DuckDB CLI specialist for SQL analysis, data processing and file conversion. Use for SQL queries, CSV/Parquet/JSON analysis, database queries, or data conversion. Triggers on "duckdb", "sql", "query",
Real data. Real impact.
Emerging
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
Helps with data analysis, SQL queries and file conversion via DuckDB CLI.
# CSV duckdb -c "SELECT * FROM 'data.csv' LIMIT 10"Parquet
duckdb -c "SELECT * FROM 'data.parquet'"
Multiple files with glob
duckdb -c "SELECT * FROM read_parquet('logs/*.parquet')"
JSON
duckdb -c "SELECT * FROM read_json_auto('data.json')"
# Create/open database duckdb my_database.duckdbRead-only mode
duckdb -readonly existing.duckdb
| Flag | Format |
|---|---|
| Comma-separated |
| JSON array |
| ASCII table |
| Markdown table |
| HTML table |
| One value per line |
| Argument | Description |
|---|---|
| Run SQL and exit |
| Run script from file |
| Use alternative to ~/.duckdbrc |
| Open in read-only mode |
| Show commands before execution |
| Stop on first error |
| Show/hide column headers |
| Text for NULL values |
| Column separator |
duckdb -c "COPY (SELECT * FROM 'input.csv') TO 'output.parquet' (FORMAT PARQUET)"
duckdb -c "COPY (SELECT * FROM 'input.parquet') TO 'output.csv' (HEADER, DELIMITER ',')"
duckdb -c "COPY (SELECT * FROM read_json_auto('input.json')) TO 'output.parquet' (FORMAT PARQUET)"
duckdb -c "COPY (SELECT * FROM 'data.csv' WHERE amount > 1000) TO 'filtered.parquet' (FORMAT PARQUET)"
| Command | Description |
|---|---|
| Show tables (with LIKE pattern) |
| Show CREATE statements |
| Show attached databases |
| Command | Description |
|---|---|
| Change output format |
| Send output to file |
| Next output to file |
| Show/hide column headers |
| Set separators |
| Command | Description |
|---|---|
| Show execution time |
| Show commands before execution |
| Stop on error |
| Run SQL from file |
| Command | Description |
|---|---|
| Open query in external editor |
| Show help |
| Shortcut | Action |
|---|---|
| Start/end of line |
| Jump word |
| Start/end of buffer |
| Shortcut | Action |
|---|---|
| Previous/next command |
| Search history |
| First/last in history |
| Shortcut | Action |
|---|---|
| Delete word backward |
| Delete word forward |
| Uppercase/lowercase word |
| Delete to end of line |
| Shortcut | Action |
|---|---|
| Autocomplete / next suggestion |
| Previous suggestion |
| Undo autocomplete |
Context-aware autocomplete activated with
TabCREATE TABLE sales AS SELECT * FROM 'sales_2024.csv';
INSERT INTO sales SELECT * FROM 'sales_2025.csv';
COPY sales TO 'backup.parquet' (FORMAT PARQUET);
SELECT COUNT(*) as count, AVG(amount) as average, SUM(amount) as total FROM 'transactions.csv';
SELECT category, COUNT(*) as count, SUM(amount) as total FROM 'data.csv' GROUP BY category ORDER BY total DESC;
SELECT a.*, b.name FROM 'orders.csv' a JOIN 'customers.parquet' b ON a.customer_id = b.id;
DESCRIBE SELECT * FROM 'data.csv';
# Read from stdin cat data.csv | duckdb -c "SELECT * FROM read_csv('/dev/stdin')"Pipe to another command
duckdb -csv -c "SELECT * FROM 'data.parquet'" | head -20
Write to stdout
duckdb -c "COPY (SELECT * FROM 'data.csv') TO '/dev/stdout' (FORMAT CSV)"
Save common settings in
~/.duckdbrc.timer on .mode duckbox .maxrows 50 .highlight on
.keyword green .constant yellow .comment brightblack .error red
Open complex queries in your editor:
.edit
Editor is chosen from:
DUCKDB_EDITOREDITORVISUALviSecure mode that restricts file access. When enabled:
.read.output.import.shLIMITread_csv_autoread_json_automemory_limitNo automatic installation available. Please visit the source repository for installation instructions.
View Installation Instructions
1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.