Datahub SQL Workflow
Ground text-to-SQL work in DataHub catalog evidence. Use when a user asks to write, draft, debug, or execute SQL; answer a data question that requires SQL; calculate a metric; query named tables; or investigate SQL results with DataHub MCP tools available. Always begin with find_sql_context, even when the user already supplied tables or dataset URNs, and call inspect_tables_for_sql on the chosen tables before writing SQL.
Install
/plugin marketplace add datahub-project/datahub-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add datahub-project/datahub-skills --skill datahub-sql-workflowgit clone --depth 1 https://github.com/datahub-project/datahub-skills.git /tmp/datahub-skills
mkdir -p ~/.claude/skills
cp -r /tmp/datahub-skills/skills/datahub-sql-workflow ~/.claude/skills/datahub-sql-workflowPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# DataHub SQL Workflow Ground every query in DataHub evidence. Two tools carry that evidence: - `find_sql_context(question)` routes: it returns a card with the documents your organization wrote about the question, the candidate tables, and the saved query patterns that touch them. - `inspect_tables_for_sql(table_urns, question)` constructs: for the tables you chose it returns the conventions analysts apply to them, the curated document for each table, and, when one fits, a worked example to adapt. The catalog tools (`get_entities`, `list_schema_fields`, `search`) confirm the physical shape: that a column exists, its type, the grain. Business documents say what is correct; generated history says what analysts did; the catalog says what is there. Rank them in that order when they disagree (section 4). Require `find_sql_context` and `inspect_tables_for_sql`. If either is missing, stop and ask the user to enable the DataHub MCP tools; do not fall back to other discovery tools, local files, memory, or the web. Treat every other tool as optional: when one is unavailable, say so and continue with the steps it does not affect. Never replace missing evidence with a guess. ## 1. Call `find_sql_context` first and read the whole card Call `find_sql_context(question=<the user's complete question>)` before any other tool, even when the user names tables or supplies dataset URNs. Pass the question as the user wrote it; do not shorten it to keywords.
Details
- Skill name
datahub-sql-workflow- Repository
- datahub-project/datahub-skills
- Path
skills/datahub-sql-workflow/SKILL.md- License
- Apache-2.0
- Repo updated
- 29 September 2026
FAQ
What does the Datahub SQL Workflow skill do?
Ground text-to-SQL work in DataHub catalog evidence. Use when a user asks to write, draft, debug, or execute SQL; answer a data question that requires SQL; calculate a metric; query named tables; or investigate SQL results with DataHub MCP tools available. Always begin with find_sql_context, even when the user already supplied tables or dataset URNs, and call inspect_tables_for_sql on the chosen tables before writing SQL.
How do I install the Datahub SQL Workflow skill?
Claude Code plugin: /plugin marketplace add datahub-project/datahub-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Datahub SQL Workflow popular?
It lives in datahub-project/datahub-skills, which has 46 GitHub stars and 98 forks.
Related skills
Datahub Connector Planning
46datahub-project/datahub-skills
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.
Datahub Connector PR Review
46datahub-project/datahub-skills
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.
Datahub Enrich
46datahub-project/datahub-skills
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.
Olore Drizzle Latest
119olorehq/olore
Local Drizzle ORM documentation reference (latest). Drizzle ORM documentation. Use for Drizzle queries, schema definitions, migrations, column types, PostgreSQL/MySQL/SQLite dialects, and Drizzle Kit.
Drupal Performance
84grasmash/drupal-claude-skills
Drupal performance review and optimization patterns and anti-patterns, backend and frontend. Treats cold-render database query count and volume per route as the core metric, because networked production databases cost roughly 10x or more per query than local, so local wall-time and Lighthouse hide real TTFB. Use when reviewing, profiling, or changing performance, before declaring performance work done, or for slow pages and high TTFB, N+1 queries, entity loads in loops, cache contexts and tags, render cache metadata, and CacheableJsonResponse endpoints.
Olore Neon Latest
119olorehq/olore
Local neon documentation reference (latest). Neon serverless Postgres documentation. Use for database branching, autoscaling, connection pooling, data API, extensions, migrations, and PostgreSQL features.
Browse the most popular Claude skills, all databases skills, or write your own with the skills generator.