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.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with concrete code and commands, but it carries redundant SDK/MCP coverage and lacks validation feedback loops for risky operations. Progressive disclosure is undermined by four broken reference links and somewhat monolithic inline content.

Suggestions

Add explicit validation/wait checkpoints for asynchronous and destructive operations: poll get_endpoint() until PROVISIONING_COMPLETE before creating indexes, and confirm sync status after sync_index() or batch upserts.

Create the four referenced files (index-types.md, end-to-end-rag.md, search-modes.md, troubleshooting-and-operations.md) or remove the dead links, since none currently exist in the bundle.

De-duplicate the SDK and MCP tool sections by presenting each operation once and noting the SDK-vs-MCP mapping, to reduce token cost and repetition.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient code and tables, but it duplicates the same operations across the SDK examples and the MCP Tools sections, which could be consolidated and tightened.	2 / 3
Actionability	It provides executable, copy-paste-ready Python code and CLI commands for endpoint/index creation, querying, filtering, and data operations.	3 / 3
Workflow Clarity	A Quick Start sequence exists (endpoint -> index -> query), but destructive and batch operations (delete index, upsert) lack validation checkpoints or wait-on-status feedback loops, which caps the score at 2.	2 / 3
Progressive Disclosure	References are clearly signaled in a Reference Files table, but all four referenced files (index-types.md, end-to-end-rag.md, search-modes.md, troubleshooting-and-operations.md) are missing from the bundle, and much detail is inline rather than split out.	2 / 3
	Total	9 / 12 Passed

Description

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.

The description is specific, uses third person, and clearly answers both what the skill does and when to use it with natural trigger terms. It occupies a distinct niche with low conflict risk.

Dimension	Reasoning	Score
Specificity	"create endpoints and indexes, query with filters, manage embeddings" lists multiple concrete actions rather than vague language, matching the score-3 anchor.	3 / 3
Completeness	It states both what it does (create/query/manage) and when to use it via an explicit "Use when building RAG applications, semantic search, or similarity matching" clause.	3 / 3
Trigger Term Quality	"RAG applications, semantic search, similarity matching" are natural terms users would say when they need this skill, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	The narrow "Databricks Vector Search" niche with RAG/semantic-search triggers makes it clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 6 missing, 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: databricks-solutions/ai-dev-kit
Path: databricks-skills/databricks-vector-search/SKILL.md
Commit: a7e1d51

Reviewed: about 4 hours ago

Table of Contents

Discovery Implementation Validation

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.