databricks-unstructured-pdf-generation: Claude Code skill
databricks-unstructured-pdf-generation creates synthetic PDF files and paired evaluation questions locally, then copies them to Databricks Unity Catalog volumes for RAG testing.
no license 328 installs ★ 408 updated 2026-10-24
npx skills add databricks/databricks-agent-skills --skill databricks-unstructured-pdf-generation -a claude-codeWhat databricks-unstructured-pdf-generation does
This skill builds synthetic document collections for testing Databricks retrieval pipelines, such as Genie Agent setups or mlflow.genai.evaluate(). It writes domain-specific HTML pages into ./raw_data/html/ and converts them to PDF files using a bundled pdf_generator.py script that calls plutoprint.
Converted documents are copied into a Unity Catalog volume using databricks fs cp. The workflow also produces pdf_eval_questions.json, mapping each document to verification queries and expected facts.
Without databricks CLI version 1.0.0 or higher and the plutoprint library, conversions and volume sync will fail. Keep the evaluation JSON off the volume attached to a Genie Agent, because the agent indexes the entire volume and absorbs the test answers directly into its context.
What it helps with
- produce synthetic multi-page PDFs from local HTML source files
- sync test PDF batches to Databricks Unity Catalog volumes
- build paired ground-truth question sets for RAG benchmarks
- prepare evaluation data for Genie Agent without leaking answers into its index
Example prompts for the agent
- Generate HTML troubleshooting guides in
./raw_data/htmland convert them to PDF - Copy local PDFs from
./raw_data/pdfto volumedbfs:/Volumes/my_catalog/my_schema/raw_data/pdf - Create
pdf_eval_questions.jsonpaired with the generated manual PDFs
How to install databricks-unstructured-pdf-generation
1Skills CLI (Vercel)
npx skills add databricks/databricks-agent-skills --skill databricks-unstructured-pdf-generation -a claude-code2Manually: put the files in place
~/.claude/skills/databricks-unstructured-pdf-generation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/databricks-unstructured-pdf-generation/
1Skills CLI (Vercel)
npx skills add databricks/databricks-agent-skills --skill databricks-unstructured-pdf-generation -a codex2Manually: put the files in place
.agents/skills/databricks-unstructured-pdf-generation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add databricks/databricks-agent-skills --skill databricks-unstructured-pdf-generation -a cursor2Manually: put the files in place
.cursor/skills/databricks-unstructured-pdf-generation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install databricks/databricks-agent-skills skills/databricks-unstructured-pdf-generation2Manually: put the files in place
.github/skills/databricks-unstructured-pdf-generation/SKILL.md1Skills CLI (Vercel)
npx skills add databricks/databricks-agent-skills --skill databricks-unstructured-pdf-generation -a gemini-cli2Platform CLI
gemini skills install https://github.com/databricks/databricks-agent-skills --path skills/databricks-unstructured-pdf-generationManually: put the files in place
.devin/skills/databricks-unstructured-pdf-generation/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add databricks/databricks-agent-skills --skill databricks-unstructured-pdf-generation -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about databricks-unstructured-pdf-generation
How do I install databricks-unstructured-pdf-generation in Claude Code?
Run npx skills add databricks/databricks-agent-skills --skill databricks-unstructured-pdf-generation -a claude-code.
What does databricks-unstructured-pdf-generation do?
It creates synthetic PDFs from HTML files and generates question-fact pairs to test unstructured RAG retrieval on Databricks.
What tools are required before running the script?
You need databricks CLI version 1.0.0 or later and the Python package plutoprint, installed with uv pip install plutoprint.