Resolves table and dataset references across AWS Glue Data Catalog, S3, S3 Tables, and Redshift with a layered search that stops at the first high-confidence match. Good for when you or another skill needs to find "the orders table" or reverse-lookup an S3 path to its catalog entry without burning tokens on full scans. Defaults to resolve mode (find the thing) rather than exploration, uses search-tables as the primary API, and only falls back to multi-database scans when necessary. The confidence gate and sources-searched reporting help you understand what was checked and what was skipped. Built to get you the answer fast and get out of the way.
npx skills add https://github.com/aws/agent-toolkit-for-aws --skill finding-data-lake-assets