Name: agent-memory
Rating: 57.599999999999994 (1 reviews)
Author: databricks

agent-memory

Add memory capabilities to your agent. Use when: (1) User asks about 'memory', 'state', 'remember', 'conversation history', (2) Want to persist conversations or user preferences, (3) Adding checkpointing or long-term storage.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, code-rich skill that is highly actionable and well-sequenced, but it is monolithic with no bundle files, repeats content across sections, references a missing examples file, and lacks an explicit validation feedback loop for the database setup.

Suggestions

Create the referenced examples/memory_tools.py bundle file with the full memory_tools implementation and trim SKILL.md to an overview, eliminating the broken reference and the repeated store-setup/deploy sections.

Add an explicit validate→fix→retry loop to the Lakebase setup: verify a test write/read after `store.setup()` and re-run setup or check grants on errors before deploying.

Replace the '...' placeholders in the Key Principles snippets with complete executable tool bodies, or explicitly mark them as abbreviated and link to the complete file.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete code and tables, but it repeats store-setup and the agent-langgraph-advanced reference across multiple sections and could be tightened.	2 / 3
Actionability	It provides extensive copy-paste-ready code, but the central 'memory_tools()' factory uses '...' placeholders and the promised 'examples/memory_tools.py' complete file does not exist.	2 / 3
Workflow Clarity	The setup checklist and ordered steps give a clear sequence, but the Lakebase database workflow lacks an explicit validate→fix→retry feedback loop before deploy, capping the score at 2.	2 / 3
Progressive Disclosure	The skill is a single ~385-line file with no bundle files, and its one reference to 'examples/memory_tools.py' points to a file that is absent; content that should be split is inline.	2 / 3
	Total	8 / 12 Passed

Description

80%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit 'Use when' triggers, good natural keywords, and a clear niche; its main weakness is the generic, second-person headline action that limits specificity.

Suggestions

Rewrite in third person and replace the generic 'Add memory capabilities to your agent' with concrete actions, e.g. 'Persists conversation history and user facts across sessions via AsyncCheckpointSaver and AsyncDatabricksStore.'

Drop the second-person 'your agent' phrasing to avoid the rubric's voice penalty; use impersonal wording like 'Adds memory to an agent.'

Dimension	Reasoning	Score
Specificity	The single headline action 'Add memory capabilities to your agent' is generic rather than a list of concrete actions, and the second-person 'your agent' triggers the rubric's third-person voice penalty, reducing the score by one.	1 / 3
Completeness	It states what the skill does ('Add memory capabilities to your agent') and gives an explicit 'Use when:' clause with three numbered triggers, clearly answering both what and when.	3 / 3
Trigger Term Quality	It includes natural terms users would actually say — 'memory', 'remember', 'conversation history', 'user preferences' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The agent-memory niche with distinctive triggers ('remember', 'conversation history', 'checkpointing') is unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: databricks/app-templates
Commit: 2a4c792

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.