dlt-hubOfficial·20 Agent Skills Included

dlthub-ai-workbench

Guided workflows to build, deploy, and monitor data pipelines

Builds data pipelines that load data from REST APIs, SQL databases, and cloud files into warehouses. Guides each step from source discovery and credentials to debugging, incremental loading, and performance tuning. Adds data quality checks, transformations, dashboards, and scheduled cloud deployment without manual boilerplate.

53|5

↗

npx skills add dlt-hub/dlthub-ai-workbench --all -g -y

Available:

Tells the agent how toolkits are structured, how to match user intent to the right toolkit, install it, and enter its workflow at the correct starting skill.

All Skills in This Repository (20)

Pure Emerald Level Indicators

📦 In Repo

dlt-hub

run-eval

Evaluate AI skill trigger accuracy against test queries using Python scripts.

validate-toolkits

Validate AI toolkit integrity by checking URLs, cross-references, and documentation sync.

create-eval

Scaffold trigger evaluation setups for toolkit skills with test workspaces and queries.

rename-component

Rename components in a dlt toolkit and update cross-references.

toolkit-dispatch

Route user requests to appropriate dlt toolkits and skills by intent.

setup-secrets

Manage dlt secrets in *.secrets.toml files for API keys, passwords, and tokens.

explore-data

Explore, profile, and visualize data in dlt pipelines with SQL and Altair code.

build-notebook

Assemble and validate Marimo Python notebooks from analysis plan files.

validate-data

Validate schemas and data integrity after dlt pipeline loads.

view-data

Query and explore dlt pipeline data using Python and ibis expressions.

new-endpoint

Add a REST API endpoint to an existing dlt pipeline configuration.

improve-skills

Update existing AI skills with session learnings and debugging patterns.

Official

Intermediate

Frequently Asked Questions

FAQPage Schema

How to install dlthub-ai-workbench?▼

Run `npx skills add dlt-hub/dlthub-ai-workbench --all -g -y` in your terminal to install all toolkits globally.

How to build a data pipeline from a REST API?▼

The rest-api-pipeline toolkit finds a verified connector for your API, scaffolds the pipeline, and walks you through debugging, pagination, and incremental loading.

Can it load data from Postgres or MySQL?▼

Yes. The sql-database-pipeline toolkit builds pipelines from any SQLAlchemy-supported database and helps you pick the fastest backend for your data volume.

Does it work with Claude Code, Cursor, and Codex?▼

Yes. All toolkits follow the standard SKILL.md format and are tested with Claude Code, Cursor, and Codex.

Can I deploy and schedule pipelines without DevOps experience?▼

Yes. The dlthub-platform toolkit handles credentials, deployment, cron scheduling, and log debugging through plain-English requests.