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 identifies its domain (Databricks Vector Search), lists concrete actions, provides explicit 'Use when' triggers with natural user terms, and distinguishes itself from generic vector/embedding skills. It uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'create endpoints and indexes, query with filters, manage embeddings' along with specific use cases like 'RAG applications, semantic search, similarity matching' and endpoint types 'storage-optimized and standard endpoints'. | 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') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Databricks', 'Vector Search', 'endpoints', 'indexes', 'embeddings', 'RAG', 'semantic search', 'similarity matching'. These cover the main terms a user working in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with the specific combination of 'Databricks Vector Search' as the domain, plus specific triggers like 'storage-optimized and standard endpoints'. Unlikely to conflict with generic search or embedding skills due to the Databricks-specific framing. | 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 strong, comprehensive skill that excels in actionability and progressive disclosure, providing executable code for all major operations and well-organized references to deeper content. The main weaknesses are moderate verbosity (some sections like 'When to Use' and the Overview table add little value for Claude) and the lack of explicit validation workflows for multi-step operations like endpoint creation → index creation → querying.
Suggestions
Add a brief sequential workflow with validation checkpoints (e.g., check endpoint status before creating index, verify index sync status before querying) to improve workflow clarity.
Remove or condense the 'When to Use' section and the Overview component table — Claude can infer these from context, and the token budget would be better spent elsewhere.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured but includes some unnecessary content like the 'When to Use' section (Claude can infer this), the Overview table explaining basic concepts, and some redundancy between SDK examples and MCP tool examples. The embedding models table and some notes could be tightened. | 2 / 3 |
Actionability | Excellent actionability with fully executable Python code examples for every operation: creating endpoints, creating all three index types, querying with text/vectors/hybrid, filtering with both syntaxes, CRUD operations, CLI commands, and MCP tool usage. All examples are copy-paste ready with realistic parameters. | 3 / 3 |
Workflow Clarity | While individual operations are clearly documented, the skill lacks explicit validation checkpoints and sequenced workflows. For example, endpoint creation is noted as asynchronous but there's no explicit 'wait for ready' step before creating indexes. The end-to-end workflow is deferred to a reference file rather than outlined here. No feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear Reference Files table pointing to one-level-deep resources (index-types.md, end-to-end-rag.md, search-modes.md, troubleshooting-and-operations.md). The main skill provides a comprehensive overview with quick-start patterns while deferring detailed topics appropriately. Related skills section adds good cross-navigation. | 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
b4071a0
- 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.