Datadata Skills

⌘ K

███████╗██╗  ██╗██╗██╗     ██╗     ███████╗
██╔════╝██║ ██╔╝██║██║     ██║     ██╔════╝
███████╗█████╔╝ ██║██║     ██║     ███████╗
╚════██║██╔═██╗ ██║██║     ██║     ╚════██║
███████║██║  ██╗██║███████╗███████╗███████║
╚══════╝╚═╝  ╚═╝╚═╝╚══════╝╚══════╝╚══════╝

Datadata Skills

Agent skills for the Datadata analytics platform. Reusable capabilities that give AI agents procedural knowledge to interact with Datadata through natural language.

Installation

Install all Datadata skills with a single command:

View package on skills.sh→

Skills

datadata-api

skill

Query Datadata via CLI — run ad-hoc SQL, inspect datasource metadata, list & describe tables, download results as NDJSON/CSV.

Query Data

Search datasources — public community search, private datasource search, username/name exact match
Metadata queries — inspect datasource info, list tables, describe column schemas
Execute SQL queries — DuckDB & ClickHouse engines, cross-source joins with DuckDB
Download results — NDJSON or CSV format
Schema scanning — trigger async scans to refresh table metadata

Ingest Data

Data Spaces table management — create tables, batch insert rows, drop tables in ducklake
Ingested data is immediately queryable via execute-adhoc

Other

User info — retrieve profile & permission list via whoami
Script generation — urllib.request examples, zero extra dependencies

Triggers:

Datadatadata explorationSQL querytable inspectionexecution results

datadata-dql

skill

Write DQL (Datadata Query Language) scripts — a Starlark-based scripting language for data transformation, cleaning, generation, and custom processing logic.

Core Capabilities

DataFrame/Series operations — transformation, cleaning, aggregation, merging, anomaly detection
SQL queries — execute SQL via query() and return DataFrame
HTTP requests — call external APIs via fetch()
2D drawing — Canvas basic graphics
Built-in modules — JSON, Time, Math, and more

Triggers:

Data transformationdata cleaningdata generationcustom data processing logic

Authentication

The skill supports two ways to authenticate:

Automatic

recommended

If no API Key is configured, the agent will automatically guide you through device authorization when you first run a command — just follow the link displayed in the terminal to complete sign-in. The key is then cached locally for 90 days.

Manual

Create an API Key in the Datadata platform with the required permissions:

Permission	Purpose
queries:execute-adhoc	Run SQL queries
executions:get	Retrieve query results
datasources:read	Read datasource metadata
datasources:scan	Trigger async schema scans
data-spaces:write	Create tables and insert data

Avatar → Settings → "API Keys" (left sidebar) → Create a new key

Select the required permissions

Set it as an environment variable:

export DATADATA_API_KEY="ak_..."