datahub-quality

A DataHub skill that walks through building new data connectors in four steps: classify the source system, research it, generate a planning document with entity mapping and architecture, and get approval before writing code.

A skill that loads all 22 DataHub connector golden standards into context, covering core standards, interface-specific standards (SQL, API, lineage), and source-type standards across 11 categories. Use it before starting connector development or review work to ensure the full set of DataHub connector development guidelines is available for reference.

A skill for reviewing DataHub connector implementations against 22 golden standards covering compliance, code quality, silent failures, test coverage, type design, and merge readiness. It supports multi-agent dispatch for deep analysis and includes security guardrails to prevent prompt injection from untrusted PR content.

A routing skill for DataHub that maps user intent to the correct DataHub interaction skill, covering search/discovery, metadata enrichment, lineage exploration, data quality management, and CLI setup.

A DataHub skill for searching and discovering entities in the data catalog. Operates in discovery mode (find, browse, list entities) and question mode (answer analytical questions by querying metadata), with multi-agent compatibility across Claude Code, Cursor, Codex, and other agents.

Provides expert DataHub lineage analysis capabilities, enabling tracing of data dependencies, impact analysis, root cause identification, data pipeline mapping, and understanding data flow across systems through upstream and downstream exploration.

Agent skills for DataHub setup and interaction — plan connectors, search the catalog, enrich metadata, trace lineage, manage data quality, and configure connections across AI coding tools.

A DataHub metadata curation skill for adding and updating metadata including descriptions, tags, glossary terms, ownership, deprecation, domains, data products, structured properties, and documents. Supports both MCP tools and DataHub CLI with GraphQL mutations, batch operations, and mandatory approval workflows.

An agent skill for working with DataHub that enables planning and reviewing connectors, searching the catalog, enriching metadata, tracing lineage, managing data quality, and setting up connections. Compatible with Claude Code, Cursor, Codex, Copilot, Gemini CLI, and other Agent Skills-compatible tools.

Part of the DataHub skills collection that enables AI agents to search the data catalog, enrich metadata with descriptions and tags, trace data lineage, manage data quality assertions, and set up ingestion connections within the DataHub platform.