New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Databricks AI Runtime

by databricks in databricks/databricks-agent-skills

Databricks AI Runtime, the databricks air CLI commands for submitting and managing GPU training workloads on Databricks serverless compute.

OfficialCustom licenceAuto-check passedBackend & APIs

Install Databricks AI Runtime

skills CLI
$ npx skills add databricks/databricks-agent-skills --skill databricks-ai-runtime -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install databricks/databricks-agent-skills databricks-ai-runtime --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/databricks/databricks-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/experimental/databricks-ai-runtime .claude/skills/databricks-ai-runtime && rm -rf skills-src

Use ~/.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/

Facts

Skill name
databricks-ai-runtime
GitHub stars
345
Token cost
~3k tokens
SKILL.md length
1,222 words
Files
5 (incl. assets)
Skills in repo
32
Repo updated
First seen
Licence
Custom licence

At a glance

Databricks AI Runtime, the databricks air CLI commands for submitting and managing GPU training workloads on Databricks serverless compute.

  • Works in 5 steps: Turn the user's intent into the YAML.… → Write the command: using the env vars… → Pre-flight the referenced resources so… → …
  • : writing and submitting databricks air workload YAML
  • SKILL.md covers Reference discipline, Session setup, Subcommands and Workload YAML, plus 7 more sections
  • Calls databricks, python and composer; needs HF_TOKEN and WANDB_API_KEY

What it does

Databricks AI Runtime is an agent skill from databricks/databricks-agent-skills, published by the product's own GitHub organization. Databricks AI Runtime, the databricks air CLI commands for submitting and managing GPU training workloads on Databricks serverless compute. Use for: writing and submitting databricks air workload YAML, passing hyperparameters and secrets, checking run status, listing/cancelling runs, streaming a run's logs and watching its progress, custom Docker image setup, and environment configuration.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including assets (for example `agents/openai.yaml` and `docker-images.md`). Compatibility notes: Requires the Databricks CLI with the air command. See the [installation guide](https://docs.databricks.com/aws/en/machine-learning/ai-runtime/cli/installation)…

It sits in Backend & APIs, covering Serverless. It works with Databricks and Docker. 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

  • : writing and submitting databricks air workload YAML
  • Passing hyperparameters and secrets
  • Checking run status
  • Listing/cancelling runs

Example prompts

  • “Use the databricks-ai-runtime skill to databrick AI Runtime, the databricks air CLI commands for submitting and managing GPU training workloads on…”
  • “/databricks-ai-runtime”

Requirements

  • Python 3
  • Docker
  • A credential in WANDB_API_KEY
  • Compatibility (from SKILL.md): Requires the Databricks CLI with the `air` command. See the [installation guide](https://docs.databricks.com/aws/en/machine-learning/ai-runtime/cli/installation) to get started.

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Turn the user's intent into the YAML. Extract model, dataset path, GPU
  2. Write the command: using the env vars above. Common launch shapes
  3. Pre-flight the referenced resources so the job does not die on startup
  4. Dry-run before submitting. This validates the config without launching
  5. Submit. Use a stable --idempotency-key so an accidental re-run does not

What it can do on your machine

Read from SKILL.md and the folder at commit f4fcec5. 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:

    • databricks
    • python
    • composer

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • HF_TOKEN
    • WANDB_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires the Databricks CLI with the `air` command. See the [installation guide](https://docs.databricks.com/aws/en/machine-learning/ai-runtime/cli/installation) to get started.

    From compatibility in the SKILL.md frontmatter.

Context cost

Databricks AI Runtime loads about 3k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 1,222 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~3k

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 1,222 words (~3,023 tokens).

“Databricks AI Runtime is a set of databricks air CLI commands for submitting GPU training workloads to Databricks serverless compute. It manages environment setup, distributed training configuration, and workload lifecycle, without requiring you to manage clusters or infrastructure.”

— opening of SKILL.md by databricks, Custom licence
name
databricks-ai-runtime
compatibility
Requires the Databricks CLI with the `air` command. See the [installation guide](https://docs.databricks.com/aws/en/machine-learning/ai-runtime/cli/installation) to get started.
metadata.version
0.2.0

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (assets) in experimental/databricks-ai-runtime of databricks/databricks-agent-skills.

  • SKILL.md
  • agents/openai.yaml
  • assets/databricks.png
  • assets/databricks.svg
  • docker-images.md

Open the folder on GitHubat commit f4fcec5

Compare with similar skills

Databricks AI Runtime 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.

Databricks AI Runtime compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Databricks AI Runtime this skilldatabricks/databricks-agent-skills345—~3kAutomated safety check: PassCustom licence
GCP Cloud Rundavila7/claude-code-templates32k7 repos~1.7kAutomated safety check: PassMIT
Neonsmontlouis/bible-strong171—~7.1kAutomated safety check: NotesGPL-3.0
Polylith Project ManagementDavidVujic/python-polylith553—~1.5kAutomated safety check: PassMIT
Model Deploymentmajiayu000/claude-skill-registry6661 repos~2.1kAutomated safety check: PassMIT
CloudbaseTencentCloudBase/CloudBase-AI-Toolkit1.1k1 repos~4.7kAutomated safety check: PassMIT

Similar skills

  • GCP Cloud Run

    davila7/claude-code-templates

    Specialized skill for building production-ready serverless applications on GCP.

    32k GitHub starsUsed in 7 repos~1.7k tokens
    Backend & APIsAuto-check passed

  • 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.

