Name: agent-memory
Rating: 66.4 (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

79%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/agent-langgraph-memory/SKILL.md

Quality

Content

77%

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

This is a comprehensive, highly actionable skill with excellent workflow clarity including a setup checklist, troubleshooting table, and clear step sequencing. Its main weakness is length—at ~300 lines it could be more concise by trimming the Key Principles section and moving detailed configuration/testing into referenced files. The progressive disclosure is decent with cross-skill references but the monolithic body undermines it.

Suggestions

Move the detailed Configuration Files (Steps 1-3) and Testing Memory sections into separate referenced files to reduce the main skill body length

Condense the Key Principles section—patterns 3-5 (error handling, JSON validation, config passing) could be shown once in the Complete Example rather than explained separately then shown again

Dimension	Reasoning	Score
Conciseness	The skill is quite long (~300 lines) with some redundancy—the Quick Setup Summary table duplicates information detailed later, and the Key Principles section explains patterns that could be more concise. However, most content is genuinely instructive and not explaining things Claude already knows.	2 / 3
Actionability	The skill provides fully executable code snippets throughout: complete Python implementations, exact YAML configurations, curl commands for testing, and a one-liner for table initialization. Code is copy-paste ready with specific library imports and parameters.	3 / 3
Workflow Clarity	The multi-step process is clearly sequenced across configuration files (Steps 1-3), with an explicit first-time setup checklist, table initialization before deploy, and a troubleshooting table for error recovery. Validation is addressed through the testing section and the checklist ensures no steps are missed.	3 / 3
Progressive Disclosure	The skill references external skills (lakebase-setup, deploy, run-locally) and links to GitHub templates, which is good. However, the body itself is quite long and could benefit from splitting detailed configuration and testing sections into separate files. The reference to 'examples/memory_tools.py' is good but no bundle files were provided to verify it exists.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 reasonably well-structured description with a clear 'Use when' clause and good trigger term coverage. Its main weakness is that the 'what' portion is somewhat vague—'add memory capabilities' doesn't specify concrete actions like storing/retrieving memories, configuring storage backends, or managing conversation windows. The description also uses second person ('your agent') which is a minor style issue but not penalized as heavily as first person.

Suggestions

Make the 'what' portion more specific by listing concrete actions, e.g., 'Store and retrieve conversation history, persist user preferences across sessions, implement checkpointing for long-running agent tasks.'

Improve distinctiveness by specifying the technology or framework context (e.g., 'LangChain memory', 'agent framework') to reduce overlap with general database or caching skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('memory capabilities') and some actions like 'persist conversations', 'adding checkpointing', 'long-term storage', but doesn't list concrete specific actions (e.g., what APIs, what data structures, what storage backends). It's more of a feature category than a list of concrete operations.	2 / 3
Completeness	Clearly answers both 'what' (add memory capabilities to your agent) and 'when' with an explicit 'Use when:' clause listing three specific trigger scenarios. The when clause is well-structured with numbered conditions.	3 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'memory', 'state', 'remember', 'conversation history', 'persist conversations', 'user preferences', 'checkpointing', 'long-term storage'. These cover a good range of terms a user might naturally use.	3 / 3
Distinctiveness Conflict Risk	'Memory capabilities' and 'state' could overlap with other skills related to caching, database management, or session handling. While the trigger terms like 'conversation history' and 'checkpointing' help narrow the scope, 'state' and 'remember' are broad enough to potentially conflict with other skills.	2 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: databricks/app-templates
Commit: 2302cd3

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.