Cookbook Compute
databricks-solutions/databricks-apps-cookbook
Connect Databricks Apps to shared clusters or serverless compute using Databricks Connect.
Serverless compute for Databricks jobs, Lakeflow pipelines and Declarative Automation Bundles (DABs), with STANDARD or PERFORMANCEOPTIMIZED and classic only where serverless cannot run the workload.
Install Databricks Serverless
$ npx skills add databricks/databricks-agent-skills --skill databricks-serverless -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install databricks/databricks-agent-skills databricks-serverless --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/databricks/databricks-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/databricks-serverless .claude/skills/databricks-serverless && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "databricks-serverless" agent skill from https://github.com/databricks/databricks-agent-skills/tree/main/skills/databricks-serverless into .claude/skills/databricks-serverless/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "databricks-serverless", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/databricks/databricks-agent-skills/tree/main/skills/databricks-serverlessType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add databricks/databricks-agent-skills --skill databricks-serverless -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install databricks/databricks-agent-skills databricks-serverless --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/databricks/databricks-agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/databricks-serverless .agents/skills/databricks-serverless && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "databricks-serverless" agent skill from https://github.com/databricks/databricks-agent-skills/tree/main/skills/databricks-serverless into .agents/skills/databricks-serverless/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "databricks-serverless", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add databricks/databricks-agent-skills --skill databricks-serverless -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install databricks/databricks-agent-skills databricks-serverless --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/databricks/databricks-agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/databricks-serverless .cursor/skills/databricks-serverless && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "databricks-serverless" agent skill from https://github.com/databricks/databricks-agent-skills/tree/main/skills/databricks-serverless into .cursor/skills/databricks-serverless/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "databricks-serverless", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/databricks/databricks-agent-skills.git --path skills/databricks-serverless--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add databricks/databricks-agent-skills --skill databricks-serverless -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install databricks/databricks-agent-skills databricks-serverless --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/databricks/databricks-agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/databricks-serverless .gemini/skills/databricks-serverless && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "databricks-serverless" agent skill from https://github.com/databricks/databricks-agent-skills/tree/main/skills/databricks-serverless into .gemini/skills/databricks-serverless/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "databricks-serverless", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install databricks/databricks-agent-skills databricks-serverlessInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add databricks/databricks-agent-skills --skill databricks-serverless -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/databricks/databricks-agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/databricks-serverless .github/skills/databricks-serverless && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "databricks-serverless" agent skill from https://github.com/databricks/databricks-agent-skills/tree/main/skills/databricks-serverless into .github/skills/databricks-serverless/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "databricks-serverless", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add databricks/databricks-agent-skills --skill databricks-serverless -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install databricks/databricks-agent-skills databricks-serverless --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/databricks/databricks-agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/databricks-serverless .opencode/skills/databricks-serverless && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "databricks-serverless" agent skill from https://github.com/databricks/databricks-agent-skills/tree/main/skills/databricks-serverless into .opencode/skills/databricks-serverless/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "databricks-serverless", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
databricks-serverless- GitHub stars
- 345
- Token cost
- ~2.7k tokens
- SKILL.md length
- 1,406 words
- Files
- 4 (incl. assets)
- Skills in repo
- 34
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Serverless compute for Databricks jobs, Lakeflow pipelines and Declarative Automation Bundles (DABs), with STANDARD or PERFORMANCEOPTIMIZED and classic only where serverless cannot run the workload.
- Works in 5 steps: Serverless or classic → Put every task on serverless → Choose the performance mode → …
- Deciding its compute
- SKILL.md covers 1. Serverless or classic, 2. Put every task on serverless, 3. Choose the performance mode and 4. Code you write runs on…, plus 4 more sections
- Calls pip
What it does
Databricks Serverless is an agent skill from databricks/databricks-agent-skills, published by the product's own GitHub organization. Serverless compute for Databricks jobs, Lakeflow pipelines and Declarative Automation Bundles (DABs), with STANDARD or PERFORMANCEOPTIMIZED and classic only where serverless cannot run the workload. Use when creating, deploying, scheduling or editing a job or pipeline, or deciding its compute. Invoke BEFORE writing a job spec. For migrating existing classic workloads, use databricks-serverless-migration.
Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including assets (for example `agents/openai.yaml`). Compatibility notes: Requires databricks CLI (= v0.292.0)
It sits in Backend & APIs, covering Serverless. It works with Databricks. The repository describes itself as: Databricks AI Tools: skills and plugins for building on Databricks with Claude Code, Cursor, Codex, GitHub Copilot, and other AI coding agents.
When your agent uses it
- Deciding its compute
- Tasks that involve Serverless
Example prompts
- “/databricks-serverless”
Requirements
- Python 3
- Docker
- Compatibility (from SKILL.md): Requires databricks CLI (>= v0.292.0)
Workflow steps
5 steps, taken from the step headings in SKILL.md.
- Serverless or classic
- Put every task on serverless
- Choose the performance mode
- Code you write runs on serverless from the start
- Existing code: a quick check, not a migration
What it can do on your machine
Read from SKILL.md and the folder at commit aa6b16a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
docs.databricks.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Requires databricks CLI (>= v0.292.0)
From compatibility in the SKILL.md frontmatter.
Context cost
Databricks Serverless loads about 2.7k tokens when it runs. Until then it costs about 108 tokens; SKILL.md has 1,406 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,406 words (~2,725 tokens).
“FIRST: Use the parent databricks-core skill for CLI basics, authentication and profile selection.”
- name
- databricks-serverless
- compatibility
- Requires databricks CLI (>= v0.292.0)
- metadata.version
- 0.3.2
- parent
- databricks-core
Files
SKILL.md and 3 other files (assets) in skills/databricks-serverless of databricks/databricks-agent-skills.
