databricks-ai-functions
Use Databricks built-in AI Functions (ai_classify, ai_extract, ai_summarize, ai_mask, ai_translate, ai_fix_grammar, ai_gen, ai_analyze_sentiment, ai_similarity, ai_parse_document, ai_query, ai_forecast) to add AI capabilities directly to SQL and PySpark pipelines without managing model endpoints. Also covers document parsing and building custom RAG pipelines (parse → chunk → index → query).
70
85%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
82%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 description with excellent specificity, listing all 12 Databricks AI Functions by name and covering concrete use cases including RAG pipeline construction. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill. The trigger terms are naturally what users would say when working with Databricks AI capabilities.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Databricks AI Functions, adding AI capabilities to SQL or PySpark queries, document parsing in Databricks, or building RAG pipelines on Databricks.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists 12 specific AI functions by name (ai_classify, ai_extract, ai_summarize, etc.) and describes concrete use cases like adding AI to SQL/PySpark pipelines, document parsing, and building custom RAG pipelines with a clear workflow (parse → chunk → index → query). | 3 / 3 |
Completeness | The 'what' is thoroughly covered with specific functions and use cases, but there is no explicit 'Use when...' clause or equivalent trigger guidance telling Claude when to select this skill. The 'when' is only implied by the capabilities listed, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes highly natural and specific trigger terms users would say: 'Databricks', 'AI Functions', each function name individually, 'SQL', 'PySpark', 'RAG pipelines', 'document parsing', 'model endpoints'. These cover a wide range of natural user queries related to this domain. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly distinctive by naming specific Databricks AI Functions and the exact pipeline context (SQL/PySpark). It would be very unlikely to conflict with other skills due to the specificity of the Databricks platform and the enumerated function names. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that efficiently covers a broad set of Databricks AI Functions with concrete, executable examples and excellent progressive disclosure. The function selection tables are particularly well-designed, providing clear decision rules. The main weakness is the lack of explicit validation checkpoints within multi-step workflows (e.g., the document ingestion pipeline could benefit from a verify step before writing results).
Suggestions
Add explicit validation/verification steps to multi-step patterns like Pattern 3 (Document Ingestion) — e.g., check row counts after filtering parse errors, sample and inspect results before writing to a table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. The overview table is a smart way to convey function selection without verbose prose. There's no unnecessary explanation of what SQL or PySpark are, and every section earns its place. The brief 'Overview' paragraph is borderline but provides genuinely useful context about how AI Functions differ from manual endpoint setup. | 3 / 3 |
Actionability | Every pattern includes fully executable SQL and/or PySpark code that is copy-paste ready. The Quick Start shows both SQL and PySpark equivalents with concrete column names and function calls. The ai_query example even includes from_json parsing with a complete schema definition. | 3 / 3 |
Workflow Clarity | The patterns are clearly sequenced (e.g., Pattern 3 shows read → parse → filter errors → enrich), and the function selection tables provide clear decision logic. However, there are no explicit validation checkpoints or error recovery feedback loops for batch operations — the Common Issues table addresses troubleshooting reactively but doesn't embed validation steps into the workflows themselves. | 2 / 3 |
Progressive Disclosure | The SKILL.md provides a well-structured overview with quick start and common patterns, then clearly signals four reference files covering task-specific functions, ai_query, ai_forecast, and document processing pipelines. References are one level deep and clearly labeled with descriptive summaries of what each file contains. | 3 / 3 |
Total | 11 / 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
93cb4e3
- 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.