Add serialized_space schema and best practices to databricks-genie skill#473
Open
sean-zhang-dbx wants to merge 1 commit intodatabricks-solutions:mainfrom
Open
Conversation
Add two reference documents that fill gaps in the existing Genie skill: - references/schema.md: Complete serialized_space JSON schema including field reference tables, formatting rules (sql as string arrays, ID generation, sorting requirements), prompt matching (v1 vs v2 fields, API vs UI behavior), join_specs format (--rt= annotation), and benchmark configuration. - references/best-practices.md: Curated best practices covering instruction priority (SQL expressions > example SQL > text), SQL expression authoring (measures/filters/dimensions), example SQL query formatting, parameterized queries, text instruction tips, column configuration and prompt matching, benchmark creation (core vs stretch), a troubleshooting decision tree for 8 common issues, and a 23-item validation checklist. SKILL.md updated to link to the new reference files.
7 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
references/schema.md: completeserialized_spaceJSON schema with field reference tables, formatting rules, prompt matching docs, join_specs format, and benchmark configurationreferences/best-practices.md: curated best practices covering instruction authoring, column configuration, benchmarks, a troubleshooting decision tree, and a 23-item validation checklistSKILL.mdto link to the two new reference filesContext
The existing
databricks-genieskill covers MCP tool usage and the Conversation API well, but has no documentation for theserialized_spaceJSON payload structure or deeper best practices around instruction authoring, prompt matching, benchmarks, and troubleshooting. This PR fills those gaps with content adapted from the prompt-to-genie project.Test plan