- SKILL.md
- agents/openai.yaml
- assets/databricks.png
- assets/databricks.svg
Open the folder on GitHubat commit aa6b16a
Compare with similar skills
Databricks Serverless next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Databricks Serverless this skilldatabricks/databricks-agent-skills | 345 | — | ~2.7k | Automated safety check: Pass | Custom licence | |
| Cookbook Computedatabricks-solutions/databricks-apps-cookbook | 183 | — | ~790 | Automated safety check: Pass | Custom licence | |
| Neonsmontlouis/bible-strong | 171 | — | ~7.1k | Automated safety check: Notes | GPL-3.0 | |
| Azure Synapse AnalyticsMicrosoftDocs/Agent-Skills | 777 | 1 repos | ~13k | Automated safety check: Pass | CC-BY-4.0 | |
| Arcgis To Portaljsdatopian/portaljs | 2.4k | 1 repos | ~2k | Automated safety check: Pass | MIT | |
| AWS Serverless Edazxkane/aws-skills | 367 | 4 repos | ~3.2k | Automated safety check: Pass | MIT |
Similar skills
Neon
smontlouis/bible-strong
Overview of Neon, a complete set of cloud backend primitives for apps and agents, spanning Lakebase Postgres, Auth, the Data API, Object Storage, Compute Functions, and the AI Gateway.
- Official
Azure Synapse Analytics
MicrosoftDocs/Agent-Skills
Expert knowledge for Azure Synapse Analytics development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration…
Arcgis To Portaljs
datopian/portaljs
Migrate a whole ArcGIS Hub site into a PortalJS Arc portal end-to-end.
AWS Serverless Eda
zxkane/aws-skills
AWS serverless and event-driven architecture expert based on Well-Architected Framework.
Nubase
OtterMind/Nubase
A skill your agent uses when the user mentions Nubase broadly, wants a backend for an AI-generated app, or needs to deploy/publish generated code online — across Database, Auth, Storage, Assets…
More from databricks/databricks-agent-skills
All 34 skills in this repo- Official
Databricks Dbsql
databricks/databricks-agent-skills
Databricks SQL (DBSQL) advanced features and SQL warehouse capabilities.
- Official
Databricks Synthetic Data Gen
databricks/databricks-agent-skills
Generate realistic synthetic data using Spark + Faker (strongly recommended).
- Official
Databricks Model Serving
databricks/databricks-agent-skills
Databricks Model Serving endpoint lifecycle and ops. An agent skill from databricks/databricks-agent-skills.
- Official
Databricks Python SDK
databricks/databricks-agent-skills
Databricks development guidance including Python SDK, Databricks Connect, CLI, and REST API.
- Official
Databricks Spark Structured Streaming
databricks/databricks-agent-skills
Comprehensive guide to Spark Structured Streaming for production workloads.
- Official
Databricks App Design
databricks/databricks-agent-skills
Design the UX of custom-code Databricks Apps (AppKit/React) data screens — KPI/overview pages, reports, charts, tables, and Genie/chat data assistants — mapped to concrete AppKit components.
Related
Works with
Categories
Questions about Databricks Serverless
What does Databricks Serverless do?
Serverless compute for Databricks jobs, Lakeflow pipelines and Declarative Automation Bundles (DABs), with STANDARD or PERFORMANCEOPTIMIZED and classic only where serverless cannot run the workload. Databricks Serverless is an agent skill from databricks/databricks-agent-skills, published by the product's own GitHub organization. Serverless compute for Databricks jobs, Lakeflow pipelines and Declarative Automation Bundles (DABs), with STANDARD or PERFORMANCEOPTIMIZED and classic only where serverless cannot run the workload.
When should I use Databricks Serverless?
Databricks Serverless fits situations like: deciding its compute; tasks that involve Serverless.
How do I install Databricks Serverless in Claude Code?
Run `npx skills add databricks/databricks-agent-skills --skill databricks-serverless -a claude-code`. Or copy the skill folder (skills/databricks-serverless in databricks/databricks-agent-skills) into .claude/skills/databricks-serverless in your project. Claude Code loads it when a task matches its description.
How do I install Databricks Serverless in Codex?
Run `npx skills add databricks/databricks-agent-skills --skill databricks-serverless -a codex`. Or copy the skill folder (skills/databricks-serverless in databricks/databricks-agent-skills) into .agents/skills/databricks-serverless in your project. Codex loads it when a task matches its description.
Can I use Databricks Serverless in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add databricks/databricks-agent-skills --skill databricks-serverless -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/databricks-serverless, .gemini/skills/databricks-serverless, .github/skills/databricks-serverless and .opencode/skills/databricks-serverless in your project.
What does Databricks Serverless need to run?
Going by SKILL.md and its folder, Databricks Serverless needs the command-line tools its instructions call (pip). Our summary lists: Python 3; Docker. Compatibility (from SKILL.md): Requires databricks CLI (>= v0.292.0).
Does Databricks Serverless access the network?
SKILL.md names 1 domain. As links in the text: docs.databricks.com. This is read from the text; nothing was executed.
Is Databricks Serverless safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Databricks Serverless use?
Databricks Serverless has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Databricks Serverless use?
About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Databricks Serverless?
Skills that share tags, products or a category with Databricks Serverless: Cookbook Compute (databricks-solutions/databricks-apps-cookbook, 183 stars), Neon (smontlouis/bible-strong, 171 stars), Azure Synapse Analytics (MicrosoftDocs/Agent-Skills, 777 stars) and Arcgis To Portaljs (datopian/portaljs, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Databricks Serverless?
databricks (a GitHub organization, an official publisher) maintains it in databricks/databricks-agent-skills, which has 345 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on October 9, 2026.
Source: databricks/databricks-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.