connect-data

Guide users through connecting datasets from CSV, DuckDB, PostgreSQL, BigQuery, or Snowflake sources.

21|11|Updated Mar 15, 2026
One-click install
npx skills add https://github.com/ai-analyst-lab/ai-analyst-plugin --skill connect-data-ai-analyst-lab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: connect-data
Source: https://github.com/ai-analyst-lab/ai-analyst-plugin/tree/main/skills/connect-data
Command: npx skills add https://github.com/ai-analyst-lab/ai-analyst-plugin --skill connect-data-ai-analyst-lab

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill guides users through connecting a new dataset by selecting a connection type, collecting credentials, validating the connection, profiling the schema, and bootstrapping the knowledge brain.

Core Features & Use Cases

  • Guided connection wizard for multiple data sources (CSV, DuckDB, MotherDuck, PostgreSQL, BigQuery, Snowflake) and automatic dataset brain setup
  • Step-by-step collection of credentials, validation, and schema profiling to ensure a ready-to-use dataset
  • Use Case: A data analyst wants to connect a new PostgreSQL database and generate a schema and active dataset for exploration

Quick Start

Say "connect-data" to start the connection wizard and begin connecting a dataset.

Frequently Asked Questions about connect-data

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I connect a PostgreSQL database and generate a schema for analysis?

To connect a PostgreSQL database, use a guided dataset connection wizard to collect credentials, validate the connection, profile the schema, and bootstrap a working dataset brain for exploration.

Can I use this guided connection wizard to set up CSV and BigQuery data sources?

Yes, the guided connection wizard supports CSV, DuckDB, MotherDuck, PostgreSQL, BigQuery, and Snowflake data sources, automatically profiling schemas and initializing a working brain for each.

What is dataset brain setup and when do I need it for data exploration?

Dataset brain setup initializes a working knowledge brain during the dataset connection process, generating schemas and configuring the active dataset so analysts can immediately query and explore connected data sources.

How do I validate data source credentials before profiling a dataset schema?

The connection wizard validates data source credentials step-by-step before proceeding to schema profiling, ensuring the database or file connection is secure and ready for dataset brain initialization.

Does this dataset connection process handle credentials securely for Snowflake and MotherDuck?

Yes, the dataset connection process applies secure handling of credentials across all supported sources including Snowflake and MotherDuck, collecting and validating them before schema profiling and brain setup.

What's the best way to add a new DuckDB dataset and initialize a working brain?

The best way to add a DuckDB dataset is through the guided connection wizard, which handles data-source selection, credential collection, connection validation, schema profiling, and automatic dataset brain creation end-to-end.