Name: agent-memory
Rating: 62.4 (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

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/agent-langgraph-memory/SKILL.md

The canonical home for this skill is agent-memory in databricks/app-templates

Quality

Content

63%Weight 40%Scale 1-5

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

A thorough, highly actionable integration guide with executable code, a setup checklist, and a troubleshooting table, but it leans verbose with redundant store-setup examples and relies on a monolithic structure plus a broken internal file reference.

Suggestions

Add the missing examples/memory_tools.py bundle file (or remove the reference) so the 'Complete Example' pointer resolves.

De-duplicate the AsyncDatabricksStore setup shown in the Integration Example, Short-Term Memory, and Initialize Tables sections into one canonical snippet.

Move the large Configuration Files and Troubleshooting blocks into reference files under references/ and link to them from the overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with dense tables and code, but the ~380-line body repeats store-setup patterns across the 'Integration Example', 'Short-Term Memory', and 'Initialize Tables' sections, and the 'Complete Example' section is a thin pointer that could be trimmed.	3 / 5
Actionability	Rich, copy-paste-ready code and concrete commands (uv sync, bundle deploy, curl tests) cover common cases, but the referenced examples/memory_tools.py file does not exist in the bundle and the memory_tools factory shows elided '...' bodies.	4 / 5
Workflow Clarity	Clear sequenced flow (prereqs -> configure -> init tables -> deploy -> test) with a first-time checklist and a troubleshooting error-recovery table, though validation is documented as a separate testing section rather than an explicit gate inside the deploy flow.	4 / 5
Progressive Disclosure	Well-sectioned with headers and tables, but it is a monolithic single file with config/troubleshooting/testing content inlined that could live in separate reference files, and it points to a non-existent examples/memory_tools.py.	3 / 5
	Total	14 / 20 Passed

Description

83%Weight 40%Scale 1-5

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 that pairs a clear capability statement with an explicit, numbered 'Use when' trigger list containing natural user language. It is well above the completeness cap and distinct within its niche, with only minor gaps in action specificity and trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ('Add memory capabilities') plus several concrete actions via the use-case list ('persist conversations or user preferences', 'checkpointing or long-term storage'), with minor gaps in coverage such as recall/delete.	4 / 5
Completeness	Clearly answers 'what' ('Add memory capabilities to your agent') and explicitly answers 'when' with three numbered, concrete trigger phrases — above the anchor-4 bar whose 'when' could still be more explicit.	5 / 5
Trigger Term Quality	Includes natural user phrases quoted directly ('memory', 'state', 'remember', 'conversation history') with good synonym coverage, though a few natural variations like 'recall' or 'forget' are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear agent-memory niche with distinct triggers; minor overlap risk with sibling agent-state skills via broad terms like 'state'.	4 / 5
	Total	17 / 20 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
Path: .claude/skills/agent-langgraph-memory/SKILL.md
Commit: fdc1b49

Reviewed: 1 day 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.