Name: author-recipes-and-cookbooks
Rating: 67.2 (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

82%

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 1-5

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 with strong validation and feedback loops, but it is dense and inlines several topics that would read better as one-level-deep reference files. The unused quality-checklist.md bundle is the clearest progressive-disclosure gap.

Suggestions

Link references/quality-checklist.md from the body (e.g. in a 'Before finishing' callout) so the provided bundle file is actually surfaced, and reconcile its divergent guidance (app-templates flat layout, npm run verify:images) with the body.

Extract the solutions authoring section and the image/brand-palette contract into separate reference files referenced one level deep from the body, reducing the main SKILL.md length.

Tighten editorial prose (e.g. the 'inspirational gallery, not a step-by-step manual guide' line) and de-duplicate the Public Vocabulary vs Internal Implementation Tiers framing.

Dimension	Reasoning	Score
Conciseness	The ~350-line body is mostly domain-specific guidance that earns its place (registry contracts, SQL dialect rules, dry-run script), but editorial padding like 'an inspirational gallery of what's possible, not a step-by-step manual guide' and repetition between 'Public Vocabulary' and 'Internal Implementation Tiers' could be trimmed. It is not a 4 because several sections over-explain rationale that an agent could infer.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance throughout: concrete file paths, a full example directory tree, registry mutation steps, and a runnable dry-run bash block covering the common deploy case.	5 / 5
Workflow Clarity	Each authoring path (recipe, cookbook, example) is numbered end-to-end with explicit validation checkpoints ('Validate Before Finishing' 13-point list, 'pnpm fmt && typecheck && build && test') and a feedback loop for dry-run failures (fix in repo, re-copy, retry).	5 / 5
Progressive Disclosure	Section headings and a dedicated References block give real structure, but large chunks that belong in separate files (the solutions authoring guide, image contracts, brand palette table, full dry-run workflow) are inlined, and the one provided bundle file references/quality-checklist.md is never linked from the body. It is not a 4 because of the orphaned bundle reference and the heavy inlining.	3 / 5
	Total	16 / 20 Passed

Description

87%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.

A strong, third-person description that concretely states what it does and when to use it with explicit trigger phrases. Minor room to add a few more natural synonyms, but it cleanly clears the top anchors on completeness and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('DevHub templates') and several concrete actions — 'Author and maintain', 'creating, updating, or reorganizing' — with only minor coverage gaps. It is not a 5 because the action set, while specific, is not exhaustive across the three internal entry kinds.	4 / 5
Completeness	Explicitly answers both 'what' ('Author and maintain DevHub templates... three internal entry kinds') and 'when' ('Use when creating, updating, or reorganizing any template-tier content') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('creating, updating, or reorganizing', 'template-tier content') with good keyword coverage. It stops short of 5 because synonyms and the user-facing term variations (e.g. 'snippet', 'walkthrough', 'example app') are not surfaced as triggers.	4 / 5
Distinctiveness Conflict Risk	The 'developers.databricks.com/templates' niche and the three-kind scoping make it clearly distinct with minimal conflict risk against other skills.	5 / 5
	Total	18 / 20 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: f83a74d

Reviewed: 4 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.