# databricks-jobs

Teaches your coding agent to build and ship Lakeflow Jobs on Databricks: tasks, dependencies, triggers, alerts. Useful when a new data pipeline should be defined in code, not clicked together.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 943 installs · ★ 368
- Author: databricks
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/databricks/databricks-agent-skills/tree/HEAD/skills/databricks-jobs/SKILL.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/databricks-jobs

## What it does

The skill spells out how an agent should assemble a job: a DAG of tasks, launch conditions such as `ALL_SUCCESS` or `ALL_DONE`, and schedules driven by cron, a file landing, or a Unity Catalog table change. Reference material inside covers task kinds (notebook, Python, SQL, dbt, pipeline, JAR, run_job, for_each), monitoring settings, and worked ETL examples.

A new project gets scaffolded non-interactively with `databricks bundle init` and a config file, which also drops an `AGENTS.md` into the tree. You then declare the job in one of three ways: DABs in `resources/jobs.yml`, the Python SDK with `w.jobs.create`, or `databricks jobs create` from the CLI. Compute defaults to serverless, so leave cluster blocks alone unless you have a reason.

You need the `databricks CLI` at v1.0.0 or newer. Auth and profile choice live in the parent `databricks-core` skill. Serverless versus classic and the performance mode belong to `databricks-serverless`; this skill tells the agent to consult that one before any cluster setting lands in the config.

## Requirements
- Works with: Databricks

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add databricks/databricks-agent-skills --skill databricks-jobs -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/databricks-jobs/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/databricks-jobs/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add databricks/databricks-agent-skills --skill databricks-jobs -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/databricks-jobs/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add databricks/databricks-agent-skills --skill databricks-jobs -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/databricks-jobs/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install databricks/databricks-agent-skills databricks-jobs
```

2. **Manually: put the files in place**
- File: `.github/skills/databricks-jobs/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add databricks/databricks-agent-skills --skill databricks-jobs -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/databricks/databricks-agent-skills --path skills/databricks-jobs
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/databricks-jobs/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add databricks/databricks-agent-skills --skill databricks-jobs -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/databricks/databricks-agent-skills/tree/HEAD/skills/databricks-jobs/SKILL.md

## When to use it
- chain several notebook, SQL and Python tasks into one DAG
- scaffold a job project without interactive prompts
- start a job when a file arrives or a table changes
- add retries, timeouts and failure alerts
- move an existing job definition into a declarative bundle

## Example prompts
- Create a Lakeflow Job with extract and transform tasks, where the second depends on the first.
- Write the job definition into `resources/jobs.yml` and run it with `databricks bundle`.
- I need a job that fires whenever a new file shows up in the landing directory.

## Similar
- [xlsx](https://affpapa.org/en/nevibecode/skills/xlsx.md) — skill · 187223 installs
- [google-agents-cli-observability](https://affpapa.org/en/nevibecode/skills/google-agents-cli-observability.md) — skill · 511300 installs
- [caveman-evidence-review](https://affpapa.org/en/nevibecode/skills/caveman-evidence-review.md) — skill · 104500 installs
- [migration](https://affpapa.org/en/nevibecode/skills/migration.md) — skill · 103900 installs
- [performance-optimization](https://affpapa.org/en/nevibecode/skills/performance-optimization.md) — skill · 65200 installs
- [supabase](https://affpapa.org/en/nevibecode/skills/supabase.md) — skill · 8 installs

From the same set: [databricks/databricks-agent-skills](https://affpapa.org/en/nevibecode/by/databricks/databricks-agent-skills.md) — 12 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md