How do I install the Quickstart skill?

Run npx skillmds@latest add databricks/quickstart-4 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Quickstart safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Quickstart?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Quickstart free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Quickstart?

databricks (@databricks) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Quickstart by databricks — Agent Skill

Name: Quickstart
Author: databricks

Quickstart

Set up the Databricks chatbot app for local development and deployment. Use when: (1) First time setup, (2) User says 'quickstart', 'set up', 'authenticate', or 'configure databricks', (3) No .env file exists, (4) User says 'enable feedback', 'feedback widget', or 'MLFLOW_EXPERIMENT_ID'.

databricks 483d586 3.2 KB Updated Sep 17, 2026

File contents

Quickstart: Databricks Chatbot App

Run the interactive setup script from the e2e-chatbot-app-next/ directory:

./scripts/quickstart.sh

What It Configures

The script walks through the following steps interactively:

Prerequisites — installs jq, nvm, Node 20, and the Databricks CLI if missing
Databricks auth — lets you select an existing profile or create a new one via databricks auth login
Serving endpoint — prompts for your agent endpoint name (Agent Bricks or custom agent); validates it exists
Feedback widget — if the endpoint has a linked MLflow experiment, offers to enable thumbs up/down feedback (default: yes). This automatically:
- Sets MLFLOW_EXPERIMENT_ID in .env
- Uncomments the experiment resource in databricks.yml
- Uncomments MLFLOW_EXPERIMENT_ID in app.yaml
App/bundle name — optionally customize the app name (default: db-chatbot-dev-<username>, max 30 chars)
Database — optionally enable persistent chat history via a Lakebase instance (~5-10 min, costs apply)
Deploy — runs databricks bundle deploy and starts the app

Enabling Feedback After Initial Setup

If you skipped feedback during quickstart, or ran the script before feedback support was added, enable it manually:

1. Find the experiment name for your endpoint:

npx tsx scripts/get-experiment-id.ts --endpoint <your-serving-endpoint-name>

For Agent Bricks (Knowledge Assistant / Multi-Agent Supervisor):

npx tsx scripts/get-experiment-id.ts --agent-brick <agent-brick-name>

2. Set MLFLOW_EXPERIMENT_ID in .env (for local dev):

MLFLOW_EXPERIMENT_ID=<experiment-name-from-step-1>

3. Configure databricks.yml — uncomment and fill in the experiment resource:

        - name: experiment
          description: "MLflow experiment for collecting user feedback"
          experiment:
            name: "<experiment-name-from-step-1>"
            permission: CAN_EDIT

4. Configure app.yaml — uncomment the env var:

      - name: MLFLOW_EXPERIMENT_ID
        valueFrom: experiment

5. Redeploy:

databricks bundle deploy
databricks bundle run databricks_chatbot

Troubleshooting

Issue	Solution
Feedback widget not showing after setup	Restart dev server; env vars are read at startup
`get-experiment-id.ts` fails with auth error	Run `databricks auth login` first
No experiment found for endpoint	Only custom agents and Agent Bricks endpoints have linked experiments; Foundation Model endpoints do not support feedback
Feedback submission returns 403	App service principal is missing `CAN_EDIT` on the experiment — check `permission: CAN_EDIT` in `databricks.yml`
"Instance name is not unique" on deploy	Run `./scripts/cleanup-database.sh` to remove the old database instance

---name: quickstart-4description: Set up the Databricks chatbot app for local development and deployment. Use when: (1) First time setup, (2) User says 'quickstart', 'set up', 'authenticate', or 'configure databricks', (3) No .env file exists, (4) User says 'enable feedback', 'feedback widget', or 'MLFLOW_EXPERIMENT_ID'.---# Quickstart: Databricks Chatbot AppRun the interactive setup script from the `e2e-chatbot-app-next/` directory:```bash./scripts/quickstart.sh```## What It ConfiguresThe script walks through the following steps interactively:1. **Prerequisites** — installs jq, nvm, Node 20, and the Databricks CLI if missing2. **Databricks auth** — lets you select an existing profile or create a new one via `databricks auth login`3. **Serving endpoint** — prompts for your agent endpoint name (Agent Bricks or custom agent); validates it exists4. **Feedback widget** — if the endpoint has a linked MLflow experiment, offers to enable thumbs up/down feedback (default: yes). This automatically: - Sets `MLFLOW_EXPERIMENT_ID` in `.env` - Uncomments the experiment resource in `databricks.yml` - Uncomments `MLFLOW_EXPERIMENT_ID` in `app.yaml`5. **App/bundle name** — optionally customize the app name (default: `db-chatbot-dev-<username>`, max 30 chars)6. **Database** — optionally enable persistent chat history via a Lakebase instance (~5-10 min, costs apply)7. **Deploy** — runs `databricks bundle deploy` and starts the app## Enabling Feedback After Initial SetupIf you skipped feedback during quickstart, or ran the script before feedback support was added, enable it manually:**1. Find the experiment name for your endpoint:**```bashnpx tsx scripts/get-experiment-id.ts --endpoint <your-serving-endpoint-name>```For Agent Bricks (Knowledge Assistant / Multi-Agent Supervisor):```bashnpx tsx scripts/get-experiment-id.ts --agent-brick <agent-brick-name>```**2. Set `MLFLOW_EXPERIMENT_ID` in `.env`** (for local dev):```MLFLOW_EXPERIMENT_ID=<experiment-name-from-step-1>```**3. Configure `databricks.yml`** — uncomment and fill in the experiment resource:```yaml - name: experiment description: "MLflow experiment for collecting user feedback" experiment: name: "<experiment-name-from-step-1>" permission: CAN_EDIT```**4. Configure `app.yaml`** — uncomment the env var:```yaml - name: MLFLOW_EXPERIMENT_ID valueFrom: experiment```**5. Redeploy:**```bashdatabricks bundle deploydatabricks bundle run databricks_chatbot```## Troubleshooting| Issue | Solution ||-------|----------|| Feedback widget not showing after setup | Restart dev server; env vars are read at startup || `get-experiment-id.ts` fails with auth error | Run `databricks auth login` first || No experiment found for endpoint | Only custom agents and Agent Bricks endpoints have linked experiments; Foundation Model endpoints do not support feedback || Feedback submission returns 403 | App service principal is missing `CAN_EDIT` on the experiment — check `permission: CAN_EDIT` in `databricks.yml` || "Instance name is not unique" on deploy | Run `./scripts/cleanup-database.sh` to remove the old database instance |

Frequently asked questions