Name: author-recipes-and-cookbooks
Rating: 63.2 (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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

A highly actionable, well-sequenced skill body with strong validation checkpoints and concrete commands. Its weaknesses are repetition of the three-kind taxonomy and monolithic inline content plus an unreferenced bundle file, which hold back conciseness and progressive disclosure.

Suggestions

Collapse the repeated three-kind taxonomy into a single canonical definition plus the table; remove the 'So: recipes are the atoms...' restatement and avoid re-listing the kinds in the URL Structure section.

Move the detailed image contract and brand-color token table into a referenced file (e.g. references/images-and-branding.md) and link to it from the body to reduce inline bulk.

Reference the existing references/quality-checklist.md from the body (e.g. in 'Validate Before Finishing') so the bundle file is discoverable rather than orphaned.

Dimension	Reasoning	Score
Conciseness	Most content is genuinely novel DevHub-specific knowledge (file layouts, SQL dialect gotchas, brand tokens), but the three-kind taxonomy is restated five times ('The Three Internal Kinds', the implementation table, the 'So:' summary, the Decision Flow, the URL table) and could be tightened.	2 / 3
Actionability	Guidance is concrete and copy-paste ready: exact paths ('content/recipes/<slug>/goal.md'), exact registry fields, a numbered bash dry-run block, and specific dialect rules ('CURRENT_DATE() not NOW()').	3 / 3
Workflow Clarity	Multi-step authoring workflows are clearly numbered with explicit validation ('npm run fmt && typecheck && build && test'), a fix-and-retry feedback loop for dry runs, and a 13-point 'Validate Before Finishing' checklist for batch/destructive operations.	3 / 3
Progressive Disclosure	Sections are well organized and there is a one-level-deep References list, but the ~350-line body is monolithic with detailed inline content (image contract, brand-color table, dry-run) that could be split out, and the bundle file references/quality-checklist.md is never signaled from the body.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 strong, well-targeted description that clearly states what the skill does and when to use it, with an explicit 'Use when' trigger and a distinctive niche. Its main weakness is that the listed actions are fairly generic content-lifecycle verbs rather than concrete, granular operations.

Dimension	Reasoning	Score
Specificity	Names the domain ('DevHub templates') and several lifecycle actions ('creating, updating, or reorganizing'), but these are generic editing verbs rather than the granular, distinct operations (e.g. 'fill forms, merge documents') the top anchor calls for.	2 / 3
Completeness	It explicitly answers both 'what' ('Author and maintain DevHub templates ... three internal entry kinds') and 'when' with an explicit trigger clause ('Use when creating, updating, or reorganizing any template-tier content').	3 / 3
Trigger Term Quality	Relevant natural terms are present ('DevHub templates', 'developers.databricks.com/templates', 'creating', 'updating', 'reorganizing'), but the vocabulary is narrow and niche, missing common variations a user might say.	2 / 3
Distinctiveness Conflict Risk	The niche is highly specific to DevHub templates at a named URL, with distinctive triggers unlikely to collide with other skills.	3 / 3
	Total	10 / 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
Commit: 131db95

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.