    171 GitHub stars~7.1k tokensUpdated yesterday
    Backend & APIsAuto-check: notes

  • Polylith Project Management

    DavidVujic/python-polylith

    Create a deployable Polylith project with poly create project — a lightweight pyproject.toml under projects/<name/ that references bricks for deployment as a Docker image, wheel, AWS Lambda, GCP…

    553 GitHub stars~1.5k tokensUpdated 3 days ago
    Backend & APIsAuto-check passed

  • Model Deployment

    majiayu000/claude-skill-registry

    Deploy trained machine learning models as production-ready services using REST APIs, containers, serverless functions, and orchestration platforms.

    666 GitHub starsUsed in 1 repo~2.1k tokens
    Backend & APIsAuto-check passed

  • Cloudbase

    TencentCloudBase/CloudBase-AI-Toolkit

    A skill your agent uses when you develop, design, build, deploy, debug, migrate, or troubleshoot CloudBase (腾讯云开发, 云开发, TCB, 微信云开发) projects — Web, 微信小程序, 小程序, uni-app, mobile (iOS, Android…

    1.1k GitHub starsUsed in 1 repo~4.7k tokens
    Backend & APIsAuto-check passed

  • Cookbook Compute

    databricks-solutions/databricks-apps-cookbook

    Connect Databricks Apps to shared clusters or serverless compute using Databricks Connect.

    183 GitHub stars~790 tokensUpdated 3 days ago
    Backend & APIsAuto-check passed

More from databricks/databricks-agent-skills

All 32 skills in this repo

  • Databricks Dbsql

    databricks/databricks-agent-skills

    Official

    Databricks SQL (DBSQL) advanced features and SQL warehouse capabilities.

    345 GitHub starsUsed in 1 repo~2.8k tokens
    Auto-check passed

  • Databricks Synthetic Data Gen

    databricks/databricks-agent-skills

    Official

    Generate realistic synthetic data using Spark + Faker (strongly recommended).

    345 GitHub stars~3.2k tokensUpdated yesterday
    Auto-check passed

  • Databricks Model Serving

    databricks/databricks-agent-skills

    Official

    Databricks Model Serving endpoint lifecycle and ops. An agent skill from databricks/databricks-agent-skills.

    345 GitHub starsUsed in 1 repo~3.3k tokens
    Auto-check passed

  • Databricks Python SDK

    databricks/databricks-agent-skills

    Official

    Databricks development guidance including Python SDK, Databricks Connect, CLI, and REST API.

    345 GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed

  • Databricks Spark Structured Streaming

    databricks/databricks-agent-skills

    Official

    Comprehensive guide to Spark Structured Streaming for production workloads.

    345 GitHub starsUsed in 1 repo~956 tokens
    Auto-check passed

  • Databricks App Design

    databricks/databricks-agent-skills

    Official

    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.

    345 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Databricks AI Runtime

What does Databricks AI Runtime do?

Databricks AI Runtime, the databricks air CLI commands for submitting and managing GPU training workloads on Databricks serverless compute. Databricks AI Runtime is an agent skill from databricks/databricks-agent-skills, published by the product's own GitHub organization. Databricks AI Runtime, the databricks air CLI commands for submitting and managing GPU training workloads on Databricks serverless compute.

When should I use Databricks AI Runtime?

Databricks AI Runtime fits situations like: : writing and submitting databricks air workload YAML; passing hyperparameters and secrets; checking run status; listing/cancelling runs.

How do I install Databricks AI Runtime in Claude Code?

Run `npx skills add databricks/databricks-agent-skills --skill databricks-ai-runtime -a claude-code`. Or copy the skill folder (experimental/databricks-ai-runtime in databricks/databricks-agent-skills) into .claude/skills/databricks-ai-runtime in your project. Claude Code loads it when a task matches its description.

How do I install Databricks AI Runtime in Codex?

Run `npx skills add databricks/databricks-agent-skills --skill databricks-ai-runtime -a codex`. Or copy the skill folder (experimental/databricks-ai-runtime in databricks/databricks-agent-skills) into .agents/skills/databricks-ai-runtime in your project. Codex loads it when a task matches its description.

Can I use Databricks AI Runtime 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-ai-runtime -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-ai-runtime, .gemini/skills/databricks-ai-runtime, .github/skills/databricks-ai-runtime and .opencode/skills/databricks-ai-runtime in your project.

What does Databricks AI Runtime need to run?

Going by SKILL.md and its folder, Databricks AI Runtime needs the command-line tools its instructions call (databricks, python and composer) and credentials named HF_TOKEN and WANDB_API_KEY. Our summary lists: Python 3; Docker; A credential in WANDB_API_KEY. Compatibility (from SKILL.md): Requires the Databricks CLI with the `air` command. See the [installation guide](https://docs.databricks.com/aws/en/machine-learning/ai-runtime/cli/installation) to get started..

Does Databricks AI Runtime access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Databricks AI Runtime 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 AI Runtime use?

Databricks AI Runtime 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 AI Runtime use?

About 3k tokens (SKILL.md is roughly 12k 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 AI Runtime?

Skills that share tags, products or a category with Databricks AI Runtime: GCP Cloud Run (davila7/claude-code-templates, 32k stars), Neon (smontlouis/bible-strong, 171 stars), Polylith Project Management (DavidVujic/python-polylith, 553 stars) and Model Deployment (majiayu000/claude-skill-registry, 666 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Databricks AI Runtime?

databricks (a GitHub organization, an official publisher) maintains it in databricks/databricks-agent-skills, which has 345 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on October 6, 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.