databricks-unstructured-pdf-generation

Convert HTML5 documents into PDFs and upload them to Unity Catalog volumes.

Updated Mar 19, 2026
One-click install
npx skills add https://github.com/Blackkadder/databricks-apps-and-agents-workshop --skill databricks-unstructured-pdf-generation-blackkadder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-unstructured-pdf-generation
Source: https://github.com/Blackkadder/databricks-apps-and-agents-workshop/tree/main/.claude/skills/databricks-unstructured-pdf-generation
Command: npx skills add https://github.com/Blackkadder/databricks-apps-and-agents-workshop --skill databricks-unstructured-pdf-generation-blackkadder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convert HTML content into polished PDF documents and store them directly in Unity Catalog volumes so teams can automate report, documentation, and dataset generation without manual file handling.

Core Features & Use Cases

  • Convert complete HTML5 documents (including CSS styles) into static PDFs suitable for reports, policy documents, and technical documentation.
  • Upload generated PDFs to a specified Unity Catalog catalog, schema, and volume, with optional folder organization for programmatic storage.
  • Support for parallel generation of multiple PDFs to improve throughput for batch or bulk document creation in Databricks MCP or app workflows.

Quick Start

Ask the assistant to generate a complete HTML document for a quarterly report and call the generate_and_upload_pdf tool with filename, catalog, and schema to store it in Unity Catalog.

Frequently Asked Questions about databricks-unstructured-pdf-generation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert HTML to PDF and store it in a Databricks Unity Catalog volume?

You can automate PDF generation in Databricks by passing complete HTML5 documents, including CSS styles, to a tool endpoint that converts them to static PDFs and uploads them programmatically to Unity Catalog volumes.

Can I generate multiple PDFs in parallel within Databricks MCP workflows?

Yes, this Skill supports parallel generation of multiple PDFs to improve throughput for batch or bulk document creation within Databricks MCP or app workflows.

Do I need an existing Unity Catalog schema and volume before generating PDFs?

Yes, generating and uploading PDFs requires an existing Unity Catalog schema and a writable volume, along with a complete HTML5 document per PDF you intend to create.

Does the HTML to PDF conversion support CSS styles for automated reports?

Yes, the conversion process accepts complete HTML5 documents including CSS styles, allowing you to generate polished static PDFs suitable for reports, policy documents, and technical documentation.

What parameters are required to upload a generated PDF to a Unity Catalog volume?

The tool endpoint requires html_content, filename, catalog, and schema parameters to upload a PDF, while volume and folder parameters are optional for organizing files within Unity Catalog.