SKILL.md
Load OpenMetadata Connector Standards
When to Activate
When a user asks to "load standards", "show connector standards", or before starting any connector development or review work.
Behavior
Load All Standards
If no specific standard is requested, load all standards in this order:
${CLAUDESKILLDIR}/standards/main.md— Architecture overview${CLAUDESKILLDIR}/standards/patterns.md— Error handling, logging, pagination${CLAUDESKILLDIR}/standards/code_style.md— Python and JSON Schema conventions${CLAUDESKILLDIR}/standards/schema.md— Connection schema patterns${CLAUDESKILLDIR}/standards/connection.md— Connection class patterns${CLAUDESKILLDIR}/standards/service_spec.md— ServiceSpec registration${CLAUDESKILLDIR}/standards/testing.md— Unit and integration test patterns${CLAUDESKILLDIR}/standards/registration.md— How to register a connector${CLAUDESKILLDIR}/standards/performance.md— Performance best practices${CLAUDESKILLDIR}/standards/memory.md— Memory management and OOM prevention${CLAUDESKILLDIR}/standards/lineage.md— Lineage extraction methods${CLAUDESKILLDIR}/standards/sql.md— SQLAlchemy patterns and URL building
Then read all source-type standards:
${CLAUDE_SKILL_DIR}/standards/source_types/*.mdLoad Specific Standard
If a specific standard or service type is requested:
| Request | File to Load |
|---|---|
| "testing" | standards/testing.md |
| "patterns" | standards/patterns.md |
| "schema" | standards/schema.md |
| "lineage" | standards/lineage.md |
| "sql" | standards/sql.md |
| "memory" | standards/memory.md |
| "database" | standards/source_types/database.md |
| "sql databases" | standards/sourcetypes/sqldatabases.md |
| "data warehouses" | standards/sourcetypes/datawarehouses.md |
| "nosql" | standards/sourcetypes/nosqldatabases.md |
| "dashboard" | standards/source_types/dashboard.md |
| "pipeline" | standards/source_types/pipeline.md |
| "messaging" | standards/source_types/messaging.md |
| "mlmodel" | standards/source_types/mlmodel.md |
| "storage" | standards/source_types/storage.md |
| "search" | standards/source_types/search.md |
| "api" | standards/source_types/api.md |
| etc. | standards/source_types/{name}.md |
After Loading
Confirm to the user which standards were loaded and summarize the key points. Example:
Loaded 12 core standards + 11 source-type standards. Key points:
- Schema-first: one JSON Schema → Python, Java, TypeScript, UI forms
- UseBaseConnectionfor SQLAlchemy,getconnection()/testconnection()for others
- Use pytest with plainassert, no unittest.TestCase
- Always include copyright header, useingestion_logger()
- Lineage via query logs (database), SQL parsing (dashboard), or task metadata (pipeline)