Duckdb Cli

DuckDB CLI specialist for SQL analysis, data processing and file conversion. Use for SQL queries, CSV/Parquet/JSON analysis, database queries, or data conver...

Security Scan

The skill is mostly documentation for the DuckDB CLI and appears harmless, but there are metadata and expectation mismatches (it does not declare the DuckDB binary requirement and package metadata fields differ) that merit caution before installing.

Purpose & Capability

The skill's name/description match the SKILL.md content (DuckDB CLI usage, SQL, conversions). However the package declares no required binaries while every runtime example invokes the duckdb CLI — the skill implicitly requires the duckdb binary to be available but does not declare that dependency. Also _meta.json contains owner/slug values that differ from the registry metadata, which is an inconsistency in provenance.

Instruction Scope

SKILL.md contains only usage examples, CLI flags, and examples that read and write local files, stdout/stdin, and the ~/.duckdbrc config. It does not direct data to external endpoints, request unrelated credentials, or instruct the agent to scan system state beyond files the user works with. Reading/writing arbitrary local files is expected for this purpose and is documented.

Install Mechanism

This is an instruction-only skill with no install spec or code to write to disk. README suggests a manual copy into a Claude skills directory. No remote downloads or extracted archives are used.

Credentials

No environment variables, credentials, or config paths are required. The skill does reference ~/.duckdbrc (DuckDB CLI config) and common filesystem paths like /dev/stdin — appropriate for a CLI helper and not requests for secrets.

Persistence & Privilege

Skill does not request always: true and does not attempt to modify other skills or system-wide settings. It is user-invocable and can be called autonomously by the agent (platform default), which is reasonable for a helper skill.

Scan Findings in Context

[no-regex-findings] expected: The static scanner had no regex matches — expected because this is an instruction-only skill with no code files to analyze.

[missing-declared-binary] unexpected: SKILL.md repeatedly invokes the 'duckdb' CLI but the skill's metadata lists no required binaries. Users should expect the duckdb executable to be necessary; omission is an incoherence that could mislead about runtime prerequisites.

[metadata-mismatch] unexpected: _meta.json ownerId/slug differ from the registry metadata shown above (and README slug differs). This inconsistency in provenance/packaging should be investigated before trusting the skill source.

What to consider before installing

This skill is essentially documentation and examples for using the DuckDB CLI — it doesn't request secrets or install code — but check a few things before using it with sensitive data: 1) Ensure you have the duckdb binary installed and know its location (the skill assumes 'duckdb' is on PATH but does not declare it). 2) Confirm the skill's source/owner (registry metadata vs _meta.json/README show inconsistent IDs/slugs); only install from a trusted publisher. 3) Be aware the examples read/write arbitrary local files and the ~/.duckdbrc config; review that file for sensitive content before letting any automated agent run commands. 4) If you plan to run the suggested commands in an automated agent, restrict them to non-sensitive test data first. If you want higher confidence, ask the publisher to correct the declared dependencies and metadata before installing.

DuckDB CLI Specialist

Helps with data analysis, SQL queries and file conversion via DuckDB CLI.

Quick Start

Read data files directly with SQL

# 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')"

Open persistent databases

# Create/open database
duckdb my_database.duckdb

# Read-only mode
duckdb -readonly existing.duckdb

Command Line Arguments

Output formats (as flags)

Flag	Format
-csv	Comma-separated
-json	JSON array
-table	ASCII table
-markdown	Markdown table
-html	HTML table
-line	One value per line

Execution arguments

Argument	Description
-c COMMAND	Run SQL and exit
-f FILENAME	Run script from file
-init FILE	Use alternative to ~/.duckdbrc
-readonly	Open in read-only mode
-echo	Show commands before execution
-bail	Stop on first error
-header / -noheader	Show/hide column headers
-nullvalue TEXT	Text for NULL values
-separator SEP	Column separator

Data Conversion

CSV to Parquet

duckdb -c "COPY (SELECT * FROM 'input.csv') TO 'output.parquet' (FORMAT PARQUET)"

Parquet to CSV

duckdb -c "COPY (SELECT * FROM 'input.parquet') TO 'output.csv' (HEADER, DELIMITER ',')"

