databricks skillA
databricks is agent-read markdown (skill) from jnpiyush/agentx: Build data engineering, analytics, and ML/AI solutions on the Databricks Lakehouse Platform. Use when creating Delta Lake tables, writing PySpark notebooks, building DLT pipelines, managing Unity Catalog, orchestrating Databricks Workflows, tracking experiments with MLflow, or deploying using Databricks Asset Bundles..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Databricks > Unified Lakehouse platform combining Apache Spark, Delta Lake, MLflow, and Unity Catalog for data engineering, analytics, and AI/ML at scale. ## When to Use - Building Delta Lakehouses with medallion architecture (Bronze -> Silver -> Gold) - Ingesting streaming or batch data with Auto Loader or Structured Streaming - Creating DLT (Delta Live Tables) pipelines with built-in data quality - Running ML experiments tracked in MLflow and serving models via Model Serving - Governing data assets across clouds with Unity Catalog - Deploying reproducible jobs and pipelines with Databricks Asset Bundles - Running SQL analytics on Delta tables via Databricks SQL Warehouses - Building AI/ML features with Vector Search and Feature Engineering ## Decision Tree ``` Working with Databricks? +-- Need storage layer? | +-- Semi-structured / schema-on-read / ML data -> Delta Lakehouse | +-- Need ACID + time travel -> Delta Lake tables | +-- Need governance across workspace -> Unity Catalog +-- Need ingestion? | +-- Cloud files (S3/ADLS/GCS) incremental -> Auto Loader …
Read the whole file at its exact version.
How to install
mdr add jnpiyush/agentx/databricks@v1.0.0mdr add jnpiyush/agentx/databricks@sha256:f813fd17159bed53Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_lvqxfa7o54rllaz5)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-09-15 | f17c505 | 15,045 B | A | view · diff |
| v1.0.0 | 2026-03-01 | 969f335 | 15,043 B | A | view · diff |
| v1.0.0 | 2026-02-28 | 75e5d34 | 21,944 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (15045 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jnpiyush/agentx · 16 stars · license Apache-2.0 · pushed 2026-09-21 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_lvqxfa7o54rllaz5 GET https://markdownregistry.com/api/v1/resolve?ref=jnpiyush/agentx/databricks GET https://markdownregistry.com/api/v1/blob/f813fd17159bed53fe6391af4b591cef72b6832ff725b931b33696491e0fcfe2
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.