data-skills

Creates and maintains dlt (data load tool) pipelines from APIs, databases, and other sources. Use when the user wants to build or debug pipelines; use verified sources (e.g. Salesforce, GitHub, Stripe) or declarative REST API or custom Python; configure destinations (e.g. DuckDB, BigQuery, Snowflake); implement incremental loading; or edit .dlt config and secrets. Use when the user mentions data ingestion, dlt pipeline, dlt init, rest_api_source, incremental load, or pipeline dashboard.

Uses the uv Python package and project manager correctly for dependencies, venvs, and scripts. Use when creating or modifying Python projects, adding dependencies, running scripts with inline deps, managing virtual environments, pinning Python versions, running CLI tools from PyPI, setting the IDE Python interpreter, or using uv in CI (e.g. GitHub Actions) or Docker containers. Use when the user mentions uv, pyproject.toml, uv.lock, uv run, uv add, uv sync, .venv, Python interpreter, poetry, pipenv, conda, CI, Docker, GitHub Actions, or asks to use uv instead of pip or poetry.

Runs dlt pipelines in Dagster as software-defined assets (Component or Pythonic @dlt_assets) or as a single standard Dagster asset. Use when orchestrating dlt with Dagster; scaffolding loads.py/defs.yaml; jobs/schedules; secrets/env; incremental/backfill via apply_hints; parallelization (one asset per resource); Dagster Cloud deployment; or external compute (ECS, Fargate — refer to dagster-integrations). Triggers: dagster-dlt, dlt on Dagster, deploy dlt with Dagster, standard Dagster asset, external compute.