Name: databricks-ai-functions
Rating: 64.8 (1 reviews)
Author: databricks

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).

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.databricks/aitools/skills/databricks-ai-functions/SKILL.md

Quality

Content

80%Weight 40%Scale 1-5

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

The content is well-structured and highly actionable with executable examples and clean progressive disclosure. The main gap is the lack of an explicit validation/retry workflow for batch operations.

Suggestions

Add an explicit batch validation workflow (e.g., filter NULL inputs → run with failOnError => false → check error_status/errorMessage → retry failed rows) as a sequenced checklist to lift workflow clarity above the batch cap.

Tighten the Overview intro and remove minor redundant commentary to push conciseness toward a 5.

Dimension	Reasoning	Score
Conciseness	The body is efficient and table-driven with executable examples and assumes Claude's competence, but a few introductory phrases and minor commentary could still be trimmed.	4 / 5
Actionability	Copy-paste-ready SQL and PySpark examples cover the common cases (classify, extract, sentiment, mask, document parsing, similarity, ai_query, forecast) with concrete VARIANT-navigation details.	5 / 5
Workflow Clarity	Patterns are sequenced with a selection-decision table and scattered validation signals (parse_error IS NULL, failOnError => false), but this batch-inference skill lacks an explicit validate→fix→retry feedback loop, so workflow clarity is capped at 3.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references (4 verified reference files) and a dedicated Reference Files section; bulk syntax is appropriately split into the references.	5 / 5
	Total	17 / 20 Passed

Description

75%Weight 40%Scale 1-5

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 highly specific and distinctive, naming every AI function and the RAG sub-stages. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit 'Use when...' sentence (e.g., 'Use when adding AI capabilities to Databricks SQL or PySpark pipelines, doing document parsing, or building a RAG pipeline without managing model endpoints.') to satisfy the completeness 'when' requirement.

Include a few more user-facing synonyms (e.g., 'LLM inference in SQL', 'batch text classification', 'PII redaction') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists all 12 named AI functions plus concrete actions (classify, extract, summarize, mask, parse) and an explicit RAG pipeline (parse → chunk → index → query), giving comprehensive coverage of capabilities.	5 / 5
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' trigger clause; per the judging guidelines, a missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	Natural keywords like 'AI Functions', 'SQL and PySpark pipelines', 'document parsing', and 'RAG pipelines' are present, but a few common variations and synonyms users might say are missing.	4 / 5
Distinctiveness Conflict Risk	The Databricks-specific function names and SQL/PySpark/RAG niche give it a clear, distinct trigger surface with minimal overlap risk against other skills.	5 / 5
	Total	17 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: databricks/devhub
Path: .databricks/aitools/skills/databricks-ai-functions/SKILL.md
Commit: ade58e4

Reviewed: 5 days 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.