dltHub
Official@dlt-hub · Germany
dltHub is the creator of data load tool (dlt)
Agent Skills by dltHub
Showing 41 vetted skills indexed across 3 GitHub repositories.
comment-style
Enforces terse, factual comment and docstring style in Python code reviews.
repo-rules
Enforces project-wide editing rules for the dlthub-start repository before file modifications.
dlthub-router
Routes user intent to the matching dltHub toolkit and installs it on demand.
deploy-run-sample-pipeline
Deploys and runs the pre-shipped Jaffle Shop sample pipeline on dltHub Platform.
init-dlthub-workspace
Initializes and verifies dltHub workspaces with uv environment setup and toolkit routing.
one-shot-workflow
Deploys and runs a pre-shipped GitHub pipeline on the dltHub Platform cloud destination.
commit
Stages changes and writes Conventional-Commit messages following repository git rules.
review-issues-severity
Prioritize open GitHub issues by severity, community impact, and maintainer abandonment.
review-vocabulary
Review and rewrite branch prose against a fixed vocabulary and Simplified Technical English rules.
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
Updates existing skills with debugging patterns and workflow learnings captured from the current session.
adjust-endpoint
Configure dlt pipeline API endpoints for production data loading.
create-rest-api-pipeline
Generate a dlt pipeline for ingesting data from a REST API source.
find-source
Identify dlt source connectors for APIs and data providers.
Frequently Asked Questions About dltHub
FAQPage SchemaWhat specific data engineering tasks does dltHub enable?▼
dltHub enables the generation of ingestion pipelines from REST sources, schema validation of loaded datasets, and the configuration of production destinations like Motherduck. It provides capabilities for debugging pipeline traces, managing secrets, and visualizing data integrity using ibis expressions and Altair.
Which technical personas benefit from these capabilities?▼
Data engineers and backend developers focused on building, maintaining, and deploying robust data ingestion pipelines benefit from these capabilities. The environment is specifically designed for those managing complex Git-based development cycles and requiring structured validation of data loads.
What are the prerequisites for deploying a pipeline to the runtime?▼
Deployment requires a configured workspace with valid production credentials and destination settings, such as Motherduck. Users must verify the runtime environment, ensure secrets are managed within the required .toml files, and prepare the workspace for scheduled execution via the deployment interface.