Connect Data

Guided wizard to connect a new dataset to the AI Analyst system. Use this skill whenever the user wants to add a new data source, connect a database, set up data access, or configure a new dataset for analysis. This skill handles the full connection workflow: choosing connection type (CSV, DuckDB, MotherDuck, PostgreSQL, BigQuery, Snowflake), collecting credentials, validating connectivity, profiling schema, and setting up the knowledge brain. Trigger this skill when users say things like "/connect-data", "connect my database", "add a new dataset", "set up my data", "I have a database I want to analyze", "can you connect to my Postgres/BigQuery/Snowflake", "I need to add CSV files", "how do I get my data into this system", or "connect to my warehouse". Also trigger after first-run welcome when users need to set up their first dataset, or after /switch-dataset when the target dataset doesn't exist yet. This is the primary entry point for all new data connections — always offer this when users mention having data they want to analyze but haven't connected yet.

mkdir -p ~/.claude/skills/connect-data
curl -L https://claudskills.com/skills/connect-data/SKILL.md \
  -o ~/.claude/skills/connect-data/SKILL.md

@misc{connect-data-2026,
  author    = {ai-analyst-lab},
  title     = {Connect Data [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/connect-data/}
}