Name: lakebase-setup
Rating: 82.39999999999999 (1 reviews)
Author: databricks

lakebase-setup

Configure Lakebase for agent memory storage. Use when: (1) Adding memory capabilities to the agent, (2) 'Failed to connect to Lakebase' errors, (3) Permission errors on checkpoint/store tables, (4) User says 'lakebase', 'memory setup', or 'add memory'.

1.72x

Quality

72%

Does it follow best practices?

Impact

100%

1.72x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./agent-langgraph-advanced/.claude/skills/lakebase-setup/SKILL.md

Evaluation results

100%

24%

Adding Persistent Memory to a Databricks Agent App

Provisioned Lakebase DAB config

Criteria

Without context

With context

Memory dependency

100%

Database resource type

100%

database_name value

100%

CAN_CONNECT_AND_CREATE permission

100%

LAKEBASE_INSTANCE_NAME wiring

100%

value_from matches resource name

100%

EMBEDDING_ENDPOINT in databricks.yml

100%

EMBEDDING_DIMS in databricks.yml

100%

.env LAKEBASE_INSTANCE_NAME

100%

.env embedding config

100%

Profile in CLI commands

100%

60%

Migrating Agent Memory to Autoscaling Lakebase

Autoscaling Lakebase DAB config

Criteria

Without context

With context

Postgres resource type

100%

Branch full path format

100%

Database full path format

100%

Internal database ID used

100%

CAN_CONNECT_AND_CREATE permission

100%

LAKEBASE_AUTOSCALING_PROJECT env var

100%

LAKEBASE_AUTOSCALING_BRANCH env var

100%

.env autoscaling vars

100%

EMBEDDING_ENDPOINT and EMBEDDING_DIMS

100%

Embedding dims value

100%

Profile in CLI commands

100%

40%

Lakebase Setup Runbook for New Team Members

SP permissions grant workflow

Criteria

Without context

With context

Profile flag on all commands

100%

Deploy before grant

100%

Get SP client ID command

60%

100%

Uses service_principal_client_id

100%

grant_lakebase_permissions.py invocation

100%

--memory-type flag

100%

bundle run after grant

20%

100%

LakebaseClient create_role first

100%

LakebaseClient identifier type

100%

Grant step marked as critical

100%

Memory dependency included

100%

Repository: databricks/app-templates
Commit: dfeb4ac

Evaluated: about 18 hours ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Adding Persistent Memory to a Databricks Agent App Migrating Agent Memory to Autoscaling Lakebase Lakebase Setup Runbook for New Team Members

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.