datahub-skills

Add or update metadata in DataHub - descriptions, tags, glossary terms, ownership

Explore lineage, trace data dependencies, and perform impact analysis

Manage data quality — assertions, incidents, and subscriptions

Search the DataHub catalog and answer questions about your data

Set up DataHub connection, install CLI, configure authentication and default scopes

Use this agent when you need to verify whether a PR author has genuinely addressed previous review comments before re-review. This agent fetches review comments, classifies them by type (code change request vs. discussion vs. question), and checks whether each was substantively addressed — not just marked as resolved. <example> Context: A PR has been updated after review and the author is requesting re-review. user: "Check if the author addressed all review comments on PR #1234" assistant: "I'll use the comment-resolution-checker agent to verify whether all review comments on PR #1234 have been substantively addressed." <commentary> PR re-review readiness check triggers this agent. </commentary> </example> <example> Context: User wants to know what's still outstanding on a PR before approving. user: "What review comments are still unaddressed on this PR?" assistant: "I'll use the comment-resolution-checker agent to analyze the PR's review comments and identify any that haven't been addressed." <commentary> Checking for unaddressed comments triggers this agent. </commentary> </example>

Research source systems for DataHub connector development. Gathers documentation, finds similar connectors, identifies entity mappings, and assesses implementation complexity. Returns structured findings for planning phase. <example> Context: User wants to build a new DataHub connector for a source system. user: "Research Snowplow for a new DataHub connector" assistant: "I'll use the connector-researcher agent to gather comprehensive research on Snowplow including API documentation, similar connectors, and entity mappings." <commentary> New connector research request triggers this agent. </commentary> </example> <example> Context: User is starting connector development and needs background information. user: "I need to build a connector for DuckDB, what do I need to know?" assistant: "I'll use the connector-researcher agent to research DuckDB's metadata APIs, find similar DataHub connectors, and assess implementation complexity." <commentary> Connector development information request triggers this agent. </commentary> </example>

Run provided validation scripts, analyze their output, and report results for DataHub connector verification steps. Handles extraction verification, capability checks, code quality gates, source connectivity, ingestion runs, and CLI verification. <example> Context: Workflow needs to verify that extraction output contains expected entities. user: "Run the verify-extraction script on the output file" assistant: "I'll use the connector-validator agent to run the verification script and analyze the results." <commentary> Extraction verification is a procedural script-running task that triggers this agent. </commentary> </example> <example> Context: Workflow needs to check that declared capabilities produce actual output. user: "Run the capability check on the connector" assistant: "I'll use the connector-validator agent to run the capability check script and report coverage." <commentary> Capability validation is a script-based check that triggers this agent. </commentary> </example>

Execute DataHub search, browse, and lineage operations, retrieve entity metadata, and return structured results. Used by the datahub-search and datahub-lineage skills to delegate catalog queries. <example> Context: User wants to find all Snowflake datasets with PII tags. user: "Search DataHub for Snowflake datasets tagged with PII" assistant: "I'll use the metadata-searcher agent to query DataHub for Snowflake datasets with PII tags." <commentary> The search skill delegates the actual search execution to this agent, which runs the queries and returns structured results. </commentary> </example> <example> Context: User asks who owns the revenue pipeline and needs metadata gathered. user: "Who owns the revenue pipeline?" assistant: "I'll use the metadata-searcher agent to find revenue-related pipelines and retrieve their ownership metadata." <commentary> The search skill delegates multi-step metadata retrieval to this agent, which searches, fetches aspects, and returns evidence for answering the question. </commentary> </example>

Plans new DataHub connectors by classifying the source system, researching it using a dedicated agent or inline research, and generating a _PLANNING.md blueprint with entity mapping and architecture decisions. Use when building a new connector, researching a source system for DataHub, or designing connector architecture. Triggers on: "plan a connector", "new connector for X", "research X for DataHub", "design connector for X", "create planning doc", or any request to plan/research/design a DataHub ingestion source.

Reviews DataHub connector implementations against 22 golden standards for compliance, code quality, silent failures, test coverage, type design, and merge readiness. Use when reviewing connector code, checking a PR, auditing a connector implementation, or verifying connector standards compliance.

Use this skill when the user wants to add or update metadata in DataHub: descriptions, tags, glossary terms, ownership, deprecation, domains, data products, structured properties, documents, or field-level metadata. Triggers on: "add tag to X", "update description for X", "set owner of X", "add glossary term", "deprecate X", "create a domain", "create a glossary term", "add a document", or any request to modify DataHub metadata.

Use this skill when the user wants to explore lineage, trace data dependencies, perform impact analysis, find root causes, map data pipelines, or understand how data flows between systems. Triggers on: "what feeds into X", "what depends on X", "show lineage for X", "impact analysis", "trace the pipeline", "root cause", "upstream of X", "downstream of X", or any request involving data lineage and dependency tracking.

Configure a DataHub instance to load and display a Micro Frontend (MFE) app. Use when the user wants to register an MFE with DataHub, add an MFE to the nav sidebar, set up MFE config for local dev or production/k8s, or troubleshoot MFE loading issues.