Name: author-recipes-and-cookbooks
Rating: 71.2 (1 reviews)
Author: databricks

author-recipes-and-cookbooks

Author and maintain DevHub templates published at `developers.databricks.com/templates`. A template is the public name for any of three internal entry kinds — atomic snippets, multi-step end-to-end walkthroughs, and full deployable example apps. Use when creating, updating, or reorganizing any template-tier content.

Quality

88%

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

77%Weight 40%Scale 1-3

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

The body is a dense, highly actionable, and well-sequenced authoring guide with strong validation feedback loops. Its weaknesses are redundancy across sections and under-use of the bundled reference, which both inflate length and leave the quality-checklist.md bundle unsignaled.

Suggestions

Deduplicate repeated rules: state the 'use template, never recipe/cookbook/guide' and 'prerequisites belong in prerequisites.md' rules once and reference them, instead of restating them across Public Vocabulary, Internal Tiers, Writing Style, and Validate Before Finishing.

Surface the bundle: link references/quality-checklist.md from the 'Validate Before Finishing' section rather than duplicating its checklist inline, so the skill body points to one level of detail instead of repeating it.

Move heavy inline reference material — the image contract and the brand color-palette hex table — into a separate bundled reference file (e.g. references/images-and-branding.md) to shrink the main SKILL.md to an overview.

Dimension	Reasoning	Score
Conciseness	Most content is project-specific and earns its place, but there is real redundancy: the 'use template not recipe/cookbook/guide' rule is restated four times and prerequisite rules three times, and the inline 'Validate Before Finishing' checklist overlaps the bundled quality-checklist. It is mostly efficient but could be tightened, so it sits at 2 rather than the lean 3.	2 / 3
Actionability	Highly actionable with concrete file paths, runnable commands (pnpm fmt && pnpm typecheck && pnpm build && pnpm test, databricks bundle deploy, databricks apps init --template), exact SQL dialect rules (CURRENT_DATE() not NOW()), registry field lists, and precise image contracts — copy-paste ready.	3 / 3
Workflow Clarity	Multi-step authoring flows are numbered and sequenced, with explicit validation checkpoints (Verify The DevHub Build, Validate Before Finishing) and a genuine dry-run feedback loop that categorizes issues by where to fix them and retries — matching the 'clear sequence with explicit validation steps and feedback loops' anchor.	3 / 3
Progressive Disclosure	Headings and the decision flow give decent in-file navigation, but the one bundle file (references/quality-checklist.md) is never linked from the body and its checklist is duplicated inline, while heavy reference material (image contracts plus the brand color-palette table) that could live in a separate file is inline — fitting 'some structure but content that should be separate is inline' rather than the cleanly split 3.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, complete, and distinctive: it lists concrete authoring/maintenance actions across three named content kinds and provides an explicit 'Use when' trigger. Voice is third person, so no specificity penalty applies.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Author and maintain', 'creating, updating, or reorganizing' — and enumerates three concrete entry kinds (atomic snippets, multi-step walkthroughs, full deployable example apps), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly states what the skill does ('Author and maintain DevHub templates') and when to use it via an explicit 'Use when creating, updating, or reorganizing any template-tier content' clause, answering both what and when.	3 / 3
Trigger Term Quality	Natural phrasing a user would actually say ('create a template', 'update', 'reorganize') plus the domain noun 'DevHub templates' gives good coverage of likely trigger terms.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche (DevHub templates at developers.databricks.com/templates) with distinct triggers, making conflict with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: databricks/devhub
Path: .agents/skills/author-recipes-and-cookbooks/SKILL.md
Commit: 01580f8

Reviewed: about 18 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.