databricks-unstructured-pdf-generation
Generate PDF documents from HTML and upload to Unity Catalog volumes. Use for creating test PDFs, demo documents, reports, or evaluation datasets.
64
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./databricks-skills/databricks-unstructured-pdf-generation/SKILL.mdQuality
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 well-crafted description that clearly states what the skill does and when to use it, with a distinctive niche combining PDF generation from HTML with Unity Catalog integration. The main weakness is that trigger term coverage could be broader—users might phrase requests using terms like 'convert HTML to PDF', 'Databricks', or 'document generation' that aren't captured.
Suggestions
Add more natural trigger term variations such as 'convert HTML to PDF', '.pdf files', 'Databricks volumes', or 'document generation' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generate PDF documents from HTML' and 'upload to Unity Catalog volumes', plus enumerates use cases like 'test PDFs, demo documents, reports, evaluation datasets'. | 3 / 3 |
Completeness | Clearly answers both what ('Generate PDF documents from HTML and upload to Unity Catalog volumes') and when ('Use for creating test PDFs, demo documents, reports, or evaluation datasets') with an explicit 'Use for' trigger clause. | 3 / 3 |
Trigger Term Quality | Includes some natural keywords like 'PDF', 'HTML', 'reports', 'Unity Catalog volumes', but misses common variations users might say such as 'convert HTML to PDF', '.pdf', 'document generation', or 'Databricks volumes'. The term 'evaluation datasets' is somewhat niche. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of HTML-to-PDF generation AND Unity Catalog volumes upload is a very specific niche that is unlikely to conflict with generic PDF or document skills. The Unity Catalog reference makes it clearly distinct. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%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 complete, executable examples and a clear tool signature, making it easy for Claude to use immediately. However, it suffers from verbosity through repetitive HTML pattern examples that add marginal value over the first example, and the workflow section lacks explicit validation/error-handling checkpoints for batch operations. The content would benefit from consolidation of similar patterns and addition of error-handling feedback loops.
Suggestions
Consolidate the three common patterns into a brief table of use cases with one full example and short diffs for variations, reducing token usage significantly.
Add explicit validation steps to the multi-document workflow: check each tool call's 'success' field, log errors, and retry failed uploads before reporting results.
Move the professional document template and common patterns into a separate TEMPLATES.md file, keeping SKILL.md focused on the tool signature, quick start, and workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes excessive repetition—three full common pattern examples (technical docs, business reports, HR policies) that are largely variations of the same HTML template with different CSS. The parallel execution section also repeats 5 nearly identical tool calls. The professional document template is quite long and could be trimmed. | 2 / 3 |
Actionability | The skill provides fully concrete, copy-paste-ready tool calls with complete HTML content, clear parameter signatures, return value schemas, and specific examples for multiple use cases. Every instruction is directly executable. | 3 / 3 |
Workflow Clarity | The 'Workflow for Multiple Documents' section lists steps but lacks explicit validation checkpoints—there's no guidance on checking the returned success/error fields, no feedback loop for handling failures, and no retry logic. The troubleshooting table partially compensates but doesn't constitute an integrated validation step. | 2 / 3 |
Progressive Disclosure | The content is a single monolithic file with no references to external files. The common patterns section (3 full HTML examples) and the professional template could be split into a separate reference file. However, the section headers provide reasonable navigation within the single file. | 2 / 3 |
Total | 9 / 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.
- Repository
- databricks-solutions/ai-dev-kit
- Commit
93cb4e3
- Reviewed
Table of Contents
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.