Skill: Kafka Streams Programming
by Confluent
Confluent's official skill for architecting, building and debugging Kafka Streams applications — topology design, join and window selection, and production failure triage.
Databricks' official entry-point agent skill: CLI authentication, profile and workspace selection, asset bundles, and routing to the right product skill for the task.
databricks-core is the front door to Databricks' officially published agent skill collection — 29 stable skills covering everything from Lakeflow Jobs and Spark Declarative Pipelines to Unity Catalog, Vector Search, Model Serving and AI/BI dashboards.
Its job is deliberately narrow: get the agent authenticated and pointed at the right workspace, then hand off. That means Databricks CLI basics, profile management and workspace targeting, plus Databricks Asset Bundle (DAB) workflows for declaratively deploying jobs, pipelines and other resources. It requires the Databricks CLI at v0.292.0 or newer and checks with databricks --version before doing anything.
The routing behaviour is what makes it worth installing first rather than cherry-picking a product skill. For data discovery — finding tables, answering natural-language questions about a dataset, or generating SQL — it defers to databricks-data-discovery, which asks Genie One first and only then falls back to manual schema exploration. For product work it names the specific skill: databricks-jobs, databricks-pipelines, databricks-apps, databricks-lakebase, databricks-model-serving and the rest. If a downstream skill is not installed, it degrades to CLI commands and a bundled manual data-exploration guide rather than guessing.
Installation. The canonical path is the Databricks CLI itself: databricks aitools install. It is also published to the Claude Code marketplace (/plugin marketplace add databricks/databricks-agent-skills), Cursor (/add-plugin databricks), and the GitHub Copilot and Codex marketplaces. Experimental skills live in experimental/ behind an --experimental flag. Distributed under the Databricks License rather than a standard OSS licence — read it before redistributing.
Best for data and platform engineers who already work in a Databricks workspace and want their agent to stop hallucinating CLI flags. It is not a general Spark or SQL tutor; it assumes a Databricks account exists.
Once installed, ask your agent something like:
Authenticate to my Databricks workspace with the prod profile and deploy this asset bundle.
The instructions your agent loads, as published by Databricks.
by Confluent
Confluent's official skill for architecting, building and debugging Kafka Streams applications — topology design, join and window selection, and production failure triage.
Firecrawl's skill for reading known web pages with its CLI: scrape a URL to markdown, links or schema-typed JSON, batch-scrape URL lists, cap PDF pages, and discover and run data-provider tools for structured results.
Firecrawl's official routing skill for its CLI: lets an agent search the web, scrape and map sites, crawl sections, monitor pages for changes and interact with pages behind clicks or logins, saving clean markdown to .firecrawl/.
by PlanetScale
How to drive the PlanetScale CLI non-interactively: --format json everywhere, auth check before anything else, pscale sql instead of pscale shell, correct flag placement.