JSON to Parquet

duckdb -c "COPY (SELECT * FROM read_json_auto('input.json')) TO 'output.parquet' (FORMAT PARQUET)"

Convert with filtering

duckdb -c "COPY (SELECT * FROM 'data.csv' WHERE amount > 1000) TO 'filtered.parquet' (FORMAT PARQUET)"

Dot Commands

Schema inspection

Command	Description
.tables [pattern]	Show tables (with LIKE pattern)
.schema [table]	Show CREATE statements
.databases	Show attached databases

Output control

Command	Description
.mode FORMAT	Change output format
.output file	Send output to file
.once file	Next output to file
.headers on/off	Show/hide column headers
.separator COL ROW	Set separators

Queries

Command	Description
.timer on/off	Show execution time
.echo on/off	Show commands before execution
.bail on/off	Stop on error
.read file.sql	Run SQL from file

Editing

Command	Description
.edit or \e	Open query in external editor
.help [pattern]	Show help

Output Formats (18 available)

Data export

• csv - Comma-separated for spreadsheets
• tabs - Tab-separated
• json - JSON array
• jsonlines - Newline-delimited JSON (streaming)

Readable formats

• duckbox (default) - Pretty ASCII with unicode box-drawing
• table - Simple ASCII table
• markdown - For documentation
• html - HTML table
• latex - For academic papers

Specialized

• insert TABLE - SQL INSERT statements
• column - Columns with adjustable width
• line - One value per line
• list - Pipe-separated
• trash - Discard output

Keyboard Shortcuts (macOS/Linux)

Navigation

Shortcut	Action
Home / End	Start/end of line
Ctrl+Left/Right	Jump word
Ctrl+A / Ctrl+E	Start/end of buffer

History

Shortcut	Action
Ctrl+P / Ctrl+N	Previous/next command
Ctrl+R	Search history
Alt+< / Alt+>	First/last in history

Editing

Shortcut	Action
Ctrl+W	Delete word backward
Alt+D	Delete word forward
Alt+U / Alt+L	Uppercase/lowercase word
Ctrl+K	Delete to end of line

Autocomplete

Shortcut	Action
Tab	Autocomplete / next suggestion
Shift+Tab	Previous suggestion
Esc+Esc	Undo autocomplete

Autocomplete

Context-aware autocomplete activated with Tab:

• Keywords - SQL commands
• Table names - Database objects
• Column names - Fields and functions
• File names - Path completion

Database Operations

Create table from file

CREATE TABLE sales AS SELECT * FROM 'sales_2024.csv';

Insert data

INSERT INTO sales SELECT * FROM 'sales_2025.csv';

Export table

COPY sales TO 'backup.parquet' (FORMAT PARQUET);

Analysis Examples

Quick statistics

SELECT
    COUNT(*) as count,
    AVG(amount) as average,
    SUM(amount) as total
FROM 'transactions.csv';

Grouping

SELECT
    category,
    COUNT(*) as count,
    SUM(amount) as total
FROM 'data.csv'
GROUP BY category
ORDER BY total DESC;

Join on files

SELECT a.*, b.name
FROM 'orders.csv' a
JOIN 'customers.parquet' b ON a.customer_id = b.id;

Describe data

DESCRIBE SELECT * FROM 'data.csv';

Pipe and stdin

# 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)"

Configuration

Save common settings in ~/.duckdbrc:

.timer on
.mode duckbox
.maxrows 50
.highlight on

Syntax highlighting colors

.keyword green
.constant yellow
.comment brightblack
.error red

External Editor

Open complex queries in your editor:

.edit

Editor is chosen from: DUCKDB_EDITOR → EDITOR → VISUAL → vi

Safe Mode

Secure mode that restricts file access. When enabled:

• No external file access
• Disables .read, .output, .import, .sh etc.
• Cannot be disabled in the same session

Tips

• Use LIMIT on large files for quick preview
• Parquet is faster than CSV for repeated queries
• read_csv_auto and read_json_auto guess column types
• Arguments are processed in order (like SQLite CLI)
• WSL2 may show incorrect memory_limit values on some Ubuntu versions