transactions, and blocks via CoinbaseQL, a ClickHouse-based SQL dialect supporting joins, CTEs, subqueries, and standard functions \n Three main tables available: base.events (decoded smart contract logs), base.transactions (full transaction data), and base.blocks (block metadata) \n Requires filtering on indexed fields ( event_signature , address , block_timestamp ) in event queries to avoid full tab

Provides data discovery and analysis expertise specializing in extracting actionable insights from complex datasets, identifying patterns and anomalies, and transforming raw data into strategic intelligence. Excels at multi-source data integration, advanced analytics, and data-driven decision support.

This skill enables comprehensive data visualization and analysis for CSV files. It provides three main capabilities: (1) creating individual interactive visualizations using Plotly, (2) automatic data profiling with statistical summaries, and (3) generating multi-plot dashboards. The skill is optimized for exploratory data analysis, statistical reporting, and creating presentation-ready visualizations.