This is a practical wrapper around DuckDB that lets Claude read pretty much any data format you throw at it: CSV, JSON, Parquet, Excel, shapefiles, SQLite databases, even Jupyter notebooks. It handles local files and remote URLs from S3, HTTPS, GCS, and Azure. The implementation uses a single macro that pattern matches file extensions and routes to the right DuckDB reader, then shows you the schema, row count, and a 20 row preview. Useful when you want Claude to quickly inspect or answer questions about a dataset without writing format specific code yourself. It will auto install DuckDB if missing and retry with the right extensions if spatial or Excel files fail on first attempt.
npx -y skills add duckdb/duckdb-skills --skill read-file --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
prisma/skills
supabase/agent-skills
syahiidkamil/software-engineer-ai-agent-atlas
neondatabase/agent-skills
firebase/agent-skills
firebase/agent-skills