databricks-docs

Databricks documentation reference via llms.txt index. Use when other skills do not cover a topic, looking up unfamiliar Databricks features, or needing authoritative docs on APIs, configurations, or platform capabilities.

Quality

87%

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

85%

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

A clean, well-structured reference skill with a concrete URL, actionable named tools, and a clear fetch-and-apply workflow. Its single weak spot is conciseness, driven by the 'Role of This Skill' section restating points already made in the introduction.

Suggestions

Collapse the 'Role of This Skill' section into the intro: keep one statement of 'reference not action, prefer MCP tools for actions and specific skills for workflows' rather than restating it twice.

Trim the four 'Use it to' bullets, which largely restate the description's triggers, to remove redundant tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, but the 'Role of This Skill' section restates the intro's 'reference not action' framing and re-explains 'prefer MCP tools for actions / load specific skills for workflows', which is redundant. Not a 3 because of this repetition; not a 1 because it avoids explaining concepts Claude already knows and is not padded with background.	2 / 3
Actionability	It gives a concrete, copy-paste URL ('https://docs.databricks.com/llms.txt'), a named retrieval step (WebFetch), and specific named MCP tools in examples (e.g., manage_pipeline(action="create_or_update")). For a reference skill the guidance is concrete and executable, matching the top anchor rather than the pseudocode/vague lower anchors.	3 / 3
Workflow Clarity	The 'How to Use' section lays out a clear fetch → search → fetch specific pages → apply-with-MCP-tools sequence, and the scenario examples reinforce it. This is a read-only reference skill with no destructive or batch operations, so the feedback-loop cap does not apply and the clear sequence earns the top anchor.	3 / 3
Progressive Disclosure	No bundle files are present (references/, scripts/, assets/ absent), so the skill is a single well-organized file with clearly labeled sections (Role, How to Use, Documentation Structure, Examples, Related Skills) and one-level external links. Per the simple-skill scoring note, well-organized sections with no nested references earn the top anchor.	3 / 3
	Total	11 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description with explicit what-and-when structure, good natural trigger terms, and a distinctive fallback positioning. Its only weakness is specificity, since the described capability is a single reference mechanism rather than a suite of concrete actions.

Suggestions

Consider naming one or two more concrete lookup outcomes (e.g., 'find API parameters, configuration options, or Terraform resource specs') to lift specificity from a single mechanism toward multiple concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('Databricks documentation reference via llms.txt index') and look-up actions ('looking up unfamiliar Databricks features'), but stops short of a comprehensive list of concrete actions — it is a single reference mechanism rather than multiple distinct operations. Not a 3 because it lacks the 'multiple specific concrete actions' breadth of the top anchor; not a 1 because it is far from vague.	2 / 3
Completeness	It states what the skill does ('Databricks documentation reference via llms.txt index') and gives an explicit 'Use when...' trigger clause covering multiple scenarios. Both what and when are explicit, matching the top anchor; it is not a 2 because the trigger is present and direct, not merely implied.	3 / 3
Trigger Term Quality	Natural user-facing terms are well covered: 'Databricks', 'documentation', 'APIs', 'configurations', 'platform capabilities', and the natural phrase 'looking up unfamiliar Databricks features'. A user needing docs would plausibly say these; it is not reduced to jargon, so it clears the top anchor rather than settling at 2.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche ('Databricks documentation reference') and is explicitly positioned as a fallback ('Use when other skills do not cover a topic'), which actively reduces conflict with the other Databricks skills. Unlikely to trigger for the wrong skill, matching the top anchor.	3 / 3
	Total	11 / 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: 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: databricks-solutions/ai-dev-kit
Path: databricks-skills/databricks-docs/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.