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'.
84
76%
Does it follow best practices?
Impact
100%
1.72xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./agent-langgraph-advanced/.claude/skills/lakebase-setup/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured skill description with strong trigger coverage and explicit 'Use when' guidance. It excels at distinctiveness due to the specific product name and error messages. The main weakness is that the 'what' portion could be more specific about the concrete actions performed during configuration.
Suggestions
Expand the capability description to list specific actions, e.g., 'Configure Lakebase for agent memory storage, set up checkpoint and store tables, manage connection settings and permissions.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Lakebase, agent memory storage) and mentions some actions like configuring and troubleshooting specific errors, but doesn't list multiple concrete configuration steps or actions beyond 'configure'. | 2 / 3 |
Completeness | Clearly answers both 'what' (configure Lakebase for agent memory storage) and 'when' with an explicit 'Use when:' clause covering four distinct trigger scenarios including feature requests, error conditions, and user keywords. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'lakebase', 'memory setup', 'add memory', plus specific error messages like 'Failed to connect to Lakebase' and 'Permission errors on checkpoint/store tables' that users would encounter and mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific product name 'Lakebase', specific error messages, and niche domain of agent memory storage configuration. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured skill with a clear 7-step workflow and excellent troubleshooting coverage. However, it suffers significantly from verbosity — the complete databricks.yml examples duplicate earlier step content, and reference material (API docs, SP identifiers) bloats the main file. The duplicate Step 5 header suggests incomplete editing.
Suggestions
Move the two complete databricks.yml examples into separate referenced files (e.g., examples/lakebase-provisioned-full.yaml and examples/lakebase-autoscaling-full.yaml) to eliminate ~80 lines of duplication
Move the LakebaseClient API reference and Service Principal Identifiers sections into a separate LAKEBASE_REFERENCE.md file, keeping only a one-line reference in the main skill
Consolidate the 'Use Cases' and 'Overview' sections — they overlap significantly in describing short-term and long-term memory
Fix the duplicate Step 5 header ('Initialize Tables' / 'Deploy') which appears to be an editing artifact
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~350+ lines with significant redundancy. The complete databricks.yml examples repeat nearly all the YAML already shown in Steps 3-4. The 'Use Cases' and 'Overview' sections overlap heavily. The LakebaseClient API reference and SP identifier tables add bulk that could be in separate files. Much content is duplicated across provisioned/autoscaling variants. | 1 / 3 |
Actionability | The skill provides fully executable commands, complete YAML configurations, specific CLI invocations with profile flags, and concrete code examples for the LakebaseClient API. Every step has copy-paste ready content with specific placeholder patterns. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with a visual diagram, explicit validation points (Step 6 is marked CRITICAL with a WARNING), and the troubleshooting table serves as error recovery guidance. The grant step correctly warns about consequences of skipping it, and the deploy-then-run distinction is explicitly called out. | 3 / 3 |
Progressive Disclosure | The skill references external files (examples/lakebase.yaml, other skills) and has a 'Next Steps' section, but the body itself is monolithic — the complete YAML examples, LakebaseClient API reference, and SP identifier tables should be in separate referenced files. There's also a duplicate Step 5 header (Initialize Tables / Deploy) suggesting editing issues. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- databricks/app-templates
- Commit
1c88215
- Reviewed
Table of Contents
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.