Name: author-recipes-and-cookbooks
Rating: 60.8 (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

70%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/author-recipes-and-cookbooks/SKILL.md

Quality

Content

55%

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

The skill is highly actionable with excellent workflow clarity — every step is concrete, sequenced, and validated. However, it suffers significantly from being a monolithic document that tries to cover everything inline (brand colors, image contracts, SQL dialect rules, directory structures, dry-run procedures) rather than splitting into focused reference files. The verbosity means Claude must process ~400+ lines of context even for simple recipe authoring tasks.

Suggestions

Extract the brand palette table, image contract details, and screenshot guidance into a separate `STYLE_GUIDE.md` or `IMAGE_CONTRACTS.md` and reference it from the main skill.

Move the detailed dry-run workflow and cleanup instructions into a separate `DRY_RUN.md` reference file, keeping only a brief summary and pointer in the main skill.

Extract the SQL dialect rules (Spark SQL vs Postgres differences) and the detailed `template/README.md` conventions into a separate `EXAMPLE_CONVENTIONS.md` file.

Remove explanatory context Claude already knows (e.g., why demos folder must be outside git repo because of .gitignore, what a README should contain) to reduce token usage by ~30%.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~400+ lines. It includes extensive detail about image contracts, color palette hex values, SQL dialect differences, and directory structure conventions that could be in separate reference files. Many sections explain things Claude can infer (e.g., what a README should contain, basic git/npm commands). The brand palette table alone is ~15 lines that belong in a referenced style guide.	1 / 3
Actionability	The skill provides highly concrete, executable guidance throughout: exact file paths, specific CLI commands, complete directory structures, code blocks for dry-run workflows, precise registration steps in named source files, and specific validation commands. Every step is copy-paste ready with real paths and real commands.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with numbered steps for each template kind (recipe, cookbook, example). The dry-run workflow includes explicit validation checkpoints, error recovery guidance ('Fixing issues found during dry run'), and a comprehensive 13-point validation checklist. The decision flow at the top clearly routes to the right workflow.	3 / 3
Progressive Disclosure	This is a monolithic wall of text with no content split into separate files despite being 400+ lines. The brand palette table, image contracts, SQL dialect rules, dry-run workflow, and detailed README conventions could all be in referenced files. The References section at the bottom points to code files but the skill itself doesn't offload any of its own content to supporting documents.	1 / 3
	Total	8 / 12 Passed

Description

85%

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

This is a strong description that clearly defines its domain (DevHub templates on Databricks), enumerates the three content types it handles, and provides explicit 'Use when' guidance. Its main weakness is that trigger terms could better cover natural user language variations beyond the specialized terminology used.

Suggestions

Add more natural trigger terms users might say, such as 'tutorial', 'guide', 'sample code', 'documentation', or 'demo app' to improve discoverability.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('author and maintain', 'creating, updating, or reorganizing') and specifies three distinct content types (atomic snippets, multi-step walkthroughs, deployable example apps) with a clear domain (DevHub templates at a specific URL).	3 / 3
Completeness	Clearly answers both 'what' (author and maintain DevHub templates across three entry kinds) and 'when' (explicit 'Use when creating, updating, or reorganizing any template-tier content'), satisfying the explicit trigger guidance requirement.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'templates', 'snippets', 'walkthroughs', 'example apps', and 'DevHub', but misses common user variations such as 'documentation', 'tutorial', 'guide', 'sample code', or 'developers.databricks.com'. The terminology is somewhat specialized and may not match how users naturally phrase requests.	2 / 3
Distinctiveness Conflict Risk	Highly distinctive with a specific platform (developers.databricks.com/templates), specific content taxonomy (atomic snippets, walkthroughs, deployable apps), and a clear niche that is unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: databricks/devhub
Commit: eef0be0

Reviewed: 3 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.