/databricks-doctor
Read-only Databricks health check: CLI, profiles, auth validity via one API call. Add `full` after the command to also check compute and recent job failures.
> /plugin marketplace add databricks/databricks-agent-skills > /plugin install databricks@databricks-agent-skills
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/databricks-doctor
Context preview
What this command does when you run it.
Read-only Databricks health check: CLI, profiles, auth validity via one API call. Add `full` after the command to also check compute and recent job failures.
Command definition
databricks-doctor.mdname: databricks-doctor
description: "Read-only Databricks health check: CLI, profiles, auth validity via one API call. Add `full` after the command to also check compute and recent job failures."
Databricks Doctor
Run a **read-only** health check and report a short status table. Make no changes; every step below only reads. If a subcommand or flag is unfamiliar, check `databricks <group> --help` first rather than guessing.
Run these in order. Don't stop on the first failure; collect what you can and report the rest as unknown.
1. **CLI**: `databricks --version`. Flag only if it's missing; don't gate on a specific version (the CLI surfaces its own update notice). 2. **Profiles**: `databricks auth profiles`. List configured profiles and validity. If the user named a profile after the command, use it for the rest. Otherwise, if more than one profile exists, ask the user which to use (**never auto-select**). 3. **Auth method**: `databricks auth describe --profile <profile>` shows the effective host, user, and credential source (never pass `--sensitive`). 4. **Auth validity**: `databricks current-user me --profile <profile>`. This single API call proves the credentials work end to end (token valid, workspace reachable, expected identity); don't probe other APIs for it. For account-level profiles (an `accounts.*` host), `current-user me` does not exist; report what `auth describe` resolved instead.
Stop here by default. Run the extended checks below only when the user typed `full` after the command or asked about compute or jobs:
5. **Compute**: `databricks warehouses list` and `databricks clusters list` for the profile. Note what's running. 6. **Recent job failures**: list recent job runs (e.g. `databricks jobs list-runs --limit 20 --profile <profile>`) and surface any recent failures.
Then print a compact table: **check | status (✅/⚠️/❌) | detail**. End with the single most useful next action (e.g. "run `/databricks-setup` to add a profile").
This is a status check; it only reads, so don't run anything that changes state.
Read more
name: databricks-doctor description: "Read-only Databricks health check: CLI, profiles, auth validity via one API call. Add `full` after the command to also check compute and recent job failures."
Databricks Doctor
Run a **read-only** health check and report a short status table. Make no changes; every step below only reads. If a subcommand or flag is unfamiliar, check `databricks <group> --help` first rather than guessing.
Run these in order. Don't stop on the first failure; collect what you can and report the rest as unknown.
1. **CLI**: `databricks --version`. Flag only if it's missing; don't gate on a specific version (the CLI surfaces its own update notice). 2. **Profiles**: `databricks auth profiles`. List configured profiles and validity. If the user named a profile after the command, use it for the rest. Otherwise, if more than one profile exists, ask the user which to use (**never auto-select**). 3. **Auth method**: `databricks auth describe --profile <profile>` shows the effective host, user, and credential source (never pass `--sensitive`). 4. **Auth validity**: `databricks current-user me --profile <profile>`. This single API call proves the credentials work end to end (token valid, workspace reachable, expected identity); don't probe other APIs for it. For account-level profiles (an `accounts.*` host), `current-user me` does not exist; report what `auth describe` resolved instead.
Stop here by default. Run the extended checks below only when the user typed `full` after the command or asked about compute or jobs:
5. **Compute**: `databricks warehouses list` and `databricks clusters list` for the profile. Note what's running. 6. **Recent job failures**: list recent job runs (e.g. `databricks jobs list-runs --limit 20 --profile <profile>`) and surface any recent failures.
Then print a compact table: **check | status (✅/⚠️/❌) | detail**. End with the single most useful next action (e.g. "run `/databricks-setup` to add a profile").
This is a status check; it only reads, so don't run anything that changes state.
Skills for AI coding assistants (Claude Code, Cursor, etc.) that provide Databricks-specific guidance.
Repo: databricks/databricks-agent-skills
Other commands on databricks-agent-skills.
- /doctor
Read-only Databricks health check: CLI, profiles, auth validity via one API call. Add `full` after the command to also check compute and recent job failures."}}
Open command - /setup
Set up Databricks CLI auth: install check, then an OAuth / PAT / service-principal profile (workspace or account-level), then verify."}}
Open command - /databricks-setup
Set up Databricks CLI auth: install check, then an OAuth / PAT / service-principal profile (workspace or account-level), then verify.
Open command

