DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to write SQL queries for warehouse data with Knowledge Work Plugins

Use the data plugin to draft and refine queries against a connected warehouse.

Credentials. The warehouse connector needs database credentials, so store them in your secret manager and do not commit them to the .mcp.json file.

Who it is forA data analyst or product manager who needs a query against Snowflake, Databricks, or BigQuery but does not want to write the SQL from scratch.

The problemWriting a correct query against an unfamiliar warehouse schema takes time and back-and-forth.

The outcomeA SQL query drafted by Claude through the data plugin's write-query command, ready for review before running.

What you need first

  • Access to Claude Cowork or Claude Code
  • Accounts for the tools you want to connect, such as your CRM, warehouse, or ticketing system
  • Credentials for each connector you enable

Steps

  1. Run claude plugin marketplace add anthropics/knowledge-work-plugins
  2. Run claude plugin install data@knowledge-work-plugins (inferred, check the README)
  3. Connect your warehouse, such as Snowflake, Databricks, or BigQuery, through its connector
  4. Run /data:write-query and describe the question in plain language

Prompt for your agent

Using the anthropics/knowledge-work-plugins repo, install the data plugin and run /data:write-query for <question about the dataset>. Expected output: a SQL query that answers the question. Verify the query against the table and column names in the connected warehouse before running it.

Caveat. The README names the write-query command but does not say which SQL dialects or warehouses are tested, so check the generated query against your warehouse before running it.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page