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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

Highly actionable with complete, executable examples and a clear tool signature, but verbose due to repeated full HTML templates and redundant parallel-call blocks. The batch workflow lacks validation checkpoints and no reference files are used to offload the long template/pattern material.

Suggestions

Collapse the 5-call parallel example to 2-3 calls plus an explanatory note; the repetition is pure token cost.

Add an explicit verification step to the multi-document workflow (e.g. check each response's `success` field and report which uploads failed before declaring done).

Move the full professional template and the per-pattern HTML examples into a referenced file (e.g. references/templates.md) so SKILL.md stays a lean overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	Content avoids explaining concepts Claude already knows, but is token-heavy: the 5 near-identical parallel tool calls and multiple full HTML5 document templates are repetitive and could be tightened, matching 'mostly efficient but could be tightened'.	2 / 3
Actionability	The full tool signature, parameter table, return JSON, and several complete copy-paste-ready HTML tool-call examples provide fully executable, specific guidance.	3 / 3
Workflow Clarity	The 'Workflow for Multiple Documents' lists sequenced steps, but the batch parallel-upload operation lacks any explicit validation/verification checkpoint (e.g. confirming each success response), which caps batch-operation workflow clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	No references/scripts/assets bundle exists; all content (CSS feature lists, full templates, patterns) is inline in a ~330-line monolithic SKILL.md that could be split into reference files, matching 'some structure but content that should be separate is inline'.	2 / 3
	Total	9 / 12 Passed

Description

92%

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 concise, third-person description that clearly states the capability and provides an explicit 'Use for' trigger clause. Its only weakness is mild overlap risk from the generic use-case terms (reports, demo documents) alongside its otherwise distinctive HTML-to-PDF/Unity Catalog niche.

Suggestions

Tie the trigger clause more tightly to the distinctive capability, e.g. 'Use when generating PDFs from HTML for upload to Unity Catalog volumes (test fixtures, demo docs, evaluation datasets)'.

Drop or qualify the generic term 'reports' unless it is a primary intended use, to reduce overlap with general document/report skills.

Dimension	Reasoning	Score
Specificity	"Generate PDF documents from HTML and upload to Unity Catalog volumes" lists multiple concrete actions (HTML-to-PDF conversion, upload to UC volumes) rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It answers both 'what' (generate PDFs from HTML, upload to UC volumes) and 'when' via the explicit "Use for creating test PDFs, demo documents, reports, or evaluation datasets" trigger clause.	3 / 3
Trigger Term Quality	Natural user-facing terms appear ("PDF documents", "test PDFs", "demo documents", "reports", "evaluation datasets", "HTML"), giving good coverage of phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The core capability (HTML-to-PDF + Unity Catalog upload) is a clear niche, but the secondary triggers "reports" and "demo documents" are generic and could overlap with general document-creation skills, so it does not fully reach the 'unlikely to conflict' anchor.	2 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: databricks-solutions/ai-dev-kit
Commit: 1c43c21

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.