Author and maintain DevHub templates published at `dev.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.
85
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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 at dev.databricks.com), enumerates the three content types it covers, and includes an explicit 'Use when' clause. The main weakness is that trigger terms are somewhat specialized and may not fully capture the natural language variations a user might employ when requesting this skill.
Suggestions
Add more natural trigger term variations users might say, such as 'publish to DevHub', 'dev.databricks.com content', 'code sample', 'tutorial', or 'quickstart' 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' clause with trigger guidance). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'templates', 'DevHub', 'snippets', 'walkthroughs', 'example apps', but these are fairly domain-specific. Missing common natural user phrases like 'dev.databricks.com', 'template content', 'publish template', or variations users might actually say when requesting this work. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped to a specific platform (dev.databricks.com/templates), specific content types, and a specific publishing workflow. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a thorough, highly actionable skill that provides excellent concrete guidance for authoring DevHub templates across all three internal kinds. Its greatest strength is workflow clarity — the decision flow, step-by-step authoring instructions, dry-run workflow with error recovery, and comprehensive validation checklist are exemplary. Its main weakness is length: the document tries to be both a quick reference and a comprehensive guide, resulting in a monolithic file that would benefit from splitting detailed subsections (image contracts, brand palette, solution authoring) into referenced companion files.
Suggestions
Extract the brand palette table, screenshot guidance, and image contract details into a separate referenced file (e.g., IMAGES.md) to reduce the main skill's token footprint.
Consider moving the 'Author A Solution' section into its own skill or companion file, as it covers a distinct content type with different rules and adds ~40 lines to an already long document.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive and mostly efficient for its scope, but it includes some sections that could be tightened — the brand palette table with hex values, the extensive screenshot guidance, and the solution authoring section add significant length. Some explanations of why certain conventions exist (e.g., why demos folder must be outside the repo) are valuable, but the overall document is quite long and could benefit from splitting more content into referenced files. | 2 / 3 |
Actionability | The skill provides highly concrete, executable guidance throughout: exact file paths, directory structures, bash commands for dry-run workflows, specific code patterns for cookbook TSX pages, precise placeholder conventions (REPLACE_ME), SQL dialect differences, and registry field names. The decision flow, authoring steps, and validation checklist are all immediately actionable. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with numbered steps for each content 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 at the end. The decision flow at the top clearly guides which kind to author. | 3 / 3 |
Progressive Disclosure | The skill references external files well (recipes.ts, existing examples, plugins) and the References section provides clear pointers. However, the document itself is monolithic — the brand palette table, screenshot guidance, solution authoring, and detailed example conventions could be split into separate referenced files. At ~400+ lines, the inline content is heavy for a single SKILL.md, especially sections like image contracts and SQL dialect rules. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%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.
6338825
Table of Contents
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.