MCP App StoreMCP App StoreThis skill equips an agent to operate and manage dbt projects using the dbt CLI. It covers project initialisation, dependency management, compilation, running models (including targeted selections and state-aware runs), tests, snapshots, seeds, documentation generation and serving, and common debugging and CI-friendly patterns. The skill lists concrete dbt commands for each operation and guidance on authentication/configuration via profiles.yml.
Invoke this skill when the user asks to run or debug dbt models, generate or serve documentation, run test suites, perform selective runs (by tag, path, state), or prepare dbt commands for CI/CD. It's useful in developer workflows, pull-request automation, and data pipeline troubleshooting where dbt is the transformation layer.
Agents that can run shell commands and have access to the project workspace and data warehouse credentials (CI agents, developer assistants, automation bots).
Pure CLI reference skill for dbt with no bundled scripts. Covers project setup, model execution, testing, snapshots, docs, and debugging comprehensively. Well-organized with clear command examples and a useful node selection syntax table. Lacks error handling guidance and troubleshooting. Architecture is monolithic — all content in one SKILL.md with no scripts/ or references/ separation.
Clean reference skill. Could improve by adding a troubleshooting section, splitting the node selection syntax table into references/, and adding error handling patterns for common dbt failures.
Dagster
Build and manage Dagster data pipelines -- create assets, jobs, schedules, sensors, and resources.
Dlt
Build data ingestion pipelines with dlt (data load tool) -- extract from APIs, databases, and files, then load to any destination.
Metabase (dashboard & questions manager)
Manage Metabase instances: create and run questions, manage dashboards and collections, and interact with the Metabase REST API for analytics workflows.
PostgreSQL
Query and manage PostgreSQL databases via psql: run queries, inspect schemas and tables, check active connections, and perform basic administration and exports.
BigQuery
Query and manage Google BigQuery datasets with the bq CLI: run SQL, inspect schemas, list tables, load CSV/JSON, and manage partitioning.
DuckDB — Local Warehouse Explorer
Run SQL and explore a project DuckDB warehouse: list tables, inspect schemas, run queries, and ingest CSV/Parquet/JSON files for ad-hoc analysis.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
WRDS Query & ETL Enforcement
Standards and enforcement guidance for querying WRDS data and running SAS/ETL on the WRDS grid—includes query validation, SGE submission patterns, and performan
Scikit-learn (Classical ML reference)
Comprehensive scikit-learn guidance for classification, regression, clustering, preprocessing, model evaluation, and production-ready ML pipelines.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
WhoDB
Database assistant for exploring and querying Postgres, MySQL, SQLite, MongoDB, Redis, Elasticsearch and ClickHouse — via MCP tools or CLI fallbacks.
Visualization Best Practices
Provides step-by-step guidance and production-ready patterns for creating clear, accurate, and effective data visualizations in analytics workflows.
CDC Pipeline Creator
Automates creation and configuration of change-data-capture (CDC) data pipelines: generates configs, code snippets, validations and best-practice recommendation
SWE-AF — Autonomous Software Engineering Fleet
Orchestrates a coordinated multi-agent engineering workflow to plan, implement, test, and merge production-grade changes across single or multiple repositories.
