databricks-vector-search
Patterns for Databricks Vector Search: create endpoints and indexes, query with filters, manage embeddings. Use when building RAG applications, semantic search, or similarity matching. Covers both storage-optimized and standard endpoints.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates specific capabilities, includes natural trigger terms, and explicitly states both what the skill does and when to use it. The Databricks Vector Search focus provides excellent distinctiveness, and the description covers key use cases (RAG, semantic search, similarity matching) without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'create endpoints and indexes, query with filters, manage embeddings' and further specifies 'storage-optimized and standard endpoints'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('create endpoints and indexes, query with filters, manage embeddings') and when ('Use when building RAG applications, semantic search, or similarity matching'). The 'Use when...' clause is explicit and well-defined. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Databricks Vector Search', 'RAG applications', 'semantic search', 'similarity matching', 'embeddings', 'endpoints', 'indexes'. These cover the main terms a user working in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with 'Databricks Vector Search' as a clear niche. The combination of Databricks-specific terminology with vector search operations makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent progressive disclosure and concrete executable examples covering all major Vector Search operations. Its main weaknesses are moderate verbosity with some redundancy between sections (Quick Start vs MCP Tools) and the lack of an explicit sequenced workflow with validation checkpoints in the main file — the end-to-end flow is deferred to a reference file.
Suggestions
Add a brief sequenced workflow (e.g., 'Create endpoint → poll until ONLINE → create index → poll until READY → query') with explicit validation/status-check steps to improve workflow clarity.
Reduce redundancy by consolidating the MCP Tools section — it largely repeats the SDK examples above. Consider a brief table mapping MCP tool names to actions with a note that they mirror the SDK patterns already shown.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy — for example, the MCP Tools section largely repeats patterns already shown in Quick Start and Common Patterns. The overview tables and 'When to Use' section add moderate value but could be tighter. The embedding models table and some explanatory text (e.g., 'Databricks Vector Search provides managed vector similarity search...') explain things Claude likely knows. | 2 / 3 |
Actionability | The skill provides fully executable Python code examples for every major operation: creating endpoints, creating all three index types, querying with text/vectors/hybrid, filtering, upserting, deleting, and syncing. CLI commands are also concrete and copy-paste ready. The code uses real SDK methods with realistic parameters. | 3 / 3 |
Workflow Clarity | While individual operations are clear, there's no explicit end-to-end workflow with validation checkpoints. Endpoint creation is noted as asynchronous but there's no explicit 'wait/poll until ready before creating index' step. The skill delegates the full workflow to end-to-end-rag.md rather than providing a clear sequenced process with validation steps in the main file. For operations like index creation and sync, there are no feedback loops for error handling. | 2 / 3 |
Progressive Disclosure | The skill has a clear structure with a Quick Start section, Common Patterns for deeper usage, and a well-organized Reference Files table pointing to one-level-deep detailed guides (index-types.md, end-to-end-rag.md, search-modes.md, troubleshooting-and-operations.md). Related skills are also clearly linked. Navigation is straightforward. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- databricks-solutions/ai-dev-kit
- Commit
02aac8c
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.